METHOD FOR OPERATING A MACHINE FOR HARVESTING AND/OR SEPARATING ROOT CROPS, ASSOCIATED MACHINE AND ASSOCIATED COMPUTER PROGRAM PRODUCT

Abstract

A method is provided for operating a machine for harvesting root crops and/or for separating root crops from further additionally conveyed material that includes at least soil in the form of loose earth and/or soil aggregates, and also, if applicable, leaves and/or stones. By means of at least one electromagnetic, in particular optical, or acoustic image capturing unit, at least one inspection image is captured of at least one portion of the material, moved relative to a machine frame of the machine by at least one transport element, in particular a screen belt. On the basis of at least one inspection data set generated using the inspection image and/or formed by this image, an evaluation device generates an adjustment signal for adjusting at least one operating parameter of the transport element and/or a further transport element of the machine. At least one feature for describing the ability to be screened of the additionally conveyed soil is determined by the evaluation device and is used for adjusting the operating parameter. The invention also relates to a machine for harvesting root crops and a computer program product.

Claims

1. A method for operating a machine for harvesting root crops and/or for separating root crops from further additionally conveyed material that includes at least soil in the form of loose earth and/or soil aggregates, the method comprising the steps of: capturing, by means of at least one electromagnetic or acoustic image acquisition unit, at least one inspection image of at least one portion of the material moved relative to a machine frame of the machine by at least one transport element generating, on the basis of at least one inspection data set generated using the inspection image and/or formed by this image, via an evaluation device, an adjustment signal for adjusting at least one operating parameter of the transport element and/or a further transport element of the machine, determining at least one feature for describing a capability of the additionally conveyed soil to be screened by the evaluation device and using the at least one feature for adjusting the operating parameter.

2. The method as claimed in claim 1, wherein the feature comprises one or more values which describe the size, shape, strength, or color of one or more soil aggregates and/or one or more distributions of the size, shape, strength or color of a plurality of soil aggregates.

3. The method as claimed in claim 1 wherein the feature is determined by the evaluation device on the basis of an input data set, generated by or formed by the inspection data set, by a neural-network-based, histogram-based and/or structure-from-motion analysis.

4. The method as claimed in claim 3, wherein the neural network is a convolutional neural network, which classifies each input data set into one of a number of classes which represent the values of different screening capability features.

5. The method as claimed in claim 1, wherein by means of a classification method, constituents of the material present in the inspection image are determined.

6. The method as claimed in claim 3, wherein for the determination of the feature by the evaluation device, a region of the inspection image or of the inspection data set is selected that contains at least 75 soil aggregates.

7. The method as claimed in claim 6, wherein a part of the inspection data set representing the region is provided directly or in processed form as an input data set into the neural-network-based, histogram-based and/or structure-from-motion analysis, in which the region is assigned the feature which is used for adjusting the operating parameter.

8. The method as claimed in claim 1, wherein the evaluation device at least partly evaluates the inspection data sets locally on the machine or on a directly connected towing vehicle.

9. The method as claimed in claim 1, wherein the evaluation device evaluates the inspection data records on a wirelessly connected server.

10. The method as claimed in claim 1, wherein the operating parameter of the transport element formed as a screening band is a screening band speed, a collection screening band speed, an adjustable height of at least one triangular roller, an adjustable height of a drop stage, a frequency of a knocker, an amplitude of a knocker, the position of a knocker, and/or the inner width of the screening band.

11. The method as claimed in claim 1, wherein a moisture content of the soil aggregates is determined by a moisture sensor and used in the evaluation device for adjusting the operating parameter.

12. The method as claimed in claim 1, wherein the determination of the operating parameter is part of a control loop of the machine.

13. The method as claimed in claim 12, wherein a rooting depth and/or a driving speed are additionally controlled with the control loop.

14. The method as claimed in claim 1, wherein the operating parameter is adjusted by a database in which features and operating parameter are stored such that they are linked to each other.

15. A machine for harvesting root crops and/or for separating root crops, the machine comprising: at least one electromagnetic or acoustic image acquisition unit, at least one a transport element, selectively moveable relative to a machine frame of the machine, and an evaluation device as well as means for adjusting the transport element or an additional transport element, wherein the machine for carrying out the steps of the method as claimed in claim 1.

16. A computer program product comprising commands which cause the machine according to claim 15 to execute the following steps: capturing, by means of at least one electromagnetic or acoustic image acquisition unit, at least one inspection image of at least one portion of material moved relative to the machine frame of the machine by the at least one transport element, generating, on the basis of at least one inspection data set generated using the inspection image and/or formed by this image, via the evaluation device, an adjustment signal for adjusting at least one operating parameter of the at least one transport element and/or a further transport element of the machine, determining at least one feature for describing a capability of additionally conveyed soil to be screened by the evaluation device, and using the at least one feature for adjusting the operating parameter.

Description

BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Reference is now made more particularly to the drawings, which illustrate the best presently known mode of carrying out the invention and wherein similar reference characters indicate the same parts throughout the views.

[0051] FIG. 1 shows a machine according to the invention in a side view.

[0052] FIG. 2 shows a part of the object according to FIG. 1 in a perspective view.

[0053] FIG. 3 shows the part of the object according to FIG. 1 that is acquired by an optical image acquisition unit.

[0054] FIG. 4 shows the selection of a region of an inspection image.

[0055] FIG. 5 shows the classification options of the region according to FIG. 4.

[0056] FIG. 6 shows a means of manipulating the screening band.

[0057] FIG. 7 shows a further means of manipulating the screening band.

[0058] FIG. 8 shows a further means of manipulating the screening band.

[0059] FIG. 9 shows a further means of manipulating the screening band.

[0060] FIG. 10 shows a flow diagram of a method according to the invention.

[0061] FIG. 11 shows a further diagram for a further method sequence according to the invention.

DETAILED DESCRIPTION OF THE INVENTION

[0062] Individual technical features of the exemplary embodiments described below, in combination with the exemplary embodiments described above as well as the features of the independent claims and any additional claims, can also lead to subject matter according to the invention. Where appropriate, functionally equivalent elements are provided with identical reference numbers.

[0063] A machine 2 is designed in the present case for harvesting root crops in the form of potatoes, and thus as a potato harvester. The material in the form of soil or soil aggregates, root crops, leaves and/or stones collected in the region of a receptacle 4 is transported in a conveying direction 1A via transport elements in the form of screening bands 10, mounted behind a machine frame 6 as well as other frame parts 8. A screening band 10 connects directly to the receptacle 4 (FIG. 2). The material transported in the direction 1A by means of the screening band 10 is captured by a first optical image acquisition unit 12 in the form of an RGB camera, which is fixed to a machine frame part 9 aligned at an angle to the screening band 10 in the direction of the receptacle 4. A lighting means 14 illuminates the screening band in the region of a second image acquisition unit 12, which is located behind the first image acquisition unit 12 in the conveying direction 1A.

[0064] The region of the machine 2 captured by the first image acquisition unit 12 arranged on the right in FIG. 2, is shown in FIG. 3, here not filled with earth. The individual screening bars 16 of the screening band 10, which is mounted directly downstream of the horizontal rooting blades 18 of the receptacle 4, are particularly visible. Below the screening band 10, adjustment means for adjusting operating parameters for the operation of the screening band 10 are provided on the machine frame 6. These can be the rollers 20 shown in FIG. 3, which can be part of additional adjustment devices, depending on the design of the machine 2 according to the invention. Using an evaluation device, an image section 22 is automatically selected (FIG. 4), in which as few root crops 24 as possible as well as additional materials 26 (here: leaves) are included. The image section 22 shown consists of at least 90% soil aggregates 28 and is already aligned at right angles, while the rest of the image is still slightly distorted in perspective.

[0065] The recognition of the leaves and the soil aggregates is carried out by means of a pixel-by-pixel classification, for example, using the color values acquired by the optical image acquisition unit 12 comprising values representing grayscale and/or actual colors. These are compared with reference values or reference value ranges. This form of differentiation enables a qualitative identification of the constituent on the inspection image and assigns a pixel to a class of (crop) material (earth/soil aggregates, leaves, root crop, stone), in particular within specifiable or specified threshold values.

[0066] Once a region 22 has been identified, the inspection data set or portion of the inspection data set representing that region is fed to the neural network, if necessary in a format adapted to the input requirements of the network. The neural network, in particular a CNN, assigns the image region at least one soil aggregate size, and in another embodiment of the invention also components of different size distributions of screening band sections in the image. The extract in FIG. 4 shows a clod size with particularly large clods, as can be seen in FIG. 5 on the right of the picture. Moving to the left from this right-hand image portion, additional size classes of soil aggregates are shown, which are recognized by the neural network and with which the neural network was trained in advance.

[0067] Depending on the aggregate size defined in this way, an operating parameter, e.g. an amplitude of a deflection or a frequency of the movement of the vibrating knocker 30 shown in FIG. 6, can be varied. The vibration of this device transmits impulses to the screening band 10, which causes crushing of soil aggregates, in particular clods. Alternatively or in addition, a frequency of the rotor knocker 32 shown in FIG. 7 or a position of the triangular wheel 34 shown in FIG. 8 is varied in relation to the machine frame 6 supporting the screening band. An adjustment rail 30 (FIG. 9) can also be varied in terms of its distance to the belt 3 of the screening band 10, so that the screening bar units, each formed from two screening bars 16 connected by connectors 38, can be moved and thus the inner width of the opening between successive bars of successive screening bar units can be varied.

[0068] A sequence of a method according to the invention shown in FIG. 10 begins with a first method step 40, in which an image acquisition unit 12 generates an inspection data set 42 which is then qualitatively divided up by means of pixel-based classification in step 43, so that individual image regions or pixels of the inspection data set can be assigned 44 to potatoes, leaves, earth or soil, etc. Then, in step 46, a region or image section 22 is selected that only contains earth and hence soil aggregates. This region 22 is analyzed in step 50 with a CNN, which in the result 52 assigns a size class according to FIG. 5 to the image section. Then, in step 54, if appropriate, the operating parameters are changed by outputting or initiating adjustment signals, whereupon the screening performance of the screening band 10 is adjusted.

[0069] The adjustment of the screening performance of the screening band 10 and thus also the screening conveyor in accordance with step 54 is preferably part of a control loop 60 (FIG. 11), in which a machine control system 62 comprising the evaluation device accesses a locally or externally existing data bank 64 and receives assignment rules from it for adjustments of the operating parameters of the screening band according to step 54, rooting depth settings 66, and/or driving speeds 68. In the machine control system 62, a large amount of other information can also be processed. This includes information from a level detector 70 at the beginning of the screen and/or a level detector 72 at the end of the screening band and/or pressure information 74 of any separators and/or information from a blockage detector 76 of any separators. Finally, the actual values of the individual operating parameters of the individual functional units can be acquired in step 78 and processed as input information for the machine control system 62.

[0070] Typically, an evaluation device 80 is part of the machine control system 62. Additional input information for the machine control system 62 includes, in addition to the estimation 52 of the soil aggregate size, clearing strategies 82 and/or environmental information about weather and soil type, which can be specified by the operating personnel and which come from an acquisition device 84. A circle 86 symbolizes the influence of the size class recognition 52 carried out by the evaluation device, the clearing strategy acquisition 82 and the environmental variable acquisition 84 on the clearing performance of the machine 2 represented by steps 70 to 78. For example, in a clearing strategy that focuses on maximum yield, on detection of a maximum aggregate size class the amplitude of the vibrating knocker, the screening bar spacing, and the band speed can be maximized, while in a less aggressive strategy the amplitude can be applied to a lesser degree and the band speed reduced at the same time.