METHOD AND SYSTEM TO DETERMINE STRENGTH OF GREEN WOOD PRODUCTS USING NEAR INFRARED IMAGING

Abstract

Near InfraRed NIR technology, including NIR cameras and detectors, is used to accurately determine the strength of the green veneer sheet or other wood product. Based on the determined strength for a given green veneer sheet or other wood product, one or more actions are taken with respect to green veneer sheet or other wood product to ensure the green veneer sheet or other wood product is put the most efficient, effective, and valuable use.

Claims

1. A method for determining strength of green wood products comprising: generating strength analysis models and/or mechanical properties model data for green wood products; providing a NIR green wood product strength analysis system, including at least one NIR green wood product strength analysis station; analyzing a green wood product using the NIR green wood product strength analysis station; and assigning a grade to the green wood product based, at least in part, on the analysis of the green wood product using the NIR green wood product strength analysis station.

2. The method of claim 1 wherein the green wood product is a green ribbon of veneer.

3. The method of claim 2 wherein analyzing the green veneer ribbon using the NIR green wood product strength analysis station includes: passing the green veneer ribbon through the NIR green wood product strength analysis station; illuminating the green veneer ribbon with one or more illumination sources; obtaining NIR reflectance spectrum data for the illuminated green veneer ribbon using one or more NIR/SWIR cameras; processing the NIR reflectance spectrum data using the strength analysis models and/or mechanical properties model data for green wood products; and assigning a grade to green veneer sheets cut from the green veneer ribbon based, at least in part, on the analysis of the green veneer ribbon using the NIR green wood product strength analysis station.

4. The method of claim 2 wherein the one or more sources of illumination include one or more LED light sources.

5. The method of claim 2 wherein the one or more illumination sources operate at a reduced spectral range of 650 and 1050 nm.

6. The method of claim 2 further comprising: taking one or more actions with respect to the green veneer sheets based, at least in part, on the grade assigned to the green veneer sheets.

7. The method of claim 6 wherein the one or more actions taken with respect to the green veneer sheets include: sorting the green veneer sheets into a bin, location or stack associated with the assigned grade; restricting the use of the green veneer sheets based on the grade assigned to the green veneer sheets; rejecting the green veneer sheets based on the grade assigned to the green veneer sheets; sending the green veneer sheets back for further processing based on the grade assigned to the green veneer sheets; adjusting one or more processing parameters of a production line based, at least in part, on the grade assigned to the green wood product/veneer sheets; and selecting a type and amounts of glues used on a production line based, at least in part, on grade assigned to the green wood product/veneer sheets.

8. The method of claim 2 further comprising: drying the graded green veneer sheets to create the dry graded green veneer sheets; generating a moisture level to greyscale mapping database, the moisture level to greyscale mapping database containing data that maps moisture level to Near InfraRed (NIR) image greyscale values for one or more wood products; providing the dry graded green veneer sheets to a NIR analysis station for detecting moisture levels in the dry graded green veneer sheets, the NIR analysis station including one or more sources of illumination positioned to illuminate a surface of the dry graded green veneer sheets, the NIR analysis station including one or more NIR cameras positioned to capture one or more NIR images of the illuminated surface of the dry graded green veneer sheets; positioning a dry graded green veneer sheet to be analyzed in the NIR analysis station such that a first surface of the dry graded green veneer sheet to be analyzed is illuminated by the one or more illumination sources; capturing, using the one or more NIR cameras, one or more NIR images of the illuminated first surface of the dry graded green veneer sheet; processing the one or more NIR images of the illuminated first surface of the dry graded green veneer sheet to generate NIR greyscale images indicating different moisture levels in the illuminated first surface of the dry graded green veneer sheet; processing the NIR greyscale images using the moisture level to greyscale mapping database to identify moisture levels for the first surface of the dry graded green veneer sheet; assigning a grade to the dry graded green veneer sheet based on the identified moisture levels for the first surface of the dry graded green veneer sheet; and based, at least in part, on the grade assigned to the dry graded green veneer sheet, taking one or more actions with respect to the dry graded green veneer sheet.

9. The method of claim 8 wherein the one or more actions taken with respect to the dry graded green veneer sheet include: sorting the dry graded green veneer sheets into a bin, location or stack associated with the assigned grade; restricting the use of the dry graded green veneer sheets based on the grade assigned to the dry graded green veneer sheets; rejecting the dry graded green veneer sheets based on the grade assigned to the dry graded green veneer sheets; sending the dry graded green veneer sheets back for further processing based on the grade assigned to the dry graded green veneer sheets; adjusting one or more processing parameters of a production line based, at least in part, on the grade assigned to the dry graded green veneer sheets; and selecting a type and amounts of glues used on a production line based, at least in part, on grade assigned to the dry graded green veneer sheets.

10. A system for determining strength of green wood products comprising: strength analysis models and/or mechanical properties model data for green wood products; a NIR green wood product strength analysis system, including at least one NIR green wood product strength analysis station; a green wood product, the green wood product being provided to the NIR green wood product strength analysis station to be analyzed using the NIR green wood product strength analysis station; and green wood product grade data assigned to the green wood product based, at least in part, on the analysis of the green wood product using the NIR green wood product strength analysis station.

11. The system of claim 10 wherein the green wood product is a green ribbon of veneer.

12. The system of claim 11 wherein the green veneer ribbon is analyzed using the NIR green wood product strength analysis station by: passing the green veneer ribbon through the NIR green wood product strength analysis station; illuminating the green veneer ribbon with one or more illumination sources; obtaining NIR reflectance spectrum data for the illuminated green veneer ribbon using one or more NIR/SWIR cameras; processing the NIR reflectance spectrum data using the strength analysis models and/or mechanical properties model data for green wood products; and generating grade data representing a grade assigned to green veneer sheets cut from the green veneer ribbon based, at least in part, on the analysis of the green veneer ribbon using the NIR green wood product strength analysis station.

13. The system of claim 12 wherein the one or more sources of illumination include one or more LED light sources.

14. The system of claim 12 wherein the one or more illumination sources operate at a reduced spectral range of 650 and 1050 nm.

15. The system of claim 12 further wherein one or more actions are taken with respect to the green veneer sheets based, at least in part, on the grade assigned to the green veneer sheets.

16. The system of claim 15 wherein the one or more actions taken with respect to the green veneer sheets include: sorting the green wood product/veneer sheets into a bin, location or stack associated with the assigned grade; restricting the use of the green wood product/veneer sheets based on the grade assigned to the green wood product/veneer sheets; rejecting the green wood product/veneer sheets based on the grade assigned to the green wood product/veneer sheets; sending the green wood product/veneer sheets back for further processing based on the grade assigned to the green wood product/veneer sheets; adjusting one or more processing parameters of a production line based, at least in part, on the grade assigned to the green wood product/veneer sheets; and selecting a type and amounts of glues used on a production line based, at least in part, on grade assigned to the green wood product/veneer sheets.

17. A method for determining strength of green veneer ribbon comprising: generating strength analysis models and/or mechanical properties model data for green veneer ribbon; providing a NIR green veneer strength analysis system, including at least one NIR green wood product strength analysis station; analyzing green veneer ribbon using the NIR green wood product strength analysis station; cutting green veneer sheets from the green veneer ribbon; analyzing the green veneer sheets for moisture using one or more NIR analysis stations; and assigning a grade to the green veneer sheets based, at least in part, on the analysis of the green veneer ribbon using the NIR green wood product strength analysis station and the one or more NIR analysis stations.

18. The method of claim 17 wherein analyzing the green veneer ribbon using the NIR green wood product strength analysis station includes: passing the green veneer ribbon through the NIR green wood product strength analysis station; illuminating the green veneer ribbon with one or more illumination sources; obtaining NIR reflectance spectrum data for the illuminated green veneer ribbon using one or more NIR/SWIR cameras; processing the NIR reflectance spectrum data using the strength analysis models and/or mechanical properties model data for green wood products; and assigning a grade to green veneer sheets cut from the green veneer ribbon based, at least in part, on the analysis of the green veneer ribbon using the NIR green wood product strength analysis station.

19. The method of claim 18 wherein the one or more sources of illumination include one or more LED light sources.

20. The method of claim 18 wherein the one or more illumination sources operate at a reduced spectral range of 650 and 1050 nm.

Description

BRIEF DESCRIPTION OF THE DRAWINGS

[0134] The patent or application file contains at least one drawing executed in color. Copies of this patent or patent application publication with color drawing(s) will be provided by the Office upon request and payment of the necessary fee.

[0135] FIG. 1A is an illustration of one example of a prior art traditional contact electrode system.

[0136] FIG. 1B is an illustration of one example of a contact electrodes of a prior art traditional contact electrode structure.

[0137] FIG. 1C is a graphical representation of the placement and spacing of individual contact electrodes using a typical traditional contact electrode system.

[0138] FIG. 1D shows a typical sample sheet generated using traditional contact electrode systems and the physical arrangement of FIG. 1C.

[0139] FIG. 2A is an illustration of one example of a prior art traditional RF moisture detection system.

[0140] FIG. 2B shows a side view of an RF transmitter positioned above surface of a veneer sheet and an RF receiver positioned a distance below a surface of the veneer sheet.

[0141] FIG. 2C shows a graphic illustration of a typical arrangement of RF transmitters over a surface of a veneer sheet moving via conveyor belts, thereby creating sample channels.

[0142] FIG. 2D shows a sample sheet created using the RF transmitter arrangement shown in FIG. 2C.

[0143] FIG. 3A is simplified block diagram of a system for detecting moisture levels in a wood product using NIR technology in accordance with one embodiment.

[0144] FIG. 3B shows one example of a physical system for detecting moisture levels in a wood product using NIR technology in accordance with one embodiment.

[0145] FIG. 4A shows a first surface of a dry veneer sheet as seen in a visual image of the dry veneer sheet and as seen in an NIR greyscale image of the dry veneer sheet.

[0146] FIG. 4B shows a first surface of a veneer sheet, including a small moisture pocket, as seen in a visual image of the veneer sheet and as seen in an NIR greyscale image of the veneer sheet.

[0147] FIG. 4C shows a first surface of a veneer sheet, including a larger moisture pocket, as seen in a visual image of the veneer sheet and as seen in an NIR greyscale image of the veneer sheet.

[0148] FIG. 5 is flow chart of a process for detecting moisture levels in a wood product using NIR technology in accordance with one embodiment.

[0149] FIG. 6 is simplified block diagram of a system for detecting moisture levels in a wood product using NIR technology and visual data in accordance with one embodiment.

[0150] FIG. 7A shows a black and white visual image of a wood product first surface of a veneer sheet including physical features which, in this specific illustrative example, are knots and knot holes.

[0151] FIG. 7B shows a color visual image of the wood product first surface of the veneer sheet of FIG. 7A including physical features which, in this specific illustrative example, are knots and knot holes of FIG. 7A.

[0152] FIG. 7C shows a superimposed composite image of the wood product first surface the of the wood product including the visual images of the physical features of FIG. 7A or 7B with an NIR greyscale image including NIR greyscale images of high moisture superimposed.

[0153] FIG. 7D shows a color enhanced superimposed composite image of the wood product first surface the of the wood product of FIG. 7C.

[0154] FIG. 8 is flow chart of a process for detecting moisture levels in a wood product using NIR technology and visual data in accordance with one embodiment.

[0155] FIG. 9 is simplified block diagram of a system for detecting moisture levels in a wood product using NIR technology and machine learning methods in accordance with one embodiment.

[0156] FIG. 10 is a simplified block diagram of a process for determining the strength of a green wood product using NIR technology in accordance with one embodiment.

[0157] FIG. 11 is a simplified block diagram of a NIR green wood product strength analysis system using NIR technology in accordance with one embodiment.

[0158] FIG. 12 is a flow chart of a process for determining the strength of a green wood product using NIR technology in accordance with one embodiment.

[0159] FIG. 13 is a simplified block diagram of a process for determining the strength of a dry wood product using NIR technology in accordance with one embodiment.

[0160] FIG. 14 is a simplified block diagram of a NIR dry wood product strength analysis system in accordance with one embodiment.

[0161] FIG. 15 is a flow chart of a process for determining the strength of a dry wood product using NIR technology in accordance with one embodiment.

[0162] Common reference numerals are used throughout the figures and the detailed description to indicate like elements. One skilled in the art will readily recognize that the above figures are merely illustrative examples and that other architectures, modes of operation, orders of operation, and elements/functions can be provided and implemented without departing from the characteristics and features of the invention, as set forth in the claims.

DETAILED DESCRIPTION

[0163] Embodiments will now be discussed with reference to the accompanying figures, which depict one or more exemplary embodiments. Embodiments may be implemented in many different forms and should not be construed as limited to the embodiments set forth herein, shown in the figures, or described below. Rather, these exemplary embodiments are provided to allow a complete disclosure that conveys the principles of the invention, as set forth in the claims, to those of skill in the art.

[0164] Embodiments of the present disclosure utilize Near InfraRed (NIR) technology, including Near InfraRed/Short Wave InfraRed (NIR/SWIR) cameras and detectors, to accurately identify moisture content, the specific locations of the moisture in a veneer sheet or other wood product, and the strength of the wood product. In addition, embodiments of the present disclosure utilize Near InfraRed (NIR) technology, including Near InfraRed/Short Wave InfraRed (NIR/SWIR) cameras and detectors,

[0165] As discussed in more detail below, using some disclosed embodiments accurate identification of moisture is accomplished by providing a NIR analysis station for the identification of moisture including one or more illumination sources and one or more NIR cameras.

[0166] A wood product, such as a veneer sheet is then positioned in, and/or is passed through, the NIR analysis station. At the NIR analysis station an entire first surface of the veneer sheet or other wood product to be analyzed is illuminated by the one or more illumination sources and the one or more NIR cameras are used to capture one or more NIR images of the illuminated surface of the veneer sheet or other wood product.

[0167] The one or more NIR images of entire first surface of the veneer sheet or other wood product are then analyzed and moisture levels over the entire first surface of the veneer sheet or other wood product are identified. In one example, this is accomplished with the aid of a moisture level to greyscale mapping database containing empirical data. In another embodiment, this is accomplished using the greyscale mapping database containing empirical data and a greyscale to color mapping database. In another embodiment, this is accomplished using one or more machine learning based models.

[0168] Once the moisture levels over the entire first surface of the veneer sheet or other wood product are identified, a grade is assigned to the wood product based on the identified moisture levels for the wood product and based, at least in part, on the grade assigned to the wood product, one or more actions are taken with respect to the wood product.

[0169] The one or more actions can include one or more of: sorting the wood product into a bin/location associated with the grade assigned to the wood product; restricting the use of the wood product based on grade assigned to the wood product; rejecting the wood product based on the grade assigned to the wood product; sending the wood product back for further processing based on the grade assigned to the wood product; adjusting one or more processing parameters of a production line based on grades assigned to one or more wood products; adjusting drying temperatures on a production line based on grades assigned to one or more wood products; and adjusting drying times on a production line based on grades assigned to one or more wood products.

[0170] As also discussed in more detail below, using some disclosed embodiments, strength determination is accomplished by providing, one or more NIR green strength analysis systems, including one or more NIR green wood product strength analysis stations. In one embodiment, before moisture analysis is performed, the green veneer sheet, ribbon, or other wood product to be analyzed is positioned in, or passed through, the NIR green wood product strength analysis station such that a surface of the green veneer sheet or other wood product to be analyzed is illuminated by the one or more illumination sources. In one embodiment, the green veneer ribbon or sheet to be analyzed is passed from a log peeling/veneer creation mechanism to the NIR green wood product strength analysis station.

[0171] In one embodiment, the NIR green wood product strength analysis stations include one or more NIR/SWIR cameras, hereafter referred to as simply NIR cameras, positioned to capture one or more NIR images of the illuminated surface of the veneer sheet or other wood product. In one embodiment, the one or more NIR cameras of the NIR green wood product strength analysis stations are then used to capture one or more NIR images of the illuminated surface of the green veneer sheet or other wood product.

[0172] In some embodiments, strength analysis models are created, and the data obtained from NIR images can be correlated with the strength properties of the green wood product using these models.

[0173] It has been found that these correlations apply to moving ribbons and/or sheets of veneer using a reduced spectral range. Consequently, in one embodiment, the one or more sources of illumination positioned to illuminate at least one surface of a veneer sheet or other wood product are selected to provide a reduced spectral range, in one embodiment between 650 and 1050 nm. This enables very rapid collection of the NIR spectra. This rapid collection is required for the evaluation of veneer in the manufacturing process.

[0174] In one embodiment, a veneer sheet or other wood product to be analyzed is positioned in, or passed through, NIR green wood product strength analysis station such that a surface of the veneer sheet or other wood product to be analyzed is illuminated by the one or more illumination sources. The one or more NIR cameras are then used to capture one or more NIR images of the illuminated surface of the veneer sheet or other wood product including NIR reflectance spectrum data.

[0175] In one embodiment, a reduced spectral range between 650 and 1050 nm is utilized to enable very rapid collection of the NIR data including NIR reflectance spectrum data. This rapid collection is required for the evaluation of veneer in the manufacturing process.

[0176] In one embodiment, the NIR reflectance spectrum data is provided to a processor for comparing and analyzing the NIR reflectance spectrum data using the one or more strength models and/or machine learning modules.

[0177] In one embodiment, secondary NIR green strength data processing is used for analysis of green wood products to compensate for the strong absorbance bands of water/moisture in the NIR region.

[0178] As discussed in more detail below, in various embodiments, different methods can be used to correlate the NIR data, i.e., NIR reflectance spectrum data, of a green wood product to a selected property of that green wood product to create the strength models and/or machine learning modules.

[0179] Consequently, using the disclosed NIR green strength analysis it is possible to collect high quality NIR spectra of wood products, including full size ribbons and/or sheets of green veneer, that contain information and data regarding the mechanical properties of wood product, including the strength of the wood product.

[0180] In one embodiment, a grade is assigned to the green wood product based on the determined strength of the green wood product based. Then, based at least in part on the grade assigned to the green wood product, one or more actions are taken with respect to the wood product.

[0181] Consequently, some disclosed embodiments use NIR technology to predict the strength of a sheet of veneer from the NIR spectra of green veneer. This allows for the gradings and sorting of green veneer before drying and moisture analysis to provide enhanced grading technology and more accurate wood product grading.

[0182] As also discussed in more detail below, using some disclosed embodiments strength determination is accomplished by providing one or more NIR dry strength analysis systems, including one or more NIR dry wood product strength analysis stations. In one embodiment, a dry veneer sheet or other wood product to be analyzed is positioned in, or passed through, the NIR dry wood product strength analysis station such that a surface of the dry veneer sheet or other wood product to be analyzed is illuminated by the one or more illumination sources.

[0183] In one embodiment, the dry veneer sheet or other wood product to be analyzed is passed from one of the NIR analysis stations discussed above used for moisture analysis after the moisture analysis is performed. In some embodiments, the NIR analysis stations discussed above used for moisture analysis and the NIR dry wood product strength analysis station are located at the same NIR analysis station.

[0184] In one embodiment, the disclosed NIR dry wood product strength analysis system includes one or more NIR dry wood product strength analysis stations. In one embodiment, the NIR dry wood product strength analysis stations include one or more sources of illumination positioned to illuminate at least one surface of a dry veneer sheet or other wood product. In one embodiment, the sources of illumination are selected to provide a reduced spectral range between 650 and 1050 nm. This enables very rapid collection of the NIR spectra. This rapid collection is required for the evaluation of veneer in the manufacturing process.

[0185] In one embodiment, the NIR dry wood product strength analysis stations include one or more NIR/SWIR cameras, hereafter referred to as simply NIR cameras, positioned to capture one or more NIR images of the illuminated surface of the veneer sheet or other wood product. In one embodiment, the one or more NIR cameras of the NIR dry wood product strength analysis stations are then used to capture one or more NIR images of the illuminated surface of the dry veneer sheet or other wood product.

[0186] In some embodiments, strength analysis models are created, and the data obtained from NIR images can be correlated with the strength properties of the wood product using these models. It has been found that these correlations apply to moving 4 ft. by 8 ft. sheets of veneer using a reduced spectral range.

[0187] In one embodiment, a veneer sheet or other wood product to be analyzed is positioned in, or passed through, the NIR dry wood product strength analysis station such that a surface of the veneer sheet or other wood product to be analyzed is illuminated by the one or more illumination sources. The one or more NIR cameras are then used to capture one or more NIR images of the illuminated surface of the dry veneer sheet or other wood product including NIR reflectance spectrum data.

[0188] As noted, in one embodiment, a reduced spectral range between 650 and 1050 nm is analyzed to enable very rapid collection of the NIR reflectance spectrum data. This rapid collection is required for the evaluation of veneer in the manufacturing process.

[0189] In some embodiments, strength analysis models are created, and the data obtained from NIR images can be correlated with the strength properties of the wood product using these models. It has been found that these correlations apply to moving 4 ft. by 8 ft. sheets of veneer using a reduced spectral range.

[0190] In one embodiment, this NIR reflectance spectrum data is provided to a processor for comparing and analyzing the NIR reflectance spectrum data using one or more strength models and/or machine learning modules.

[0191] As discussed in more detail below, in various embodiments, different methods can be used to correlate the NIR strength data, i.e., NIR spectra, of a wood product to a selected property of that wood product to create the strength models and/or machine learning modules.

[0192] Consequently, using the disclosed NIR strength analysis it is possible to collect high quality NIR spectra of wood products, including full size sheets of green and dry veneer that contain information and data regarding the mechanical properties of wood product, including strength of the wood product.

[0193] In one embodiment, a grade is assigned to the dry wood product based on the determined strength of the dry wood product. Then, based at least in part on the grade assigned to the dry wood product, one or more actions are taken with respect to the wood product.

[0194] Consequently, some disclosed embodiments use NIR technology to predict the strength of a sheet of veneer from the NIR spectra of green and/or dry veneer. This allows for the gradings and sorting of green veneer before drying and moisture analysis and/or dry veneer after moisture analysis to provide enhanced grading technology and more accurate wood product grading.

[0195] Consequently, disclosed herein is an effective and efficient technical solution to the technical problem of accurately and efficiently detecting moisture level and moisture pockets in an entire sheet or surface of a wood product, such as veneer sheets or other wood products. In addition, since, in one embodiment, the disclosed embodiments use NIR cameras to take NIR images of an entire wood product surface the technical solution is capable of accurately analyzing an entire surface of a wood product, such as a veneer sheet, in a single pass. Consequently, the embodiments can be implemented without significantly slowing down the production process or increasing the cost of the finished wood product.

[0196] In addition, embodiments of the present disclosure provide an effective and efficient technical solution to the technical problem of providing a method and system for determining the strength of a wood product that is reliable, consistent, and economically feasible to implement.

[0197] FIG. 3A is simplified block diagram of one embodiment of a system 300 for detecting moisture levels in a wood product using NIR technology in accordance with one embodiment.

[0198] In one embodiment, system 300 for detecting moisture levels in wood products includes a production environment 301 and a computing environment 350.

[0199] As seen in FIG. 3A, production environment 301 includes NIR analysis station 320 and selected action implementation module 396. As seen in FIG. 3A, NIR analysis station 320 includes one or more illumination sources, such as illumination source 322, positioned to illuminate a surface of a wood product. In various embodiments, the one or more illumination sources, such as illumination source 322, can include one or more LED light sources. In other embodiments, the one or more illumination sources, such as illumination source 322, can include, but are not limited to, halogen, halogen and tungsten light sources, or any other light sources, as discussed herein, and/or as known in the art at the time of filing, and/or as developed after the time of filing.

[0200] As seen in FIG. 3A, NIR analysis station 320 also includes one or more NIR cameras, such as NIR camera 324, positioned to capture NIR image data 362 representing one or more NIR images of the illuminated surface of the wood product. In one embodiment, the one or more NIR cameras, such as NIR camera 324, are adjustably positioned and adjustably focused to capture any desired one or more NIR images of the illuminated surface of the wood product.

[0201] As used herein, the terms Near InfraRed (NIR) and Short-Wave InfraRed (SWIR) are used interchangeably to include wavelength in the range of 750 nanometers (nm) to 3500 nm. In addition, all stated wave lengths herein are assumed to include values within 10% of the stated value.

[0202] As seen in FIG. 3A, and as discussed below, a wood product 330 to be analyzed in the NIR analysis station 320 is positioned in NIR analysis station 320. In various embodiments, the wood product 330 can be any wood product as discussed herein, and/or as known in the art at the time of filing and/or as becomes known after the time of filing. In one embodiment, the wood product 330 to be analyzed is a veneer sheet.

[0203] In one embodiment, the wood product 330 to be analyzed is positioned such that a wood product first surface 332 of the wood product 330 to be analyzed is illuminated by the illumination source 322 and the entire wood product first surface 332 is within view and focus of NIR camera 324. In one embodiment, the wood product 330 is positioned in the NIR analysis station 320 by passing the wood product 330 through the NIR analysis station 320 on a conveyor system (not shown in FIG. 3A but shown as 321 in FIG. 3B and discussed below).

[0204] In various embodiments, the one or more NIR cameras, such as NIR camera 324, can be of any resolution desired. As noted above, when the one or more NIR cameras, such as NIR camera 324, are used to scan the wood product first surface 332 of a wood product 330 for moisture and create an NIR image data 362 of the wood product first surface 332, essentially each pixel generated by NIR camera 324 is a sample point. Consequently, the resolution and accuracy of the moisture detection process is only limited by the number of pixels the NIR camera 324 has covering the field of view, e.g., the entire wood product first surface 332 of wood product 330. Consequently, in the case where NIR camera 324 is a 1.3 mega pixel camera, there are essentially 1,300,000 individual measurement points on the wood product first surface 332. Consequently, using NIR cameras, such as NIR camera 324, results in resolutions and accuracy that simply cannot be achieved using traditional moisture detection systems such as traditional contact electrode systems or RF moisture detection systems.

[0205] As seen in FIG. 3A, computing environment 350 includes computing system 352. As seen in FIG. 3A, in one embodiment, computing system 352 includes moisture to greyscale mapping database 310 containing mapping data 312 that maps moisture level to Near InfraRed (NIR) image greyscale values for one or more wood products.

[0206] Using NIR images, extremely granular differences in moisture levels can be detected. In general, locations with different levels of moisture absorb/reflect different amounts of NIR radiation at specific frequencies. For moisture detection the NIR frequencies of 1450 nm, 1900 nm and 2400 nm are found to yield the best results.

[0207] In operation, when NIR radiation of a given frequency is applied to a wood product first surface 332 of wood product 330, more NIR energy is absorbed at locations having moisture than those that are dry, with greater amounts of NIR energy being absorbed at locations having greater moisture. When the NIR camera 324 takes an image of the wood product first surface 332, the NIR camera 324 picks up the NIR energy reflected off wood product first surface 332. Consequently, when the NIR camera 324 takes an image of the wood product first surface 332, the areas of moisture, which absorb more NIR energy and therefore reflect less NIR energy, appear darker than dry areas. In addition, the more moisture that is present the darker the area appears because less NIR energy is reflected to be captured by the NIR camera 324.

[0208] Using this fact, NIR image data 362 captured by the NIR camera 324 can be processed into NIR greyscale image data 364. Greyscale images can be of varying resolution, or bit, types. A 16-bit integer grayscale image provides 65535 available tonal steps from 0 (black) to 65535 (white). A 32-bit integer grayscale image theoretically will provide 4,294,967,295 tonal steps from 0 (black) to 4294967295 (white). Converting an NIR image based on these number of greyscale tonal steps results in a margin of error of significantly less than 0.1%. This is in sharp contrast to the ±7.5% margin of error obtained using traditional moisture detection systems such as traditional contact electrode systems or RF moisture detection systems.

[0209] Using these facts, in one embodiment, the mapping data 312 is obtained through one or more empirical and/or manual processes. For instance, in one embodiment, sample wood products are first dried in a kiln or similar environment while the weight of the sample wood product is monitored. As the sample wood product dries, i.e., loses moisture, the weight of the sample wood product deceases. Once the weight of the wood product stabilizes for a defined period, such as 24 hours, the sample wood product is determined to contain minimal moisture.

[0210] Then the sample wood product is brought up in moisture content in defined increments, such as one percent of the dry sample wood product weight. At each increment, an NIR image of the sample wood product is taken and the greyscale value at that increment of moisture is determined. The greyscale value determined is then correlated to the specific moisture level at that increment.

[0211] This process is continued for multiple increments until a maximum moisture content is obtained and greyscale data for each increment is determined and correlated to the respective moisture content increment. In this way, mapping data 312 mapping each specific moisture content to specific greyscale values is generated for the sample wood product. The process can then be repeated for different wood products, different types of wood, and under varying parameters and conditions.

[0212] As seen in FIG. 3A, computing system 352 also includes physical memory 360. In one embodiment, the physical memory 360 includes NIR image data 362 representing one or more NIR images of the illuminated wood product first surface 332 of the wood product 330 captured using NIR camera 324.

[0213] As seen in FIG. 3A, in one embodiment, computing system 352 includes one or more processors 370 for processing the NIR image data representing one or more NIR images of the illuminated wood product first surface 332 of the wood product 330 to generate NIR greyscale image data 364 indicating different moisture levels in the illuminated wood product first surface 332 of the wood product 330.

[0214] In one embodiment, processor 370 processes the NIR greyscale image data 364 using the mapping data 312 from moisture to greyscale mapping database 310 to identify moisture levels for the wood product first surface 332 of the wood product 330.

[0215] As seen in FIG. 3A, in one embodiment, computing system 352 includes a grade assignment module 380 for assigning a grade to the wood product 330 based on the identified moisture levels for the wood product first surface 332. As seen in FIG. 3A, grade assignment module 380 includes moisture analysis module 374 which, along with processor 370, processes the NIR greyscale image data 364 using the mapping data 312 from moisture to greyscale mapping database 310 data to identify moisture levels for the wood product first surface 332 of the wood product 330. As a result of the processing by moisture analysis module 374 and processor 370, grade assignment data 382 is generated.

[0216] As seen in FIG. 3A, in one embodiment, grade assignment data 382 is provided to action selection and activation module 390 which selects an appropriate action of the actions represented in available actions data 392 based, at least in part on the grade indicated by grade assignment data 382. As seen in FIG. 3A, in one embodiment, the determined appropriate action is represented by selected action data 394.

[0217] As seen in FIG. 3A, in one embodiment, selected action data 394 is forwarded to an action activation module such as selected action implementation module 396 in production environment 301 to initialize one or more actions with respect to the wood product 330 based, at least in part, on the grade represented by grade assignment data 382 and assigned to the wood product 330 by action selection and activation module 390.

[0218] In one embodiment, one or more actions that can be taken represented in available actions data 392 include, but are not limited to: sorting the wood product 330 into a bin or location associated with the grade represented by grade assignment data 382 and assigned to the wood product 330; restricting the use of the wood product 330 based on the grade represented by grade assignment data 382 and assigned to the wood product 330; rejecting the wood product 330 based on the grade represented by grade assignment data 382 and assigned to the wood product 330; sending the wood product 330 back for further processing based on the grade represented by grade assignment data 382 and assigned to the wood product 330; adjusting one or more processing parameters of a production line in production environment 301 based, at least in part, on the grade represented by grade assignment data 382 and assigned to the wood product 330 and/or the grades assigned other wood products; adjusting drying temperatures on a production line in production environment 301 based, at least in part, on grade represented by grade assignment data 382 and assigned to the wood product 330 and/or the grades assigned other wood products; adjusting drying times on a production line in production environment 301 based, at least in part, on grade represented by grade assignment data 382 and assigned to the wood product 330 and/or the grades assigned other wood products; and selecting a type and amounts of glues used on a production line in production environment 301 based, at least in part, on grade represented by grade assignment data 382 and assigned to the wood product 330 and/or the grades assigned other wood products.

[0219] As a specific illustrative example a signal representing a grade assigned to the wood product 330 and/or the grades assigned other wood products can be provided to a wood product gluing station (not shown) in a production line so that a glue appropriate to adhere wood products having the assigned grade can be selected and made available to glue the wood product when it reaches the gluing station.

[0220] FIG. 3B shows one example of one embodiment of a physical system layout for detecting moisture levels in a wood product using NIR technology in accordance with one embodiment.

[0221] Referring to FIGS. 3A and 3B together, shown in FIG. 3B is a specific illustrative example of one embodiment of a physical production environment 301. As seen in FIG. 3B, in this in this specific illustrative example, production environment 301 includes NIR analysis station 320 and computing system 352.

[0222] As seen in FIG. 3B, NIR analysis station 320 includes illumination sources 322, in this specific illustrative embodiment two LED light sources, and NIR camera 324.

[0223] As seen in FIG. 3B, wood product 330, in this specific illustrative example a veneer sheet, is passed through NIR analysis station 320 via conveyor system 321 such that wood product first surface 332 is illuminated by illumination source 322. Then NIR camera 324 captures NIR image data 362 and forwards this data to computing system 352 for processing as discussed above.

[0224] Those of skill in the art will ready recognize that the specific illustrative examples of one embodiment of a production environment 301 and components shown in FIGS. 3A and 3B are but specific examples of numerous possible production environments and arrangement of physical components. Consequently, the specific illustrative example of embodiments of a production environment 301 and components shown in FIGS. 3A and 3B is not intended to limit the scope of the invention as set forth in the claims below.

[0225] FIGS. 4A, 4B, and 4C are specific illustrative examples of the operation of part of the system 300 for moisture detection of FIG. 3A. FIG. 4A shows a first surface 332 of a veneer sheet 330A as seen in a visual image 410 of the veneer sheet 330A and as seen in an NIR greyscale image 420 of the veneer sheet 330A. In the example of FIG. 4A, veneer sheet 330A has an average moisture level that is less than 5% and is therefore considered a dry veneer sheet.

[0226] It is worth noting that visual image 410 and NIR greyscale image 420 can be images of the entire wood product first surface 332 of veneer sheet 330A, i.e., can be a 4′×8′ sample. In addition, as noted above, using a standard 1.3 mega pixel camera to obtain NIR greyscale image 420 of the entire wood product first surface 332 of veneer sheet 330A there are as many as 1,300,000 data points, i.e., each pixel is a data point. This, in turn, gives rise to very high resolution and is in sharp contrast to the 128 9″×3″ samples of traditional contact electrode systems or 32 12″×12″ samples of traditional RF systems that, as discussed above, yielded ±5.0% or ±7.5% margins of error, respectively.

[0227] As seen in FIG. 4A, the visual image 410 of the wood product first surface 332 of veneer sheet 330A is relatively uniform in appearance and coloration, i.e., no moisture can be readily detected visually in visual image 410 of the wood product first surface 332 of veneer sheet 330A. Likewise, since in this specific example veneer sheet 330A is a dry veneer sheet, the NIR greyscale image 420 of wood product first surface 332 of veneer sheet 330A is also relatively uniform in appearance and greyscale coloration.

[0228] FIG. 4B shows a first surface 332 of a veneer sheet 330B as seen in a visual image 430 of the veneer sheet 330B and as seen in an NIR greyscale image 440 of the veneer sheet 330B. In the example of FIG. 4B, veneer sheet 330B has an average moisture level that is less than 6% but includes a very high moisture pocket 490.

[0229] It is again worth noting that visual image 430 and NIR greyscale image 440 can be images of the entire wood product first surface 332 of veneer sheet 330B, i.e., can be a 4′×8′ sample. In addition, as noted above, using a standard 1.3 mega pixel camera to obtain NIR greyscale image 440 of the entire wood product first surface 332 of veneer sheet 330B there are as many as 1,300,000 data points, i.e., each pixel is a data point. This, in turn, gives rise to resolutions unheard of using traditional moisture detection systems and accuracy previously unknown in the art.

[0230] This is in sharp contrast to the 128 9″×3″ samples of traditional contact electrode systems or the 32 12″×12″ samples of traditional RF systems that, as discussed above, yielded ±5.0% or ±7.5% margins of error, respectively. Indeed, using these traditional moisture detection systems, very high moisture pocket 490 could easily be missed or determined to be larger than it actually is because of these large sample sizes and large margins of error.

[0231] As seen in FIG. 4B, the visual image 430 of the wood product first surface 332 of veneer sheet 330B is relatively uniform in visual appearance and coloration, i.e., no moisture can be readily detected visually in visual image 430 of the wood product first surface 332 of veneer sheet 330B. However, in this specific example, NIR greyscale image 440 of wood product first surface 332 of veneer sheet 330B clearly shows very high moisture pocket 490 as a dark region of a higher greyscale value. Consequently, though virtually invisible to the eye, high moisture pocket 490 can readily be seen/detected in NIR greyscale image 440.

[0232] According to the disclosed embodiments, the level of moisture in very high moisture pocket 490 can then be determined by mapping the NIR greyscale image data 364 representing NIR greyscale image 440 and using the mapping data 312 from moisture to greyscale mapping database 310 to identify moisture levels for very high moisture pocket 490 and the wood product 330B.

[0233] Grade assignment module 380 can then assign a grade to the wood product 330B based on the identified moisture levels for very high moisture pocket 490 and the wood product 330B. As discussed above, action selection and activation module 390 can then select an appropriate action based, at least in part, on the grade indicated by grade assignment data 382.

[0234] FIG. 4C shows a first surface 332 of a veneer sheet 330C as seen in a visual image 450 of the veneer sheet 330C and as seen in an NIR greyscale image 460 of the veneer sheet 330C. In the example of FIG. 4C, veneer sheet 330C has an average moisture level that is less than 10% but includes a high moisture pocket 495.

[0235] As seen in FIG. 4C, the visual image 450 of the wood product first surface 332 of veneer sheet 330C is still relatively uniform in visual appearance and coloration, i.e., no moisture can be readily detected visually in visual image 450 of the wood product first surface 332 of veneer sheet 330C. However, in this specific example, NIR greyscale image 460 of wood product first surface 332 of veneer sheet 330C clearly shows high moisture pocket 495 as a dark region of a higher greyscale value than the surrounding areas. Consequently, though virtually invisible to the eye, high moisture pocket 495 can readily be seen/detected in NIR greyscale image 460.

[0236] According to the disclosed embodiments, the level of moisture in high moisture pocket 495 can then be determined by mapping the NIR greyscale image data 364 representing NIR greyscale image 460 and using the mapping data 312 from moisture to greyscale mapping database 310 to identify moisture levels for high moisture pocket 460 and wood product 330C.

[0237] Grade assignment module 380 can then assign a grade to the wood product 330C based on the identified moisture levels for high moisture pocket 495 and the wood product 330C. Action selection and activation module 390 can then select an appropriate action based, at least in part, on the grade indicated by grade assignment data 382.

[0238] Those of skill in the art will ready recognize that the specific illustrative examples of one embodiment of FIGS. 3A, 4A, 4B, and 4C are but specific examples of numerous possible production environments, arrangement of components, and images. Consequently, the specific illustrative examples of one embodiment shown in FIGS. 3A, 4A, 4B, and 4C are not intended to limit the scope of the invention as set forth in the claims below.

[0239] As a specific illustrative example of potential variations, in various embodiments, the NIR analysis station 320 can include one or more illumination sources 322 positioned to illuminate two or more surfaces of a wood product and one or more NIR cameras 324 positioned to capture one or more NIR images of the two or more illuminated surfaces of the wood product.

[0240] As a further specific illustrative example of variations possible, additional input data can be considered such as current ambient temperature and humidity. The combination of these parameters can be analyzed by an AI/ML algorithm to further refine the control process for material drying optimization and overall process efficiency.

[0241] As a another illustrative example of variations possible, multiple NIR cameras can be placed at one or more locations relative to the wood product to capture an image of the entire wood product or a portion of the wood product being subjected to moisture testing; such as at one or more of (i) above a wood product; (ii) below a wood product; (iii) at one or both sides of the wood product and/or at a position to capture an image of the product at an angle, such as at an angle of 20° to 45° (e.g. 30°) from either above or below the wood product or both. The multiple images captured from each of these cameras can be combined to form a composite image. This can smooth out any variations in detected moisture content from the actual moisture content that could be detected by capturing an image only from a single angle.

[0242] As another illustrative example of variations possible, multiple NIR cameras can be used and operated, for example, at respective different wavelengths from one another within this NIR range to provide more information about the moisture content of the wood product being analyzed. A specific more desirable wavelength at which the NIR cameras can be operated can be at one or more wavelengths in the range of, or in the range of about, from 1350 nm to 1550 nm. In some examples, the NIR camera can operate at a wavelength in the range of, or in the range of about, from 1400 nm to 1450 nm.

[0243] These and numerous other variations are possible and contemplated by the inventors to be within the scope of the invention as set forth in the claims below.

[0244] FIG. 3B shows one example of one embodiment of a physical system layout for detecting moisture levels in a wood product using NIR technology in accordance with one embodiment.

[0245] Those of skill in the art will ready recognize that the specific illustrative example of one embodiment of a physical production environment 301 and components shown in FIG. 3B is but one example of numerous possible production environments and arrangement of physical components. Consequently, the specific illustrative example of one embodiment of a physical production environment 301 and components shown in FIG. 3B is not intended to limit the scope of the invention as set forth in the claims below.

[0246] FIG. 5 is flow chart of a process 500 for detecting moisture levels in a wood product using NIR technology in accordance with one embodiment.

[0247] As seen in FIG. 5, process 500 begins at BEGIN operation 502 and then process proceeds to operation 504. In one embodiment, at operation 504 a moisture level to greyscale mapping database is generated such as any database discussed above with respect to FIGS. 3A and 3B. In one embodiment, the moisture level to greyscale mapping database contains mapping data that maps moisture level to Near InfraRed (NIR) image greyscale values for one or more wood products.

[0248] In one embodiment, the mapping data is obtained through one or more empirical and/or manual processes. In one embodiment, sample wood products as first dried in a kiln or similar environment while the weight of the sample wood product is monitored. As the sample wood product dries, i.e., loses moisture, the weight of the sample wood product deceases. Once the weight of the wood product stabilizes for a defined period, such as 24 hours, the sample wood product is determined to contain minimal moisture.

[0249] Then the sample wood product is brought up in moisture content in defined increments, such as one percent of the dry sample wood product weight. At each increment, an NIR image of the sample wood product is taken and the greyscale value at that increment of moisture is determined. The greyscale value determined is then correlated to the specific moisture level at that increment.

[0250] This process is continued for multiple increments until a maximum moisture content is obtained and greyscale data for each increment is determined and correlated to the respective moisture content increment. In this way, mapping data 312 mapping each specific moisture content to a specific greyscale value is generated for the sample wood product. The process can then be repeated for different wood products, different types of wood, and under varying parameters and conditions.

[0251] Once a moisture level to greyscale mapping database is generated at operation 504, process flow proceeds to operation 506. At operation 506, an NIR analysis station is provided. In one embodiment, the NIR analysis station is substantially similar to any NIR analysis station discussed above with respect to FIGS. 3A and 3B. As discussed above, in one embodiment, the NIR analysis station includes one or more sources of illumination positioned to illuminate a surface of a wood product and one or more NIR cameras positioned to capture one or more NIR images of the illuminated surface of the wood product.

[0252] Once an NIR analysis station is provided at operation 506, process flow proceeds to operation 508. In one embodiment, at operation 508, a wood product to be analyzed is positioned in the NIR analysis station of operation 506 such that a first surface of the wood product to be analyzed is illuminated by the one or more illumination sources using any of the methods and systems discussed above with respect to FIGS. 3A and 3B.

[0253] Once the wood product to be analyzed is positioned in the NIR analysis station at 508, process flow proceeds to operation 510. In one embodiment, at operation 510 the one or more NIR cameras of NIR analysis station take one or more NIR images of the illuminated first surface of the wood product using any of the methods and systems discussed above with respect to FIGS. 3A and 3B.

[0254] Once the one or more NIR cameras of NIR analysis station take one or more NIR images of the illuminated first surface of the wood product at operation 510, process flow proceeds to operation 512.

[0255] In one embodiment, at operation 512, the one or more NIR images of the illuminated first surface of the wood product of operation 510 are processed using any of the methods and systems discussed above with respect to FIGS. 3A and 3B, to generate NIR greyscale images indicating different moisture levels in the illuminated first surface of the wood product.

[0256] Once the one or more NIR images of the illuminated first surface of the wood product are processed to generate NIR greyscale images indicating different moisture levels in the illuminated first surface of the wood product at operation 512, process flow proceeds to operation 514.

[0257] In one embodiment, at operation 514, the NIR greyscale images are processed using the moisture level to greyscale mapping database to identify moisture levels for the first surface of the wood product by any of the methods and systems discussed above with respect to FIGS. 3A and 3B.

[0258] Once the NIR greyscale images are processed using the moisture level to greyscale mapping database to identify moisture levels for the first surface of the wood product at operation 514, process flow proceeds operation 516.

[0259] In one embodiment, at operation 516 a grade is assigned to the wood product based on the identified moisture levels for the first surface of the wood product using any of the methods and systems discussed above with respect to FIGS. 3A and 3B.

[0260] Once a grade is assigned to the wood product based on the identified moisture levels for the first surface of the wood product at operation 516, process flow proceeds to operation 518. In one embodiment, at operation 518, based, at least in part, on the grade assigned to the wood product, one or more actions are taken with respect to the wood product including any of the actions discussed above with respect to the methods and systems discussed above with respect to FIGS. 3A and 3B.

[0261] Once one or more actions with respect to the wood product at operation 518, process flow proceeds to END operation 524 where process 500 is exited to await new samples and/or data.

[0262] In some embodiments, one or more visual cameras are implemented along with the one or more NIR camera to provide the capability to generate superimposed image data representing a visual/NIR composite image of wood product and correlating moisture levels with physical features of the surfaces of the wood product.

[0263] FIG. 6 is simplified block diagram of one embodiment of a system 600 for detecting moisture levels in a wood product using NIR technology and visual data in accordance with one embodiment.

[0264] In one embodiment, system 600 for detecting moisture levels in wood products, like system 300 of FIG. 3A and FIG. 3B, includes a production environment 301 and a computing environment 350.

[0265] As seen in FIG. 6, as in system 300 of FIG. 3A and FIG. 3B, production environment 301 includes NIR analysis station 320 and selected action implementation module 396. As seen in FIG. 6, like system 300 of FIG. 3A and FIG. 3B, NIR analysis station 320 includes one or more illumination sources, such as illumination source 322, positioned to illuminate a wood product first surface 332 of a wood product 330. In various embodiments, the one or more sources of illumination can include one or more LED light sources. In other embodiments, the one or more illumination sources, such as illumination source 322, can include, but are not limited to, halogen or halogen and tungsten light sources, or any other light sources, as discussed herein, and/or as known in the art at the time of filing, and/or as developed after the time of filing.

[0266] As seen in FIG. 6, like system 300 of FIG. 3A and FIG. 3B, NIR analysis station 320 also includes one or more NIR cameras, such as NIR camera 324, positioned to capture NIR image data 362 representing one or more NIR images of the illuminated wood product first surface 332 of the wood product 330. In one embodiment, one or more NIR cameras, such as NIR camera 324, are adjustably positioned and adjustably focused to capture one or more NIR images of the illuminated wood product first surface 332 of the wood product 330.

[0267] However, unlike like system 300 of FIG. 3A and FIG. 3B, system 600 includes one or more visual cameras, such as visual camera 624, used to take visual images of wood product first surface 332 of wood product 330 and generate visual image data 662.

[0268] As discussed in more detail below, the combination of visual image data 662 and NIR image data 362 allows for the generation of superimposed image data 664 representing a visual/NIR composite image of wood product first surface 332 of wood product 330. The visual/NIR composite image of wood product first surface 332 of wood product 330 indicates not only the presence and location of moisture, as was done using system 300, but also the location of any physical features in wood product first surface 332 of wood product 330 and the physical proximity of these features to the moisture detected in wood product first surface 332 of wood product 330.

[0269] This can be an important capability because, as explained above, it is trapped pockets of moisture that, when heated, become vapor and cause the bulges and/or damage to the wood product structure as the vapor tires to expand and escape. However, if the detected moisture is physical proximate to an open physical feature, such as a knot, knot hole, or side of the wood product, then the open physical feature provides the vapor an avenue for escape without causing damage to wood product.

[0270] Consequently, by analyzing the visual/NIR composite image represented by superimposed image data 664, moisture pockets near an open physical feature that, absent the presence open physical feature would be a problem, can be identified and ignored.

[0271] As seen in FIG. 6, and as discussed below, a wood product 330 to be analyzed in the NIR analysis station 320 is positioned in NIR analysis station 320. In various embodiments, the wood product 330 can be any wood product as discussed herein, and/or as known in the art at the time of filing and/or as becomes known after the time of filing. In one embodiment, the wood product 330 to be analyzed is a veneer sheet.

[0272] In one embodiment, the wood product 330 to be analyzed is positioned such that a wood product first surface 332 of the wood product 330 to be analyzed is illuminated by the illumination source 322 and is within view and focus of NIR camera 324 and visual camera 624. In one embodiment, the wood product 330 is positioned in the NIR analysis station 320 by passing the wood product through the NIR analysis station 320 on a conveyor system (not shown in FIG. 6 but shown as 321 in FIG. 3B and discussed above).

[0273] As seen in FIG. 6, computing environment 350 includes computing system 352. As seen in FIG. 6, as with system 300 of FIGS. 3A and 3B, in one embodiment, computing system 352 includes moisture to greyscale mapping database 310 containing mapping data 312 that maps moisture level to Near InfraRed (NIR) image greyscale values for one or more wood products.

[0274] As seen in FIG. 6, as with system 300 of FIGS. 3A and 3B, computing system 352 includes physical memory 360. For use with system 600, physical memory 360 includes NIR image data 362 representing one or more NIR images of the illuminated wood product first surface 332 of the wood product 330 captured using NIR camera 324, visual image data 662 representing one or more visual images of the illuminated wood product first surface 332 of the wood product 330 captured using visual camera 624, and superimposed image data 664 representing a visual/NIR composite image of wood product first surface 332 of wood product 330, as discussed above.

[0275] As seen in FIG. 6, in one embodiment, computing system 352 includes one or more processors 370 for processing the NIR image data 362 representing one or more NIR images of the illuminated wood product first surface 332 of the wood product 330 to generate NIR greyscale image data 364 indicating different moisture levels in the illuminated wood product first surface 332 of the wood product 330.

[0276] In one embodiment, processor 370 processes the NIR greyscale image data 364 using the mapping data 312 from moisture to greyscale mapping database 310 data to identify moisture levels for the wood product first surface 332 of the wood product 330.

[0277] In the specific embodiment of FIG. 6, processors 370 also process visual image data 662 and NIR greyscale image data 364 to generate superimposed image data 664 representing a visual/NIR composite image of wood product first surface 332 of wood product 330, as discussed above.

[0278] FIG. 7A shows a black and white visual image 701 of a wood product first surface 732 of a veneer sheet 730. As seen in FIG. 7A, wood product first surface 732 includes physical features 712 which, in this specific illustrative example, are knots and knot holes.

[0279] FIG. 7B shows a color visual image 711 of wood product first surface 732 of veneer sheet 730, including physical features 712 which, as noted, in this specific illustrative example, are knots and knot holes.

[0280] FIG. 7C shows a superimposed composite image 721 of the wood product first surface 732 of the wood product 730. As seen in FIG. 7C, superimposed composite image 721 includes the visual images of physical features 712 of either black and white visual image 701 or color visual image 711. However, superimposed on these visual images is a NIR greyscale image including NIR greyscale images of high moisture pockets 750, 751, and 752.

[0281] The superimposed composite image 721 not only shows the areas of high moisture, i.e., high moisture pockets 750, 751, and 752, but also their proximity to physical features 712 which, in this specific illustrative example, are knots and knot holes. By analyzing the superimposed composite image 721, moisture pockets near an open physical feature, such as high moisture pockets 750 and 752 that, absent the presence open physical features/knots 712, would be a problem can be identified and ignored.

[0282] FIG. 7D shows a color enhanced superimposed composite image 731 that is created using a greyscale to color mapping database to provide even more pronounced visualization of the high moisture pockets 750, 751, and 752.

[0283] It is worth noting again that visual images 701, 711, 721, and 731 can be images of the entire wood product first surface 732 of veneer sheet 730, i.e., can be a 4′×8′ sample. In addition, as noted above, using a standard 1.3 mega pixel camera to obtain images 701, 711, 721, and 731 of the entire wood product first surface 732 of veneer sheet 730 there are as many as 1,300,000 data points, i.e., each pixel is a data point. This, in turn, gives rise to very high resolution and is in sharp contrast to the 128 9″×3″ samples of traditional contact electrode systems or 32 12″×12″ samples of traditional RF systems that, as discussed above, yielded ±5.0% or ±7.5% margins of error, respectively.

[0284] As seen in FIG. 6, in one embodiment, computing system 352 includes a grade assignment module 380 for assigning a grade to the wood product 330 based on the identified moisture levels and visual data of superimposed image data 664 for the wood product first surface 332. As seen in FIG. 3A, grade assignment module 380 includes moisture analysis module 374 which, along with processor 370, processes superimposed image data 664 for the wood product first surface 332 to identify moisture levels and open features for the wood product first surface 332 of the wood product 330. As a result of the processing by moisture analysis module 374 and processor 370, grade assignment data 382 is generated.

[0285] As seen in FIG. 6, in one embodiment, grade assignment data 382 is provided to action selection and activation module 390 which selects an appropriate action of the actions represented in available actions data 392 based, at least in part on the grade indicated by grade assignment data 382. As seen in FIG. 6, in one embodiment, the determined appropriate action is represented by selected action data 394.

[0286] As seen in FIG. 6, in one embodiment, selected action data 394 is forwarded to an action activation module such as selected action implementation module 396 in production environment 301 to initialize one or more actions with respect to the wood product 330 based, at least in part, on the grade represented by grade assignment data 382 and assigned to the wood product 330 by action selection and activation module 390.

[0287] In one embodiment, one or more actions that can be taken represented in available actions data 392 include, but are not limited to: sorting the wood product 330 into a bin or location associated with the grade represented by grade assignment data 382 and assigned to the wood product 330; restricting the use of the wood product 330 based on the grade represented by grade assignment data 382 and assigned to the wood product 330; rejecting the wood product 330 based on the grade represented by grade assignment data 382 and assigned to the wood product 330; sending the wood product 330 back for further processing based on the grade represented by grade assignment data 382 and assigned to the wood product 330; adjusting one or more processing parameters of a production line in production environment 301 based, at least in part, on the grade represented by grade assignment data 382 and assigned to the wood product 330 and/or the grades assigned other wood products; adjusting drying temperatures on a production line in production environment 301 based, at least in part, on grade represented by grade assignment data 382 and assigned to the wood product 330 and/or the grades assigned other wood products; adjusting drying times on a production line in production environment 301 based, at least in part, on grade represented by grade assignment data 382 and assigned to the wood product 330 and/or the grades assigned other wood products; and; and selecting a type and amounts of glues used on a production line in production environment 301 based, at least in part, on grade represented by grade assignment data 382 and assigned to the wood product 330 and/or the grades assigned other wood products.

[0288] Those of skill in the art will ready recognize that the specific illustrative examples of embodiments of FIGS. 6, 7A, 7B, 7C, and 7D are but specific example of numerous possible production environments, arrangement of components, and images. Consequently, the specific illustrative examples of embodiments of FIGS. 6, 7A, 7B, 7C, and 7D are not intended to limit the scope of the invention as set forth in the claims below.

[0289] As a specific illustrative example of potential variations, in various embodiments, the NIR analysis station 320 can include one or more illumination sources 322 positioned to illuminate two or more surfaces of a wood product and one or more NIR cameras 324 positioned to capture one or more NIR images of the two or more illuminated surfaces of the wood product. In one embodiment, one or visual cameras 624 can be positioned to capture one or more NIR images of the two or more illuminated surfaces of the wood product.

[0290] FIG. 8 is flow chart of a process 800 for detecting moisture levels in a wood product using NIR technology and visual data in accordance with one embodiment.

[0291] As seen in FIG. 8, process 800 begins at BEGIN operation 802 and then process proceeds to operation 804. In one embodiment, at operation 804 a moisture level to greyscale mapping database is generated such as any database discussed above with respect to FIGS. 3A, 3B and 6. In one embodiment, the moisture level to greyscale mapping database contains mapping data that maps moisture level to Near InfraRed (NIR) image greyscale values for one or more wood products.

[0292] Once a moisture level to greyscale mapping database is generated at operation 804, process flow proceeds to operation 806. At operation 806, an NIR analysis station is provided. In one embodiment, the NIR analysis station is substantially similar to any NIR analysis station discussed above with respect to FIGS. 3A, 3B, and 6. As discussed above, in one embodiment, the NIR analysis station includes one or more sources of illumination positioned to illuminate a surface of a wood product and one or more NIR cameras positioned to capture one or more NIR images of the illuminated surface of the wood product.

[0293] Returning to FIG. 8, once an NIR analysis station is provided at operation 806, process flow proceeds to operation 808. In one embodiment, at operation 808 a visual analysis station is provided including one or more visual image cameras such as any visual cameras discussed above with respect to FIG. 6. In one embodiment, one or more visual image cameras are adjustably positioned to capture visual images of the first surface of the wood product using any method or system as discussed above with respect to FIGS. 3A, 3B, and 6.

[0294] In one embodiment, once one or more visual image cameras are provided at operation 808, process flow proceeds to operation 810. In one embodiment, at operation 810, a wood product to be analyzed is positioned in the NIR analysis station of operation 806 such that a first surface of the wood product to be analyzed is illuminated by the one or more illumination sources using any of the methods and systems discussed above with respect to FIGS. 3A, 3B and 6.

[0295] Once the wood product to be analyzed is positioned in the NIR analysis station at operation 810, process flow proceeds to operation 812. In one embodiment, at operation 812 the one or more NIR cameras of NIR analysis station take one or more NIR images of the illuminated first surface of the wood product using any of the methods and systems discussed above with respect to FIGS. 3A, 3B and 6.

[0296] Once the one or more NIR cameras of NIR analysis station take one or more NIR images of the illuminated first surface of the wood product at operation 812, process flow proceeds to operation 814.

[0297] In one embodiment, at operation 814, the one or more NIR images of the illuminated first surface of the wood product of operation 812 are processed using any of the methods and systems discussed above with respect to FIGS. 3A, 3B and 6, to generate NIR greyscale images indicating different moisture levels in the illuminated first surface of the wood product.

[0298] Once the one or more NIR images of the illuminated first surface of the wood product are processed to generate NIR greyscale images indicating different moisture levels in the illuminated first surface of the wood product at operation 814, process flow proceeds to operation 816.

[0299] In one embodiment, at operation 816, the NIR greyscale images are processed using the moisture level to greyscale mapping database to identify moisture levels for the first surface of the wood product by using any of the methods and systems discussed above with respect to FIGS. 3A, 3B and 6.

[0300] Once the NIR greyscale images are processed using the moisture level to greyscale mapping database to identify moisture levels for the first surface of the wood product at operation 816, process flow proceeds operation 818.

[0301] In one embodiment, at operation 818, the wood product is positioned in the visual analysis station of operation 808 such that one or more visual images of the first surface of the wood product can be captured using the one or more visual image cameras of operation 808 and using any of the methods and systems discussed above with respect to FIGS. 3A, 3B and 6.

[0302] Once the wood product is positioned such that one or more visual images of the first surface of the wood product can be captured at operation 818, process flow proceeds to operation 820. In one embodiment at operation 820 one or more visual images of the first surface of the wood product are captured using the one or more visual image cameras of operation 808 and using any of the methods and systems discussed above with respect to FIGS. 3A, 3B and 6.

[0303] Once one or more visual images of the first surface of the wood product are captured at operation 820, process flow proceeds to operation 822. In one embodiment, at operation 822 the one or more NIR greyscale images and the one or more visual images of the first surface of the wood product are processed to generate NIR greyscale and visual superimposed images of the first surface of the wood product correlating different moisture levels and visual elements in the first surface of the wood product using any of the methods and systems discussed above with respect to FIGS. 3A, 3B and 6.

[0304] As noted above, the combination of visual image data and NIR image data allows for the generation of superimposed image data and a visual/NIR composite image of the wood product first surface. The visual/NIR composite image of the wood product first surface indicates not only the presence and location of moisture, as was done using process 500, but also the location of any physical features in wood product first surface of the wood product and the physical proximity of these features to the moisture detected in wood product first surface.

[0305] This can be critical feature because, as explained above, it is trapped pockets of moisture that, when heated, become vapor and cause the bulges and/or damage to the wood product structure as the vapor tires to expand and escape. However, if the detected moisture is physical proximate to open physical feature, such as a knot, knot hole, or side of the wood product, then the open physical feature provides the vapor an avenue for escape without causing damage to wood product.

[0306] Consequently, by analyzing the visual/NIR composite image represented by superimposed image data of operation 822 at operation 824 discussed below, moisture pockets near an open physical feature that, absent the presence of the open physical feature would be an issue, can be identified and ignored.

[0307] Once the one or more NIR greyscale images and the one or more visual images of the first surface of the wood product are processed to generate NIR greyscale and visual superimposed images of the first surface of the wood product correlating different moisture levels and visual elements in the first surface of the wood product at operation 822, process flow proceeds to operation 824.

[0308] In one embodiment, at operation 824 a grade is assigned to the wood product based on the identified moisture levels and visual elements in the first surface of the wood product using any of the methods and systems discussed above with respect to FIGS. 3A, 3B and 6.

[0309] Once a grade is assigned to the wood product based on the identified moisture levels and visual elements in the first surface of the wood product at operation 824, process flow proceeds to operation 826. In one embodiment, at operation 826, based, at least in part, on the grade assigned to the wood product, taking one or more actions with respect to the wood product including any of the actions discussed above with respect to the methods and systems discussed above with respect to FIGS. 3A, 3B and 6.

[0310] Once one or more actions with respect to the wood product at operation 818, process flow proceeds to END operation 834 where process 800 is exited to await new samples and/or data.

[0311] In some embodiments, machine leaning based models are used to predict moisture levels and behavior of wood products based on NIR image data for a wood product under analysis.

[0312] FIG. 9 is simplified block diagram of one embodiment of a system 900 for detecting moisture levels in a wood product using NIR technology and machine learning methods in accordance with one embodiment.

[0313] In one embodiment, system 900 for detecting moisture levels in wood products, like system 300 of FIGS. 3A and 3B, includes production environment 301 and a computing environment 350.

[0314] As seen in FIG. 9, like system 300 of FIGS. 3A and 3B, production environment 301 includes NIR analysis station 320 and selected action implementation module 396. As seen in FIG. 9, NIR analysis station 320 includes one or more illumination sources, such as illumination source 322, positioned to illuminate a wood product first surface 332 of a wood product 330. In various embodiments, the one or more sources of illumination, such as illumination source 322, can include one or more LED light sources. In other embodiments, the one or more illumination sources, such as illumination source 322, can include, but are not limited to, halogen or halogen and tungsten light sources, or any other light sources, as discussed herein, and/or as known in the art at the time of filing, and/or as developed after the time of filing.

[0315] As seen in FIG. 9, NIR analysis station 320 also includes one or more NIR cameras, such as NIR camera 324, positioned to capture NIR image data 362 representing one or more NIR images of the illuminated wood product first surface 332 of the wood product 330. In one embodiment, one or more NIR cameras, such as NIR camera 324, are adjustably positioned and adjustably focused to capture one or more NIR images of the illuminated wood product first surface 332 of the wood product 330.

[0316] As seen in FIG. 9, and as discussed below, the wood product 330 to be analyzed in the NIR analysis station 320 is positioned in NIR analysis station 320. In various embodiments, the wood product 330 can be any wood product as discussed herein, and/or as known in the art at the time of filing and/or as becomes known after the time of filing. In one embodiment, the wood product 330 to be analyzed is a veneer sheet.

[0317] In one embodiment, the wood product 330 to be analyzed is positioned such that the wood product first surface 332 of the wood product 330 to be analyzed is illuminated by the illumination source 322 and is within view and focus of NIR camera 324. In one embodiment, the wood product 330 is positioned in the NIR analysis station 320 by passing the wood product 330 through the NIR analysis station 320 on a conveyor system (not shown in FIG. 9 but shown as 321 in FIG. 3B and discussed below).

[0318] As seen in FIG. 9, like system 300 of FIGS. 3A and 3B, computing environment 350 includes computing system 352. However, unlike system 300 of FIGS. 3A and 3B, as seen in FIG. 9, in one embodiment, computing system 352 of system 900 does not include moisture to greyscale mapping database 310 but instead includes moisture prediction module 910.

[0319] In one embodiment, moisture prediction module 910 includes one or more trained Machine Learning (ML) based moisture level detection models, such as Machine Learning (ML) based moisture detection model 912. In various embodiments the one or more trained machine learning based moisture level detection models, such as machine learning based moisture detection model 912, are trained using NIR image data for one or more wood products and corresponding determined moisture levels for the one or more wood products.

[0320] Various types of machine learning based models are well known in the art. Consequently the one or more trained machine learning based moisture level detection models, such as machine learning based moisture detection model 912, can be any machine learning based model type or use any machine learning based algorithm, as discussed herein, and/or as known in the art at the time of filing, and/or as becomes known or available after the time of filing.

[0321] Specific illustrative examples of machine learning based model types and machine learning based algorithms that can be used for, or with, the one or more trained machine learning based moisture level detection models of moisture prediction module 910, such as machine learning based moisture detection model 912, include, but are not limited to: supervised machine learning-based models; semi-supervised machine learning-based models; unsupervised machine learning-based models; classification machine learning-based models; logistical regression machine learning-based models; neural network machine learning-based models; and deep learning machine learning-based models.

[0322] In various embodiments, and largely depending on the machine-learning based models used, the NIR image data for one or more wood products, including in some cases various environmental and production parameters, and corresponding determined moisture levels for the one or more wood products can be processed using various methods known in the machine learning arts to identify elements and vectorize the NIR image data and/or corresponding determined moisture levels data. As a specific illustrative example, in a case where the machine leaning based model is a supervised model, the NIR image data can be analyzed and processed into elements found to be indicative of a wood product moisture levels and product performance. Then these elements are used to create vectors in multidimensional space which are, in turn, used as input data for one or more machine learning models. The correlated determined moisture levels data for each NIR image data vector is then used as a label for the resulting vector. This process is repeated for multiple, often millions, of correlated pairs of NIR image data vector and determined moisture levels data with the result being one or more trained machine learning based moisture level detection models.

[0323] Then when new NIR image data is obtained, this new NIR image data is also vectorized and the new NIR image vector data is provided as input data to the one or more trained machine learning based moisture level detection models. The new NIR image vector data is then processed to find a distance between the new NIR image vector and previously labeled NIR image vectors, whose associated moisture level data is known. Based on a calculated distance between the new NIR image vector data and the previously labeled NIR image vector data, a probability that the new NIR image vector data correlates to a moisture level associated with the previously labeled NIR image vector data can be calculated. This results in a probability score for the wood product being analyzed.

[0324] Those of skill in the art will readily recognize that there are many different types of machine learning based models known in the art. Consequently, the specific illustrative example of a specific supervised machine learning based model discussed above is not limiting.

[0325] As seen in FIG. 9, computing system 352 also include physical memory 360. in one embodiment, the physical memory 360 includes NIR image data 362 representing one or more NIR images of the illuminated wood product first surface 332 of the wood product 330 captured using NIR camera 324.

[0326] As seen in FIG. 9, in one embodiment, computing system 352 includes one or more processors, such as processor 370, for generating the NIR image data 362 representing one or more NIR images of the illuminated wood product first surface 332 of the wood product 330 from NIR camera 324.

[0327] In one embodiment, NIR image data 362 is provided to moisture prediction module 910 where it is processed/vectorized and provided to machine learning based moisture level detection model 912.

[0328] Machine learning based moisture level detection model 912 then processes the vectorized NIR image data 362 as discussed above and generates moisture level prediction data 914 for the wood product 330.

[0329] As seen in FIG. 9, moisture level prediction data 914 for the wood product 330 is then provided to grade assignment module 380. As discussed above, grade assignment module 380 then assigns a grade to the wood product 330 based on moisture level prediction data 914 for the wood product 330.

[0330] As seen in FIG. 9, grade assignment module 380 includes moisture analysis module 374 which, along with processor 370, processes moisture level prediction data 914 for the wood product 330 and generates grade assignment data 382 based on this processing

[0331] As seen in FIG. 9, in one embodiment, grade assignment data 382 is provided to action selection and activation module 390 which selects an appropriate action of the actions represented in available actions data 392 based, at least in part on the grade indicated by grade assignment data 382. As seen in FIG. 9, in one embodiment, the determined appropriate action is represented by selected action data 394.

[0332] As seen in FIG. 9, in one embodiment, selected action data 394 is forwarded to an action activation module, such as selected action implementation module 396 in production environment 301 to initialize one or more actions with respect to the wood product 330 based, at least in part, on the grade represented by grade assignment data 382 and assigned to the wood product 330 by action selection and activation module 390.

[0333] In one embodiment, one or more actions that can be taken represented in available actions data 392 include, but are not limited to: sorting the wood product 330 into a bin or location associated with the grade represented by grade assignment data 382 and assigned to the wood product 330; restricting the use of the wood product 330 based on the grade represented by grade assignment data 382 and assigned to the wood product 330; rejecting the wood product 330 based on the grade represented by grade assignment data 382 and assigned to the wood product 330; sending the wood product 330 back for further processing based on the grade represented by grade assignment data 382 and assigned to the wood product 330; adjusting one or more processing parameters of a production line in production environment 301 based, at least in part, on the grade represented by grade assignment data 382 and assigned to the wood product 330 and/or the grades assigned other wood products; adjusting drying temperatures on a production line in production environment 301 based, at least in part, on grade represented by grade assignment data 382 and assigned to the wood product 330 and/or the grades assigned other wood products; adjusting drying times on a production line in production environment 301 based, at least in part, on grade represented by grade assignment data 382 and assigned to the wood product 330 and/or the grades assigned other wood products; and selecting a type and amount of glues used on a production line in production environment 301 based, at least in part, on grade represented by grade assignment data 382 and assigned to the wood product 330 and/or the grades assigned other wood products.

[0334] Those of skill in the art will ready recognize that the specific illustrative example of one embodiment of FIG. 9 is but one example of numerous possible production environments and arrangement of components. Consequently, the specific illustrative example of one embodiment shown in FIG. 9 is not intended to limit the scope of the invention as set forth in the claims below.

[0335] As a specific illustrative example of possible variations, in some embodiments, the NIR analysis station 320 can include one or more illumination sources 322 positioned to illuminate two or more surfaces of a wood product and one or more NIR cameras 324 positioned to capture one or more NIR images of the two or more illuminated surfaces of the wood product.

[0336] As noted above, embodiments of the present disclosure also provide an effective and efficient technical solution to the technical problem of providing a method and system for determining the strength of a wood product that is reliable, consistent, and economically feasible to implement.

[0337] Embodiments of the present disclosure utilize Near InfraRed (NIR) technology, including Near InfraRed/Short Wave InfraRed (NIR/SWIR) cameras and detectors, to accurately determine the strength of green and/or dry the wood products, such as veneer. To this end, in one embodiment, one or more NIR green strength analysis systems, including one or more NIR green wood product strength analysis stations, are provided.

[0338] FIG. 10 is simplified block diagram of a NIR green wood product strength analysis process 1000 for determining the strength of a green wood product in accordance with one embodiment.

[0339] As seen in FIG. 10, in one embodiment, the green wood product is green veneer created by peeling thin layers of wood from a peeler log 1001, or other lumber source, in a continuous manner. This process is similar to unrolling a bolt of cloth. Also shown in FIG. 10 is pressure bar 1002, knife 1004, lathe chuck 105, conveyor 1010, and green veneer ribbon 1013.

[0340] The resulting green wood product, in this case relatively thin green veneer layer or “ribbon” 1013 is then provided to NIR green wood product strength analysis system 1020 by conveyor 1010. In one embodiment, green veneer ribbon 1013 is analyzed by NIR green wood product strength analysis system 1020 as discussed below and a grade is assigned to the veneer ribbon 1013.

[0341] The veneer ribbon 1013 is then cut to individual green veneer sheets of specific green veneer sheet dimensions at cutting station 1030. The individual green veneer sheets 1043 are then stacked into green veneer sheet stacks 1053 at automated stacking station 1040. In one embodiment, at automated stacking station 1040 the individual green veneer sheets 1043 are stacked according to the grade assigned to the parent veneer ribbon section.

[0342] In one embodiment, at automated stacking station 1040 the individual green veneer sheets 1043 are stacked according to the grade assigned to the parent green veneer ribbon using any of the stacking systems described in related applications Bolton et al., U.S. application Ser. No. 16/697,458 filed on Nov. 27, 2019 and issuing Aug. 17, 2021 as U.S. Pat. No. 11,090,833; Bolton et al., U.S. application Ser. No. 17/356,804 filed on Jun. 24, 2021; Bolton et al., U.S. application Ser. No. 17/356,805 filed on Jun. 24, 2021; Bolton et al., U.S. application Ser. No. 17/361,808 filed on Jun. 29, 2021; and Bolton et al., U.S. application Ser. No. 17/366,432, filed Jul. 2, 2021, which are hereby incorporated by reference in their entirety as if they were fully set forth herein.

[0343] In one embodiment, at automated stacking station 1040 the individual green veneer sheets 1043 are stacked according to the grade assigned to the parent veneer ribbon using any stacking system discussed herein, and/or as known in the art at the time of filing, and/or are become known after the time of filing.

[0344] Consequently, using the disclosed NIR green strength analysis it is possible to collect high quality NIR spectra of wood products, including full size ribbons and/or sheets of green veneer, that contain information and data regarding the mechanical properties of wood product, including strength of the wood product, before moisture analysis is performed.

[0345] FIG. 11 is simplified block diagram of a NIR green wood product strength analysis system 1020, including NIR green wood product strength analysis station 1121, in accordance with one embodiment.

[0346] Referring now to FIGS. 10 and 11, in one embodiment, NIR green wood product strength analysis system 1020 includes a production environment 1101 and a computing environment 1150.

[0347] As seen in FIG. 11, production environment 1101 includes NIR green wood product strength analysis station 1121 and selected action implementation module 1196. As seen in FIG. 11, NIR green wood product strength analysis station 1121 includes one or more illumination sources, such as illumination source 1122, positioned to illuminate a surface of a wood product. In various embodiments, the one or more illumination sources, such as illumination source 1122, can include one or more LED light sources. In other embodiments, the one or more illumination sources, such as illumination source 1122, can include, but are not limited to, halogen, halogen and tungsten light sources, or any other light sources, as discussed herein, and/or as known in the art at the time of filing, and/or as developed after the time of filing.

[0348] As used herein, the terms Near InfraRed (NIR) and Short-Wave InfraRed (SWIR) are used interchangeably to include wavelength in the range of 750 nanometers (nm) to 11500 nm. In addition, all stated wave lengths herein are assumed to include values within 10% of the stated value.

[0349] In one embodiment, the one or more illumination sources, such as illumination source 1122, are selected to provide a reduced spectral range between 650 and 1050 nm. This enables very rapid collection of the NIR spectra. This rapid collection is required for the evaluation of veneer in the manufacturing process.

[0350] As seen in FIG. 11, NIR green wood product strength analysis station 1121 also includes one or more NIR cameras, such as NIR camera 1124, positioned to capture NIR image data 1162 representing one or more NIR images of the illuminated surface of the green wood product/veneer ribbon 1013. In one embodiment, the one or more NIR cameras, such as NIR camera 1124, are adjustably positioned and adjustably focused to capture any desired one or more NIR images of the illuminated, of first, surface 1114 of the green wood product/veneer ribbon 1013.

[0351] As seen in FIG. 11, and as discussed below, a green wood product/veneer ribbon 1013 to be analyzed in the NIR green wood product strength analysis station 1121 is positioned in NIR green wood product strength analysis station 1121. In various embodiments, the green wood product/veneer ribbon 1013 can be any green wood product as discussed herein, and/or as known in the art at the time of filing and/or as becomes known after the time of filing. In one embodiment, the green wood product/veneer ribbon 1013 to be analyzed is a green veneer ribbon of multiple veneer sheet lengths 1043.

[0352] In one embodiment, the green wood product/veneer ribbon 1013 to be analyzed is positioned such that a wood product first surface 1114 of the green wood product/veneer ribbon 1013 to be analyzed is illuminated by the illumination source 1122 and the entire wood product first surface 1114 is within view and focus of NIR camera 1124. In one embodiment, the green wood product/veneer ribbon 1013 is positioned in the NIR green wood product strength analysis station 1121 by passing the green wood product/veneer ribbon 1013 through the NIR green wood product strength analysis station 1121 on a conveyor system.

[0353] In various embodiments, the one or more NIR cameras, such as NIR camera 1124, can be of any resolution desired. As noted above, when the one or more NIR cameras, such as NIR camera 1124, are used to scan the wood product first surface 1114 of a green wood product/veneer ribbon 1013 for strength and create NIR image data 1162 of the wood product first surface 1114, essentially each pixel generated by NIR camera 1124 is a sample point. Consequently, the resolution and accuracy of the strength detection process is only limited by the number of pixels the NIR camera 1124 has covering the field of view, e.g., the entire wood product first surface 1114 of green wood product/veneer ribbon 1013. Consequently, in the case where NIR camera 1124 is a 1.3 mega pixel camera, there are essentially 1,110,000 individual measurement points on the wood product first surface 1114. Consequently, using NIR cameras, such as NIR camera 1124, results in resolutions and accuracy that simply cannot be achieved using traditional detection systems.

[0354] In some embodiments, strength analysis models are created, and the data obtained from NIR images can be correlated with the strength properties of the green wood product using these models.

[0355] As seen in FIG. 11, computing environment 1150 includes computing system 1152. As seen in FIG. 11, in one embodiment, computing system 1152 includes strength model database 1110 containing one or more strength analysis models and mechanical properties model data 1112.

[0356] In one embodiment, the one or more strength analysis models and mechanical properties model data 1112 include models and/or data to predict the Metriguard number, and the actual Modulus Of Rupture (MOR) or stiffness Modulus Of Elasticity (MOE) of veneer values of wood products, such as green or dry veneers and/or for one or more other green wood products.

[0357] In various embodiments, different methods can be used to correlate the NIR data, i.e., NIR reflectance spectrum data, of a green wood product to a selected property of that green wood product to create the strength models and/or machine learning modules included in strength analysis models and mechanical properties model data 1112.

[0358] These correlations have been demonstrated empirically on various different commercial softwoods and hardwoods. These correlations have also been demonstrated on green wood. It has been found that these same correlations also apply to moving 4 ft. by 8 ft. sheet of green veneer using a reduced spectral range.

[0359] In some embodiment, the NIR spectra of green veneers can be evaluated off-line using two or more different NIR spectrometers. The veneers were then dried in the commercial process and the NIR spectra were collected on the dry veneers.

[0360] There are a number of methods that can be used to correlate the NIR reflectance spectrum data of a wood sample to some property of that wood sample. One common method is Projection of Latent Structures (PLS) analysis. In some cases, the NIR reflectance spectrum data of the sample are correlated with a response variable, e.g., some measure of the mechanical properties of the wood sample. Since it is not practical to measure the mechanical properties of a full size sheet of veneer, the response variable used for this work was the Metriguard number of the veneer sheet.

[0361] The Metriguard numbers on the full sized sheets of veneer can be measured using the commercial systems. There are several different ways to generate these PLS correlations and to measure the “quality” of the correlation model. All of these PLS models can be constructed using full cross validation techniques. There are also several different “data pretreatments” that can be applied to the NIR reflectance spectrum data prior to constructing a PLS model.

[0362] For the NIR reflectance spectrum data measured on green veneers a common data pretreatment known as Orthogonal Signal Correction (OSC) can be used to mathematically “dry” the green samples prior to construction of the PLS models. The procedure for construction of the PLS models involves using about half of the samples to construct a calibration (CALM) model that correlates the measured or “true” Metriguard number with the NIR reflectance spectrum data. This model is then used to predict the Metriguard number from the NIR reflectance spectrum data of a second of samples that were not contained in the original model. These predicted Metriguard numbers are then compared to the measured Metriguard numbers of this second set of samples.

[0363] Those of skill in the art will also readily recognize that these models can be supplemented and/or replaced with various machine learning and artificial intelligence methods and modules, or any other methods and systems for correlating data, such as the NIR reflectance spectrum data, of a green wood product to a selected property of that green wood product.

[0364] Empirical results show a correlation coefficient (r) between the measured Metriguard number and the Metriguard number predicted with NIR analysis are relatively good for a heterogeneous substrate like wood, 0.83 and 0.69 respectively. The spectral range was between 650 and 1050 nm which is the range required for rapid acquisition times.

[0365] There are several general conclusions that can be drawn from these empirical results. The first general conclusion is that the PLS models constructed using the reduced spectral range 650-1050 nm are as good as or better than those constructed using the full spectral range. This is critically important since the use of this reduced spectral range is required for the rapid acquisition times that will be needed for on-line process monitoring.

[0366] The second general conclusion is that the correlations based on NIR spectra collected from dry veneers is higher than those based on green veneers.

[0367] A third general conclusion is that that OSC of the NIR data before construction of the PLS models significantly improves the quality of the correlations. There are many different ways to actually construct the PLS models from OSC data and the preferred method will be impacted by the conditions used to collected the NIR spectra.

[0368] It may be impractical to measure the actual strength MOR or stiffness MOE of a full size sheet of veneer. To better understand the correlations between these two measures of veneer quality a series of 2 ft. by 2 ft. Douglas Fir veneer samples were cut from full size sheets and sent to NREL. These samples were further cut into samples 6 inches wide and 2 ft. long.

[0369] A portable Metriguard system was used to obtain a Metriguard number for these small samples. The true MOR and MOE were measured in three point bending.

[0370] Based on the empirical results of this work it is possible to collect high quality NIR reflectance spectrum data of full size sheets of veneers. It is also clear that the NIR reflectance spectrum data contains information on the mechanical properties of veneer. It is also clear that the NIR spectra of either green or dry veneer can be used to construct models that predict the Metriguard number, and the actual MOE and MOR values of veneers. Models based on the reduced spectral range 650-1050 nm are as good as or better than those constructed using the full spectral range.

[0371] Consequently, using the disclosed NIR green strength analysis it is possible to collect high quality NIR reflectance spectrum data of wood products, including full size ribbons and/or sheets of green veneer that contain information and data regarding the mechanical properties of wood product, including strength of the wood product.

[0372] As seen in FIG. 11, computing system 1152 also includes physical memory 1160. In one embodiment, the physical memory 1160 includes NIR image data 1162 representing one or more NIR images of the illuminated wood product first surface 1114 of the green wood product/veneer ribbon 1013 captured using NIR camera 1124.

[0373] As seen in FIG. 11, in one embodiment, computing system 1152 includes one or more processors 1170 for processing the NIR image data 1162 representing one or more NIR images of the illuminated wood product first surface 1114 of the green wood product/veneer ribbon 1013 using the one or more strength analysis models and mechanical properties model data 1112 of strength model database 1110.

[0374] As noted above, in one embodiment, the one or more strength analysis models and mechanical properties model data 1112 predict the Metriguard number, and the actual MOE and MOR values of wood products, such as green or dry veneers and/or for one or more other wood products.

[0375] In one embodiment, processor 1170 processes the NIR image data 1162 using the mechanical properties model data 1112 of strength model database 1110 to determine/predict various mechanical properties of the green wood product/veneer ribbon 1013 and therefore the strength of the green wood product/veneer ribbon 1013.

[0376] As seen in FIG. 11, in one embodiment, computing system 1152 includes a grade assignment module 1180 for assigning a grade to the green wood product/veneer ribbon 1013 based on determined/predicted mechanical properties of the green wood product/veneer ribbon 1013.

[0377] As seen in FIG. 11, grade assignment module 1180 includes strength analysis module 1174 which, along with processor 1170, processes the NIR image data 1162 using the mechanical properties model data 1112 of strength model database 1110 to determine/predict various mechanical properties of the green wood product/veneer ribbon 1013 and therefore the strength of the green wood product/veneer ribbon 1013. As a result of the processing by strength analysis module 1174 and processor 1170, grade assignment data 1182 is generated.

[0378] As seen in FIG. 11, in one embodiment, grade assignment data 1182 is provided to action selection and activation module 1190 which selects an appropriate action of the actions represented in available actions data 1192 based, at least in part on the grade indicated by grade assignment data 1182. As seen in FIG. 11, in one embodiment, the determined appropriate action is represented by selected action data 1194.

[0379] As seen in FIG. 11, in one embodiment, selected action data 1194 is forwarded to an action activation module such as selected action implementation module 1196 in production environment 1101 to initialize one or more actions with respect to the green wood product/veneer ribbon 1013 based, at least in part, on the grade represented by grade assignment data 1182 and assigned to the green wood product/veneer ribbon 1013 by action selection and activation module 1190.

[0380] In one embodiment, one or more actions that can be taken represented in available actions data 1192 include, but are not limited to: sorting the green wood product/veneer ribbon 1013 into a bin, location or stack associated with the grade represented by grade assignment data 1182 and assigned to the green wood product/veneer ribbon 1013; restricting the use of the green wood product/veneer ribbon 1013 based on the grade represented by grade assignment data 1182 and assigned to the green wood product/veneer ribbon 1013; rejecting the green wood product/veneer ribbon 1013 based on the grade represented by grade assignment data 1182 and assigned to the green wood product/veneer ribbon 1013; sending the green wood product/veneer ribbon 1013 back for further processing based on the grade represented by grade assignment data 1182 and assigned to the green wood product/veneer ribbon 1013; adjusting one or more processing parameters of a production line in production environment 1101 based, at least in part, on the grade represented by grade assignment data 1182 and assigned to the green wood product/veneer ribbon 1013 and/or the grades assigned other wood products; adjusting various processing parameters on a production line in production environment 1101 based, at least in part, on grade represented by grade assignment data 1182 and assigned to the green wood product/veneer ribbon 1013 and/or the grades assigned other wood products; and selecting a type and amounts of glues used on a production line in production environment 1101 based, at least in part, on grade represented by grade assignment data 1182 and assigned to the green wood product/veneer ribbon 1013 and/or the grades assigned other wood products.

[0381] As noted, in one embodiment, the action taken by selected action implementation module 1196 includes sorting the green wood product/veneer ribbon 1013 into a bin, location or stack associated with the grade represented by grade assignment data 1182 and assigned to the green wood product/veneer ribbon 1013.

[0382] In one embodiment, sorting the green wood product/veneer ribbon 1013 into a bin, location or stack associated with the grade represented by grade assignment data 1182 and assigned to the green wood product/veneer ribbon 1013 is performed at automated stacking station 1040.

[0383] In one embodiment, at automated stacking station 1040, the individual veneer sheets 1043 stacked according to the grade assigned to the parent veneer ribbon section using any of the stacking systems described in related applications Bolton et al., U.S. application Ser. No. 16/697,458 filed on Nov. 27, 2019 and issuing Aug. 17, 2021 as U.S. Pat. No. 11,090,833; Bolton et al., U.S. application Ser. No. 17/356,804 filed on Jun. 24, 2021; Bolton et al., U.S. application Ser. No. 17/356,805 filed on Jun. 24, 2021; Bolton et al., U.S. application Ser. No. 17/361,808 filed on Jun. 29, 2021; and Bolton et al., U.S. application Ser. No. 17/366,432, filed Jul. 2, 2021, which are hereby incorporated by reference in its entirety as if they were fully set forth herein.

[0384] FIG. 12 is a flow chart of a process 1200 for determining the strength of a green wood product using NIR technology in accordance with one embodiment.

[0385] Referring to FIGS. 10, 11 and 12, as seen in FIG. 12, process 1200 begins at operation 1202 and then proceeds to operation 1203.

[0386] In one embodiment, at operation 1203, strength analysis models and/or mechanical properties model data are created. In one embodiment, data obtained from NIR images can be correlated with the strength properties of the green wood product using the strength analysis models and/or mechanical properties model data.

[0387] As discussed above, in various embodiments, different methods can be used to correlate the NIR data, i.e., NIR reflectance spectrum data, of a green wood product to a selected property of that green wood product to create the strength models and/or machine learning modules.

[0388] Consequently, using the disclosed NIR green strength analysis it is possible to collect high quality NIR spectra of wood products, including full size ribbons and/or sheets of green veneer that contain information and data regarding the mechanical properties of wood product, including strength of the wood product.

[0389] It has been found that these correlations apply to moving ribbons and/or sheets of veneer using a reduced spectral range if a reduced spectral range is processed. Consequently, as discussed above, in one embodiment, one or more sources of illumination positioned to illuminate at least one surface of a veneer sheet or other wood product are selected to provide a reduced spectral range between 650 and 1050 nm. This enables very rapid collection of the NIR spectra. This rapid collection is required for the evaluation of veneer in the manufacturing process.

[0390] As discussed above, in one embodiment, the one or more strength analysis models and mechanical properties model data predict the Metriguard number, and the actual MOE and MOR values of wood products, such as green or dry veneers and/or for one or more other wood products.

[0391] In one embodiment, once strength analysis models and/or mechanical properties model data are created at operation 1203, process flow proceeds to operation 1204.

[0392] In one embodiment, at operation 1204 one or more NIR green wood product strength analysis systems, including one or more NIR green wood product strength analysis stations, such as those discussed above are provided.

[0393] In one embodiment, once one or more NIR green wood product strength analysis systems are provided at operation 1204, process flow proceeds to operation 1206.

[0394] In one embodiment, at operation 1206, the green veneer sheet, ribbon, or other wood product to be analyzed is positioned in, or passed through, an NIR green wood product strength analysis system, including an NIR green wood product strength analysis station, for analysis.

[0395] In one embodiment, at operation 1206, the green veneer sheet, ribbon, or other wood product to be analyzed is positioned in, or passed through, an NIR green wood product strength analysis station such that a surface of the green veneer sheet or other wood product to be analyzed is illuminated by the one or more illumination sources. In one embodiment, the green veneer ribbon or sheet to be analyzed is passed from a log peeling/veneer creation station to the NIR green wood product strength analysis station.

[0396] As noted above, in one embodiment, the one or more illumination sources are selected to provide a reduced spectral range between 650 and 1050 nm is utilized to enable very rapid collection of the NIR data including NIR reflectance spectrum data. This rapid collection is required for the evaluation of veneer in the manufacturing process.

[0397] In one embodiment, the NIR green wood product strength analysis station of operation 1206 include one or more NIR/SWIR cameras, hereafter referred to as simply NIR cameras, positioned to capture one or more NIR images of the illuminated surface of the veneer sheet or other wood product.

[0398] In one embodiment, at operation 1206, the one or more NIR cameras are then used to capture one or more NIR images of the illuminated surface of the veneer sheet or other wood product including NIR reflectance spectrum data. In one embodiment, a reduced spectral range, in one embodiment between 650 and 1050 nm, is processed to enable very rapid collection of the NIR data including NIR reflectance spectrum data. This rapid collection is required for the evaluation of veneer in the manufacturing process.

[0399] In one embodiment, at operation 1206, the NIR reflectance spectrum data is provided to a processor for comparing and analyzing the NIR reflectance spectrum data using the one or more strength models and/or machine learning modules of operation 1203.

[0400] In one embodiment, at operation 1206, secondary NIR green strength data processing is also performed for analysis of green wood products to compensate for the strong absorbance bands of water/moisture in the NIR region.

[0401] In one embodiment, once the green veneer sheet, ribbon, or other wood product to be analyzed is positioned in, or passed through, an NIR green wood product strength analysis station for analysis at operation 1206, process flow proceeds to operation 1208.

[0402] In one embodiment, at operation 1208 a grade is assigned to the green wood product based on the determined strength of the green wood product.

[0403] In one embodiment, once a grade is assigned to the green wood product based on the determined strength of the green wood product process flow proceeds to operation 1210.

[0404] In one embodiment, at operation 1210, one or more actions are taken with respect to the green wood product based, at least in part, on the grade assigned to the green wood product at operation 1208.

[0405] In one embodiment, one or more actions that can be taken at operation 1210 include, but are not limited to: sorting the wood product/veneer ribbon into a bin, location or stack associated with the assigned grade; restricting the use of the wood product/veneer ribbon based on the grade assigned to the wood product/veneer ribbon; rejecting the wood product/veneer ribbon based on the grade assigned to the wood product/veneer ribbon; sending the wood product/veneer ribbon back for further processing based on the grade assigned to the wood product/veneer ribbon; adjusting one or more processing parameters of a production line based, at least in part, on the grade assigned to the wood product/veneer ribbon and/or the grades assigned other wood products; adjusting various processing parameters on a production line based, at least in part, on grade assigned to the wood product/veneer ribbon and/or the grades assigned other wood products; and selecting a type and amounts of glues used on a production line based, at least in part, on grade assigned to the wood product/veneer ribbon and/or the grades assigned other wood products.

[0406] As noted, in one embodiment, the action taken at 1210 can include sorting the wood product/veneer ribbon into a bin, location or stack associated with the grade assigned to the wood product/veneer ribbon.

[0407] In one embodiment, sorting the wood product/veneer ribbon into a bin, location or stack associated with the grade assigned to the wood product/veneer ribbon is performed at an automated stacking station.

[0408] In one embodiment, at the automated stacking station, the individual veneer sheets are stacked according to the grade assigned to the parent veneer ribbon section using any of the stacking systems described in related applications Bolton et al., U.S. application Ser. No. 16/697,458 filed on Nov. 27, 2019 and issuing Aug. 17, 2021 as U.S. Pat. No. 11,090,833; Bolton et al., U.S. application Ser. No. 17/356,804 filed on Jun. 24, 2021; Bolton et al., U.S. application Ser. No. 17/356,805 filed on Jun. 24, 2021; Bolton et al., U.S. application Ser. No. 17/361,808 filed on Jun. 29, 2021; and Bolton et al., U.S. application Ser. No. 17/366,432, filed Jul. 2, 2021, which are hereby incorporated by reference in its entirety as if it were fully set forth herein.

[0409] Consequently, some disclosed embodiments use NIR technology to predict the strength of a sheet of veneer from the NIR spectra of green veneer. This allows for the gradings and sorting of green veneer before drying and moisture analysis to provide enhanced grading technology and more accurate wood product grading.

[0410] Once one or more actions with respect to the wood product at operation 1220, process flow proceeds to END operation 1234 where process 1200 is exited to await new samples and/or data.

[0411] As noted above, embodiments of the present disclosure also provide an effective and efficient technical solution to the technical problem of providing a method and system for determining the strength of a dry wood product that is reliable, consistent, and economically feasible to implement.

[0412] FIG. 13 is simplified block diagram of a NIR dry wood product strength analysis process 1300 for determining the strength of a dry wood product in accordance with one embodiment.

[0413] As seen in FIG. 13, in one embodiment, the wood product is dry veneer sheets, or another dry wood product, 1313. In one embodiment, the dry wood product/dry veneer sheets 1313 are provided to NIR dry wood product strength analysis process 1300 from a dryer by conveyor 1390.

[0414] In one embodiment, the resulting dry wood product/veneer sheets 1313 are then provided to an NIR moisture analysis station 1310 such as any of the NIR analysis stations discussed with respect to FIG. 3A, 6, or 9. In one embodiment, the dry wood product/veneer sheets 1313 are analyzed at NIR moisture analysis station 1310 using any of the systems or methods described above with respect to FIGS. 3A through 9.

[0415] In one embodiment, the dry wood product/veneer sheets 1313 are then provided to NIR dry wood product strength analysis system 1320 by conveyor 1390.

[0416] The dry wood product/veneer sheets 1313 are then analyzed by NIR dry wood product strength analysis system 1320 as discussed below.

[0417] In one embodiment, the dry wood product/veneer sheets 1313 are then provided to visual defect analysis station 1330 by conveyor 1390. In one embodiment, visual defect analysis station 1330 is used detect visual defects in or on the surface of dry wood product/veneer sheets 1313. In one embodiment, visual defect analysis station 1330 is any visual defect analysis system discussed herein, and/or as known in the art at the time of filing, and/or as developed after the time of filing, for detecting visual defects in or on the surface of a wood product.

[0418] In one embodiment, the visual defect analysis station 1330 can be any of the visual defect analysis systems set forth in related applications Bolton et al., U.S. application Ser. No. 16/205,027 filed on Nov. 29, 2018 and issuing on Nov. 3, 2020 as U.S. Pat. No. 10,825,164; Bolton et al., U.S. application Ser. No. 17/074,956 filed on Oct. 20, 2020 and issuing on Dec. 14, 2021 as U.S. Pat. No. 11,200,663; Bolton et al., U.S. application Ser. No. 17/084,397 filed on Oct. 29, 2020 and issuing on Jan. 11, 2022 as U.S. Pat. No. 11,222,419; and Bolton et al., U.S. application Ser. No. 17/523,528 filed on Nov. 19, 2021,_which are hereby incorporated by reference in their entirety as if they were fully set forth herein.

[0419] In one embodiment, based on the analysis of NIR moisture analysis station 1310, and/or NIR dry wood product strength analysis system 1320 and/or visual defect analysis station 1330, a grade is assigned to the dry wood product/veneer sheets 1313.

[0420] In one embodiment, the individual dry wood product/veneer sheets 1313 are then stacked into veneer sheet stacks 1353 at automated stacking station 1340. In one embodiment, at automated stacking station 1340 the individual veneer sheets 1343 stacked according to the grade assigned to the dry wood product/veneer sheets 1313.

[0421] In one embodiment, at automated stacking station 1340 the individual dry wood product/veneer sheets 1313 are stacked according to the grade assigned to the dry wood product/veneer sheets 1313 using any of the stacking systems described in related applications Bolton et al., U.S. application Ser. No. 16/697,458 filed on Nov. 27, 2019 and issuing Aug. 17, 2021 as U.S. Pat. No. 11,090,833; Bolton et al., U.S. application Ser. No. 17/356,804 filed on Jun. 24, 2021; Bolton et al., U.S. application Ser. No. 17/356,805 filed on Jun. 24, 2021; Bolton et al., U.S. application Ser. No. 17/361,808 filed on Jun. 29, 2021; and Bolton et al., U.S. application Ser. No. 17/366,432, filed Jul. 2, 2021, which are hereby incorporated by reference in their entirety as if they were fully set forth herein.

[0422] In one embodiment, at automated stacking station 1340 the individual dry wood product/veneer sheets 1313 are stacked according to the grade assigned to the dry wood product/veneer sheets 1313 using any stacking system discussed herein, and/or as known in the art at the time of filing, and/or are become known after the time of filing.

[0423] Consequently, using the disclosed NIR dry strength analysis it is possible to collect high quality NIR spectra of wood products, including full size sheets of dry veneer that contain information and data regarding the mechanical properties of wood product, including strength of the wood product, after drying and/or moisture analysis is performed.

[0424] FIG. 14 is simplified block diagram of a NIR dry wood product strength analysis system 1320, including NIR dry wood product strength analysis station 1421, in accordance with one embodiment.

[0425] Referring now to FIGS. 13 and 14, in one embodiment, NIR dry wood product strength analysis system 1320 includes a production environment 1401 and a computing environment 1450.

[0426] As seen in FIG. 14, production environment 1401 includes NIR dry wood product strength analysis station 1421 and selected action implementation module 1496. As seen in FIG. 14, NIR dry wood product strength analysis station 1421 includes one or more illumination sources, such as illumination source 1422, positioned to illuminate a surface 1414 of a dry wood product/veneer sheet 1313, such as a dry sheet of veneer.

[0427] In various embodiments, the one or more illumination sources, such as illumination source 1422, can include one or more LED light sources. In other embodiments, the one or more illumination sources, such as illumination source 1422, can include, but are not limited to, halogen, halogen and tungsten light sources, or any other light sources, as discussed herein, and/or as known in the art at the time of filing, and/or as developed after the time of filing.

[0428] As used herein, the terms Near InfraRed (NIR) and Short-Wave InfraRed (SWIR) are used interchangeably to include wavelength in the range of 750 nanometers (nm) to 14500 nm. In addition, all stated wave lengths herein are assumed to include values within 13% of the stated value.

[0429] In one embodiment, the one or more illumination sources, such as illumination source 1422, are selected to provide a reduced spectral range, in one embodiment between 650 and 1350 nm. This enables very rapid collection of the NIR spectra. This rapid collection is required for the evaluation of veneer in the manufacturing process.

[0430] As seen in FIG. 14, NIR dry wood product strength analysis station 1421 also includes one or more NIR cameras, such as NIR camera 1424, positioned to capture NIR image data 1462 representing one or more NIR images of the illuminated surface 1414 of the dry wood product/veneer sheet 1313. In one embodiment, the one or more NIR cameras, such as NIR camera 1424, are adjustably positioned and adjustably focused to capture any desired one or more NIR images of the illuminated, or first, surface 1414 of the dry wood product/veneer sheet 1313.

[0431] As seen in FIG. 14, and as discussed below, a dry wood product/veneer sheet 1313 to be analyzed in the NIR dry wood product strength analysis station 1421 is positioned in NIR dry wood product strength analysis station 1421. In various embodiments, the dry wood product/veneer sheet 1313 can be any wood product as discussed herein, and/or as known in the art at the time of filing and/or as becomes known after the time of filing. In one embodiment, the dry wood product/veneer sheet 1313 to be analyzed are dry veneer sheets.

[0432] In one embodiment, the dry wood product/veneer sheet 1313 to be analyzed is positioned such that a dry wood product first surface 1414 of the dry wood product/veneer sheet 1313 to be analyzed is illuminated by the illumination source 1422 and the entire dry wood product first surface 1414 is within view and focus of NIR camera 1424. In one embodiment, the dry wood product/veneer sheet 1313 is positioned in the NIR dry wood product strength analysis station 1421 by passing the dry wood product/veneer sheet 1313 through the NIR dry wood product strength analysis station 1421 on a conveyor system (not shown in FIG. 14 but shown as 1310 in FIG. 13 and discussed above).

[0433] In various embodiments, the one or more NIR cameras, such as NIR camera 1424, can be of any resolution desired. As noted above, when the one or more NIR cameras, such as NIR camera 1424, are used to scan the dry wood product first surface 1414 of a dry wood product/veneer sheet 1313 for strength and create NIR image data 1462 of the wood product first surface 1414, essentially each pixel generated by NIR camera 1424 is a sample point. Consequently, the resolution and accuracy of the strength detection process is only limited by the number of pixels the NIR camera 1424 has covering the field of view, e.g., the entire wood product first surface 1414 of dry wood product/veneer sheet 1313. Consequently, in the case where NIR camera 1424 is a 1.3 mega pixel camera, there are essentially 1,110,000 individual measurement points on the wood product first surface 1414. Consequently, using NIR cameras, such as NIR camera 1424, results in resolutions and accuracy that simply cannot be achieved using traditional detection systems.

[0434] In some embodiments, strength analysis models are created, and the data obtained from NIR images can be correlated with the strength properties of the dry wood product using these models.

[0435] As seen in FIG. 14, computing environment 1450 includes computing system 1452. As seen in FIG. 14, in one embodiment, computing system 1452 includes strength model database 1410 containing one or more strength analysis models and mechanical properties model data 1412.

[0436] In one embodiment, the one or more strength analysis models and mechanical properties model data 1412 predict the Metriguard number, and the actual MOE and MOR values of wood products, such as green or dry veneers and/or for one or more other wood products.

[0437] In various embodiments, different methods can be used to correlate the NIR data, i.e., NIR reflectance spectrum data, of a dry wood product to a selected property of that dry wood product to create the strength models and/or machine learning modules.

[0438] These correlations have been demonstrated empirically on various different commercial softwoods and hardwoods. These correlations have also been demonstrated on dry wood. It has been found that these same correlations also apply to moving 4 ft. by 8 ft. sheet of dry veneer using a reduced spectral range.

[0439] In some embodiment, the NIR spectra of dry veneers can be evaluated off-line using two different NIR spectrometers.

[0440] As discussed above, there are a number of methods that can be used to correlate the NIR reflectance spectrum data of a wood sample to some property of that wood sample. One common method is Projection of Latent Structures (PLS) analysis. In some cases, the NIR reflectance spectrum data of the sample are correlated with a response variable, e.g., some measure of the mechanical properties of the wood sample. Since it is not practical to measure the mechanical properties of a full size sheet of veneer, the response variable used for this work was the Metriguard number of the veneer sheet.

[0441] The Metriguard numbers on the full sized sheets of veneer can be measured using the commercial systems. There are several different ways to generate these PLS correlations and to measure the “quality” of the correlation model. All of these PLS models can be constructed using full cross validation techniques. There are also several different “data pretreatments” that can be applied to the NIR reflectance spectrum data prior to constructing a PLS model.

[0442] In one instance, for the NIR reflectance spectrum data measured on green veneers a common data pretreatment known as Orthogonal Signal Correction (OSC) was used to mathematically “dry” the green samples prior to construction of the PLS models. The procedure for construction of the PLS models involves using about half of the samples to construct a calibration (CALM) model that correlates the measured or “true” Metriguard number with the NIR reflectance spectrum data. This model is then used to predict the Metriguard number from the NIR reflectance spectrum data of a second of samples that were not contained in the original model. These predicted Metriguard numbers are then compared to the measured Metriguard numbers of this second set of samples.

[0443] Those of skill in the art will also readily recognize that these models can be supplemented and/or replaced with various machine learning and artificial intelligence methods and modules, or any other methods and systems for correlating data, such as the NIR reflectance spectrum data, of a green wood product to a selected property of that green wood product.

[0444] Empirical results show a correlation coefficient (r) between the measured Metriguard number and the Metriguard number predicted with NIR analysis are relatively good for a heterogeneous substrate like wood, 0.83 and 0.69 respectively. The spectral range was between 650 and 1050 nm which is the range required for rapid acquisition times.

[0445] There are several general conclusions that can be drawn from these empirical results. The first general conclusion is that the PLS models constructed using the reduced spectral range of 650-1050 nm are as good as or better than those constructed using the full spectral range. This is critically important since the use of this reduced spectral range is required for the rapid acquisition times that will be needed for on-line process monitoring.

[0446] The second general conclusion is that the correlations based on NIR spectra collected from dry veneers is higher than those based on green veneers.

[0447] A third general conclusion is that that OSC of the NIR data before construction of the PLS models significantly improves the quality of the correlations. There are many different ways to actually construct the PLS models from OSC data and the preferred method will be impacted by the conditions used to collected the NIR spectra.

[0448] It is may be impractical to measure the actual strength MOR or stiffness MOE of a full size sheet of veneer. To better understand the correlations between these two measures of veneer quality a series of 2 ft. by 2 ft. Douglas Fir veneer samples were cut from full size sheets and sent to NREL. These samples were further cut into samples 6 inches wide and 2 ft. long.

[0449] A portable Metriguard system was used to obtain a Metriguard number for these small samples. The true MOR and MOE were measured in three point bending.

[0450] Based on the empirical results of this work it is possible to collect high quality NIR reflectance spectrum data of full size sheets of veneers. It is also clear that the NIR reflectance spectrum data contains information on the mechanical properties of veneer. It is also clear that the NIR spectra of either green or dry veneer can be used to construct models that predict the Metriguard number, and the actual MOE and MOR values of veneers. Models based on the reduced spectral range of 650-1050 nm are as good as or better than those constructed using the full spectral range. Empirical results also indicate that the Metriguard number is poorly correlated with the actual mechanical properties of veneers.

[0451] Consequently, using the disclosed NIR green strength analysis it is possible to collect high quality NIR reflectance spectrum data of wood products, including full size ribbons and/or sheets of green veneer that contain information and data regarding the mechanical properties of wood product, including strength of the wood product.

[0452] As seen in FIG. 14, computing system 1452 also includes physical memory 1460. In one embodiment, the physical memory 1460 includes NIR image data 1462 representing one or more NIR images of the illuminated wood product first surface 1414 of the dry wood product/veneer sheet 1313 captured using NIR camera 1424.

[0453] As seen in FIG. 14, in one embodiment, computing system 1452 includes one or more processors 1470 for processing the NIR image data 1462 representing one or more NIR images of the illuminated wood product first surface 1414 of the dry wood product/veneer sheet 1313 using the one or more strength analysis models and mechanical properties model data 1412 of strength model database 1410.

[0454] As noted above, in one embodiment, the one or more strength analysis models and mechanical properties model data 1412 predict the Metriguard number, and the actual MOE and MOR values of wood products, such as dry or dry veneers and/or for one or more other wood products.

[0455] In one embodiment, processor 1470 processes the NIR image data 1462 using the using the mechanical properties data 1412 of strength model database 1410 to determine/predict various mechanical properties of the dry wood product/veneer sheet 1313 and therefore the strength of the dry wood product/veneer sheet 1313.

[0456] As seen in FIG. 14, in one embodiment, computing system 1452 includes a grade assignment module 1480 for assigning a grade to the dry wood product/veneer sheet 1313 based on determined/predicted mechanical properties of the dry wood product/veneer sheet 1313.

[0457] As seen in FIG. 14, grade assignment module 1480 includes strength analysis module 1474 which, along with processor 1470, processes the NIR image data 1462 using the using the mechanical properties data 1412 of strength model database 1410 to determine/predict various mechanical properties of the dry wood product/veneer sheet 1313 and therefore the strength of the dry wood product/veneer sheet 1313. As a result of the processing by strength analysis module 1474 and processor 1470, grade assignment data 1482 is generated.

[0458] As seen in FIG. 14, in one embodiment, grade assignment data 1482 is provided to action selection and activation module 1490 which selects an appropriate action of the actions represented in available actions data 1492 based, at least in part on the grade indicated by grade assignment data 1482. As seen in FIG. 14, in one embodiment, the determined appropriate action is represented by selected action data 1494.

[0459] As seen in FIG. 14, in one embodiment, selected action data 1494 is forwarded to an action activation module such as selected action implementation module 1496 in production environment 1401 to initialize one or more actions with respect to the dry wood product/veneer sheet 1313 based, at least in part, on the grade represented by grade assignment data 1482 and assigned to the dry wood product/veneer sheet 1313 by action selection and activation module 1490.

[0460] In one embodiment, one or more actions that can be taken represented in available actions data 1492 include, but are not limited to: sorting the dry wood product/veneer sheet 1313 into a bin, location or stack associated with the grade represented by grade assignment data 1482 and assigned to the dry wood product/veneer sheet 1313; restricting the use of the dry wood product/veneer sheet 1313 based on the grade represented by grade assignment data 1482 and assigned to the dry wood product/veneer sheet 1313; rejecting the dry wood product/veneer sheet 1313 based on the grade represented by grade assignment data 1482 and assigned to the dry wood product/veneer sheet 1313; sending the dry wood product/veneer sheet 1313 back for further processing based on the grade represented by grade assignment data 1482 and assigned to the dry wood product/veneer sheet 1313; adjusting one or more processing parameters of a production line in production environment 1401 based, at least in part, on the grade represented by grade assignment data 1482 and assigned to the dry wood product/veneer sheet 1313 and/or the grades assigned other wood products; adjusting various processing parameters on a production line in production environment 1401 based, at least in part, on grade represented by grade assignment data 1482 and assigned to the dry wood product/veneer sheet 1313 and/or the grades assigned other wood products; and selecting a type and amounts of glues used on a production line in production environment 1401 based, at least in part, on grade represented by grade assignment data 1482 and assigned to the dry wood product/veneer sheet 1313 and/or the grades assigned other wood products.

[0461] As noted, in one embodiment, the action taken by selected action implementation module 1496 includes sorting the dry wood product/veneer sheet 1313 into a bin, location or stack associated with the grade represented by grade assignment data 1482 and assigned to the dry wood product/veneer sheet 1313.

[0462] In one embodiment, sorting the dry wood product/veneer sheet 1313 into a bin, location or stack associated with the grade represented by grade assignment data 1482 and assigned to the dry wood product/veneer sheet 1313 is performed at automated stacking station 1340.

[0463] In one embodiment, at automated stacking station 1340, the individual veneer sheets 1343 stacked according to the grade assigned to dry wood product/veneer sheet 1313 using any of the stacking systems described in related applications Bolton et al., U.S. application Ser. No. 16/697,458 filed on Nov. 27, 2019 and issuing Aug. 17, 2021 as U.S. Pat. No. 11,090,833; Bolton et al., U.S. application Ser. No. 17/356,804 filed on Jun. 24, 2021; Bolton et al., U.S. application Ser. No. 17/356,805 filed on Jun. 24, 2021; Bolton et al., U.S. application Ser. No. 17/361,808 filed on Jun. 29, 2021; and Bolton et al., U.S. application Ser. No. 17/366,432, filed Jul. 2, 2021, which are hereby incorporated by reference in its entirety as if it were fully set forth herein.

[0464] FIG. 15 is a flow chart of a process for determining the strength of a dry wood product using NIR technology in accordance with one embodiment.

[0465] Referring to FIGS. 13, 14 and 15, as seen in FIG. 15, process 1500 begins at operation 1502 and then process proceeds to operation 1503.

[0466] In one embodiment, at operation 1503, strength analysis models and/or mechanical properties model data are created. In one embodiment, data obtained from NIR images can be correlated with the strength properties of the dry wood product using the strength analysis models and/or mechanical properties model data.

[0467] In various embodiments, different methods can be used to correlate the NIR data, i.e., NIR reflectance spectrum data, of a dry wood product to a selected property of that dry wood product to create the strength models and/or machine learning modules.

[0468] Consequently, using the disclosed NIR dry strength analysis it is possible to collect high quality NIR spectra of wood products, including full size sheets of dry veneer that contain information and data regarding the mechanical properties of wood product, including strength of the wood product.

[0469] It has been found that these correlations apply to moving ribbons and/or sheets of veneer using a reduced spectral range if a reduced spectral range is processed. Consequently, as discussed below, in one embodiment, one or more sources of illumination positioned to illuminate at least one surface of a veneer sheet or other wood product are selected to provide a reduced spectral range, in one embodiment between 650 and 1350 nm. This enables very rapid collection of the NIR spectra. This rapid collection is required for the evaluation of veneer in the manufacturing process.

[0470] As discussed above, in one embodiment, the one or more strength analysis models and mechanical properties model data predict the Metriguard number, and the actual MOE and MOR values of wood products, such as dry or dry veneers and/or for one or more other wood products.

[0471] In one embodiment, once strength analysis models and/or mechanical properties model data are created at operation 1503, process flow proceeds to operation 1504.

[0472] In one embodiment, at operation 1504 one or more NIR dry wood product strength analysis systems, including one or more NIR dry wood product strength analysis stations, such as any of the NIR dry wood product strength analysis systems, including one or more NIR dry wood product strength analysis stations, discussed above herein are provided.

[0473] In one embodiment, once one or more NIR dry wood product strength analysis systems are provided at operation 1504, process flow proceeds to operation 1506.

[0474] In one embodiment, at operation 1506, the dry veneer sheet or other wood product to be analyzed is positioned in, or passed through, an NIR dry wood product strength analysis system, including an NIR dry wood product strength analysis station for analysis.

[0475] In one embodiment, at operation 1506, the dry veneer sheet, or other wood product, to be analyzed is positioned in, or passed through, an NIR dry wood product strength analysis station such that a surface of the dry veneer sheet or other wood product to be analyzed is illuminated by the one or more illumination sources. In one embodiment, the dry veneer sheet to be analyzed is passed from a moisture detection system to the NIR dry wood product strength analysis station.

[0476] As noted above, in one embodiment, the one or more illumination sources are selected to provide a reduced spectral range, in one embodiment between 650 and 1350 nm, are utilized to enable very rapid collection of the NIR data including NIR reflectance spectrum data. This rapid collection is required for the evaluation of veneer in the manufacturing process.

[0477] In one embodiment, the NIR dry wood product strength analysis stations of operation 1506 include one or more NIR/SWIR cameras, hereafter referred to as simply NIR cameras, positioned to capture one or more NIR images of the illuminated surface of the veneer sheet or other wood product.

[0478] In one embodiment, at operation 1506, the one or more NIR cameras are then used to capture one or more NIR images of the illuminated surface of the veneer sheet or other wood product including NIR reflectance spectrum data. In one embodiment, a reduced spectral range, in one embodiment between 650 and 1350 nm, is processed to enable very rapid collection of the NIR data including NIR reflectance spectrum data. This rapid collection is required for the evaluation of veneer in the manufacturing process.

[0479] In one embodiment, at operation 1506, the NIR reflectance spectrum data is provided to a processor for comparing and analyzing the NIR reflectance spectrum data using the one or more strength models and/or machine learning modules of operation 1503.

[0480] In one embodiment, at operation 1506, secondary NIR dry strength data processing is also performed for analysis of dry wood products to compensate for the strong absorbance bands of water/moisture in the NIR region.

[0481] In one embodiment, once the dry veneer sheet, or other wood product, to be analyzed is positioned in, or passed through, an NIR dry wood product strength analysis station for analysis at operation 1506, process flow proceeds to operation 1508.

[0482] In one embodiment, at operation 1508 a grade is assigned to the dry wood product based on the determined strength of the dry wood product.

[0483] In one embodiment, once a grade is assigned to the dry wood product based on the determined strength of the dry wood product process flow proceeds to operation 1510.

[0484] In one embodiment, at operation 1510, one or more actions are taken with respect to the dry wood product based, at least in part, on the grade assigned to the dry wood product at operation 1508.

[0485] In one embodiment, one or more actions that can be taken at operation 1510 include, but are not limited to: sorting the dry wood product/veneer sheet into a bin, location or stack associated with the assigned grade; restricting the use of the dry wood product/veneer sheet based on the grade assigned to the dry wood product/veneer sheet; rejecting the dry wood product/veneer sheet based on the grade assigned to the dry wood product/veneer sheet; sending the dry wood product/veneer sheet back for further processing based on the grade assigned to the dry wood product/veneer sheet; adjusting one or more processing parameters of a production line based, at least in part, on the grade assigned to the dry wood product/veneer sheet and/or the grades assigned other wood products; adjusting various processing parameters on a production line based, at least in part, on grade assigned to the dry wood product/veneer sheet and/or the grades assigned other wood products; and selecting a type and amounts of glues used on a production line based, at least in part, on grade assigned to the dry wood product/veneer sheet and/or the grades assigned other wood products.

[0486] As noted, in one embodiment, the action taken at 1510 can include sorting the dry wood product/veneer sheet into a bin, location or stack associated with the grade assigned to the dry wood product/veneer sheet.

[0487] In one embodiment, sorting the dry wood product/veneer sheet into a bin, location or stack associated with the grade assigned to the dry wood product/veneer sheet is performed at an automated stacking station.

[0488] In one embodiment, at the automated stacking station, the individual veneer sheets are stacked according to the grade assigned to the veneer sheet using any of the stacking systems described in related applications Bolton et al., U.S. application Ser. No. 16/697,458 filed on Nov. 27, 2019 and issuing Aug. 17, 2021 as U.S. Pat. No. 11,090,833; Bolton et al., U.S. application Ser. No. 17/356,804 filed on Jun. 24, 2021; Bolton et al., U.S. application Ser. No. 17/356,805 filed on Jun. 24, 2021; Bolton et al., U.S. application Ser. No. 17/361,808 filed on Jun. 29, 2021; and Bolton et al., U.S. application Ser. No. 17/366,432, filed Jul. 2, 2021, which are hereby incorporated by reference in their entirety as if it were fully set forth herein.

[0489] Consequently, some disclosed embodiments use NIR technology to predict the strength of a sheet of veneer from the NIR spectra of dry veneer. This allows for the gradings and sorting of dry veneer after drying and moisture analysis to provide enhanced grading technology and more accurate wood product grading.

[0490] Once one or more actions with respect to the wood product at operation 1520, process flow proceeds to END operation 1534 where process 1500 is exited to await new samples and/or data.

[0491] As shown above, the disclosed embodiments utilize NIR cameras to scan the surface of a wood product for moisture and create an NIR image of the surface of the wood product. Since essentially each pixel of camera image data is a sample point, the resolution and accuracy of the moisture detection process is the number of pixels the camera has covering the field of view, e.g., the entire first surface of a wood product. Consequently, in the case where a 1.3 mega pixel camera is there are essential 1,300,000 individual measurement points on the surface of the wood product. Consequently, using NIR cameras, as disclosed herein, results in resolutions and accuracy that simply cannot be achieved using traditional moisture detection systems such as traditional contact electrode systems or RF moisture detection systems.

[0492] As noted, using traditional moisture detection systems such as traditional contact electrode systems or RF moisture detection systems accuracy levels are at best subject to the ±5% or the ±7.5% margin of error, respectively. This resulted in the need to be very conservative when determining the potential use of a given veneer sheet or other wood product and often resulted in wood products, such as veneer sheets, not being put to their most cost effective and efficient use simply to ensure that the ±5% or the ±7.5% margin of error did not result in inferior or unsafe wood products.

[0493] In contrast, using the disclosed NIR-based systems, accuracy on the order of ±0.1% is readily achieved. Therefore, the highest value use of a given veneer sheet or other wood product can be accurately determined and the wood products, such as veneer sheets, can be confidently put to their most cost effective and efficient use.

[0494] In addition, when, as disclosed herein, NIR cameras are used as the moisture detection mechanism, when greater or less resolution is deemed necessary, a higher or lower mega-pixel camera can be selected to achieve the desired resolution for the process. In addition, unlike tradition contact electrode and RF moisture detection systems, NIR camera placement with respect to the sample under analysis can be adjusted such that a quality image can be obtained as long as there is a clear field of view between the wood product surface and NIR camera. Horizontal, vertical, or angled placements have no impact on the functionality of the NIR camera. Further, combinations of NIR cameras and lenses can provide opportunities to perform measurements that are currently prohibitive due to the need for a conveyor section to convey the material through a sensing array of contact electrodes or RF instruments.

[0495] The use of NIR cameras, are disclosed herein, eliminates the need for any physical contact with the wood product by any part of the moisture detection device, or even the need for the moisture detection device, i.e., the NIR camera, to be close to the wood product surface. Not only does this fact eliminate wear and tear on both the sample taking device and the wood product, but as discussed above it allows for more flexible placement of the sample taking device, i.e., the NIR camera.

[0496] In addition, unlike RF moisture detection devices and contact electrodes, NIR cameras are virtually immune to static electricity or spurious RF emissions. Consequently, use of NIR cameras as disclosed herein is far more suitable for a physical production line environment.

[0497] In addition, unlike traditional contact electrode systems that require high voltages and represent a danger to workers, NIR technology has been deemed to represent no hazards to workers or other devices by several testing and safety agencies. Consequently, the use of the disclosed NIR based moisture detection systems results in a safer and more comfortable and efficient workplace and production floor.

[0498] In addition, using the disclosed NIR strength analysis systems, the antiquated and extremely inefficient and ineffective currently used prior art methods and systems for determining the density, and therefore the strength, of wood products, including veneer sheets, and various other materials is not requited.

[0499] For example, using the disclosed NIR strength analysis systems the use of prior art contact electrode systems and ultrasonic density detection systems similar to the RF detection systems used for moisture detection discussed above is no longer needed. Therefore, the shortcomings inefficiencies, and inaccuracies of prior art ultrasonic density detection systems discussed above are avoided.

[0500] Consequently, in contrast to prior art ultrasonic density detection systems, the disclosed NIR strength analysis systems are quite capable of determining wood product strength within the margins of error now required in many industries. In addition, in contrast to prior art ultrasonic density detection systems, the disclosed NIR strength analysis systems have relatively few moving parts and components so they are less subject to failure, lighter, require significantly less maintenance, than the antiquated, largely ineffective, and inefficient prior art ultrasonic density detection systems.

[0501] The present invention has been described in particular detail with respect to specific possible embodiments. Those of skill in the art will appreciate that the invention may be practiced in other embodiments. For example, the nomenclature used for components, capitalization of component designations and terms, the attributes, data structures, or any other programming or structural aspect is not significant, mandatory, or limiting, and the mechanisms that implement the invention or its features can have various different names, formats, or protocols. Further, the system or functionality of the invention may be implemented via various combinations of software and hardware, as described, or entirely in hardware elements. Also, particular divisions of functionality between the various components described herein are merely exemplary, and not mandatory or significant. Consequently, functions performed by a single component may, in other embodiments, be performed by multiple components, and functions performed by multiple components may, in other embodiments, be performed by a single component.

[0502] Some portions of the above description present the features of the present invention in terms of algorithms and symbolic representations of operations, or algorithm-like representations, of operations on information/data. These algorithmic or algorithm-like descriptions and representations are the means used by those of skill in the art to most effectively and efficiently convey the substance of their work to others of skill in the art. These operations, while described functionally or logically, are understood to be implemented by computer programs or computing systems. Furthermore, it has also proven convenient at times to refer to these arrangements of operations as steps or modules or by functional names, without loss of generality.

[0503] In addition, the operations shown in the figures, or as discussed herein, are identified using a particular nomenclature for ease of description and understanding, but other nomenclature is often used in the art to identify equivalent operations.

[0504] Therefore, numerous variations, whether explicitly provided for by the specification or implied by the specification or not, may be implemented by one of skill in the art in view of this disclosure.