Additive manufacturing system and method and feature extraction method

Abstract

An additive manufacturing (AM) method includes using an AM tool to fabricate a plurality of workpiece products; measuring qualities of the first workpiece products respectively; performing a temperature measurement on each of the melt pools on the powder bed during a fabrication of each of the workpiece products; performing photography on each of the melt pools on the powder bed during the fabrication of each of the workpiece products; extracting a length and a width of each of the melt pools; performing a melt-pool feature processing operation; building a conjecture model by using a plurality of sets of first process data and the actual metrology values of the first workpiece products in accordance with a prediction algorithm; and predicting a virtual metrology value of the second workpiece product by using the conjecture model based on a set of second process data.

Claims

1. An additive manufacturing (AM) method, comprising: using an AM tool to fabricate a plurality of workpiece products, wherein the workpiece products are divided into a plurality of first workpiece products and a second workpiece product, and the second workpiece product is fabricated after the first workpiece products, an operation of fabricating each of the workpiece products comprising: placing a powder layer on a powder bed; and directing an energy beam to a plurality of powder bodies on the powder layer sequentially to melt powder bodies to form a plurality of melt pools; measuring qualities of the first workpiece products respectively after the first workpiece products are completely fabricated, thereby obtaining a plurality of actual metrology values of the first workpiece products; performing a temperature measurement on each of the melt pools on the powder bed during a fabrication of each of the workpiece products, thereby obtaining a temperature of each of the melt pools of each of the workpiece products; performing photography on each of the melt pools on the powder bed during the fabrication of each of the workpiece products, thereby obtaining an image of each of the melt pools of each of the workpiece products; extracting a length and a width of each of the melt pools from the image of each of the melt pools; performing a melt-pool feature processing operation to convert the length, the width and the temperature of each of the melt pools to a melt-pool length feature, a melt-pool width feature and a melt-pool temperature feature of each of the workpiece products; building a conjecture model by using a plurality of sets of first process data and the actual metrology values of the first workpiece products in accordance with a prediction algorithm, the sets of first process data comprising the melt-pool length feature, the melt-pool width feature and the melt-pool temperature feature of each of the first workpiece products; and predicting a virtual metrology value of the second workpiece product by using the conjecture model based on a set of second process data, the set of second process data comprising the melt-pool length feature, the melt-pool width feature and the melt-pool temperature feature of the second workpiece product.

2. The additive manufacturing (AM) method of claim 1, further comprising: performing a simulation operation based on the sets of process data and/or the actual metrology values of the workpiece products, thereby generating a set of suggested parameter ranges; generating a set of process-parameter adjusted values based on the virtual metrology value; generating a set of process-parameter tracking values based on the set of process-parameter adjusted values, the set of suggested parameter ranges and a set of parameter design values; and controlling and adjusting the AM tool to process the second workpiece product in accordance with the set of process-parameter tracking values.

3. The additive manufacturing (AM) method of claim 1, wherein the melt-pool length feature, the melt-pool width feature and the melt-pool temperature feature comprise a maximum value, a minimum value, a mean value, a variance, a standard deviation, a skewness of statistic distribution, a kurtosis of statistic distribution, a full distance and/or a set of quantile of lengths of the melt pools in each of at least one predetermined area; a maximum value, a minimum value, a mean value, a variance, a standard deviation, a skewness of statistic distribution, a kurtosis of statistic distribution, a full distance and/or a set of quantile of widths of the melt pools in each of the at least one predetermined area; and a maximum value, a minimum value, a mean value, a variance, a standard deviation, a skewness of statistic distribution, a kurtosis of statistic distribution, a full distance and/or a set of quantiles of temperatures of the melt pools in each of the at least one predetermined area.

4. The additive manufacturing (AM) method of claim 1, further comprising: extracting a central location of each of the melt pools from the image of each of the melt pools; and performing the melt-pool feature processing operation to convert the central location of each of the melt pools to a central-location feature of each of the workpiece products.

5. An additive manufacturing (AM) feature extraction method, comprising: performing a temperature measurement on each of a plurality of melt pools on a powder bed during a fabrication of a workpiece product, thereby obtaining a temperature of each of the melt pools of the workpiece product; performing photography on each of the melt pools on the powder bed during the fabrication of the workpiece product, thereby obtaining a plurality of images of the melt pools of the workpiece product; extracting a length and a width of each of the melt pools from the images; and performing a melt-pool feature processing operation to convert the length, the width and the temperature of each of the melt pools to a melt-pool length feature, a melt-pool width feature and a melt-pool temperature feature of the workpiece product; and extracting a central location of each of the melt pools from the image of each of the melt pools; and performing the melt-pool feature processing operation to convert the central location of each of the melt pools to a central-location feature of the workpiece product.

6. The additive manufacturing (AM) feature extraction method of claim 5, wherein the melt-pool length feature, the melt-pool width feature and the melt-pool temperature feature comprise a maximum value, a minimum value, a mean value, a variance, a standard deviation, a skewness of statistic distribution, a kurtosis of statistic distribution, a full distance and/or a set of quantile of lengths of the melt pools in each of at least one predetermined area; a maximum value, a minimum value, a mean value, a variance, a standard deviation, a skewness of statistic distribution, a kurtosis of statistic distribution, a full distance and/or a set of quantile of widths of the melt pools in each of the at least one predetermined area; and a maximum value, a minimum value, a mean value, a variance, a standard deviation, a skewness of statistic distribution, a kurtosis of statistic distribution, a full distance and/or a set of quantiles of temperatures of the melt pools in each of the at least one predetermined area.

Description

BRIEF DESCRIPTION OF THE DRAWINGS

(1) The invention can be more fully understood by reading the following detailed description of the embodiment, with reference made to the accompanying drawings as follows:

(2) FIG. 1A is a schematic diagram showing an additive manufacturing (AM) system in accordance with some embodiments of the disclosure;

(3) FIG. 1B is a schematic diagram showing an additive manufacturing (AM) tool on a process stage in accordance with some embodiments of the disclosure;

(4) FIG. 2A is a schematic block diagram of an in-situ metrology system in accordance with some embodiments of the disclosure;

(5) FIG. 2B is a schematic diagram showing additive manufacturing (AM) features in accordance with some embodiments of the disclosure;

(6) FIG. 2C is a schematic diagram showing extraction results of additive manufacturing (AM) features in accordance with some embodiments of the disclosure;

(7) FIG. 3 a schematic block diagram of a virtual metrology (VM) system in accordance with some embodiments of the disclosure;

(8) FIG. 4 a schematic block diagram of a compensator in accordance with some embodiments of the disclosure; and

(9) FIG. 5 illustrates a schematic flow chart showing an additive manufacturing (AM) method in accordance with some embodiments of the disclosure.

DETAILED DESCRIPTION

(10) Reference will now be made in detail to the present embodiments of the invention, examples of which are illustrated in the accompanying drawings. Wherever possible, the same reference numbers are used in the drawings and the description to refer to the same or like parts.

(11) Referring to FIG. 1A, FIG. 1A is a schematic diagram showing an additive manufacturing (AM) system 10 in accordance with some embodiments of the disclosure, in which switches C11, C12 and C13 are used for selecting if data are inputted to a corresponding system or device. The AM system 10 includes an AM tool 100, a product metrology system 120, an in-situ metrology system 200, a VM system 130, a compensator 140, a track planner 150, a controller 160, a simulator 170 and an augmented reality (AR) device 180.

(12) Referring to FIG. 1B, FIG. 1B is a schematic diagram showing the AM tool 100 on a process stage in accordance with some embodiments of the disclosure. The AM tool 100 includes a powder bed 110 and a fusion system 102 (such as a laser source). The power bed 110 includes a powder bed container 116 in which a substrate 114 and a powder layer 112 placed on the substrate 114 are held, in which the powder bed 112 includes plural powder bodies. The AM tool 100 uses a powder bed fusion process to fabricate workpiece products. During the fabrication process of each of the workpiece products, the fusion system 102 is used to provide an energy beam 104 to the respective powder bodies of the powder bed 110, and the powder layer 112 is melted to form and obtain a desired profile of the workpiece product by controlling specific parameters. When the respective powder bodies are melted. Plural melt pools are formed on the powder bed 110. In some embodiments, the powder bed fusion process is a selective laser melting (SLM) process, or a selective laser sintering (SLS) process.

(13) As shown in FIG. 1A, an object of the simulator 170 is to find feasible process parameter ranges, and the AR device 180 is configured to assist the operation and maintenance of the AM tool 100. The product metrology system 120, the in-situ metrology system 200, the VM system 130 are integrated to estimate variation of each material layer on the powder bed 110 of the AM tool 100. The compensator 140 can compensate process variation online (on the production line) or offline (off the production line) by adjusting process parameters. The product metrology system 120 is configured to measure qualities of the workpiece products respectively after the workpiece products are completely fabricated, thereby obtaining plural actual metrology values EM (such as an actual metrology value of surface roughness or porosity, etc.). The in-situ metrology system 200 is configured to collect a set of feature data IM of each melt pool on the powder bed 110 during a fabrication process of each workpiece product, and the set of feature data IM (melt pool characteristics) includes a melt-pool length feature, a melt-pool width feature and a melt-pool temperature feature.

(14) The VM system 130 is configured to use sets of process data PD and actual metrology values EM of the workpiece products to predict a virtual metrology value VM (such as a virtual metrology value of surface roughness or porosity, etc.) of a next workpiece product processed by the AM tool 100 in accordance with a prediction algorithm after the workpiece products have been fabricated by the AM tool 100, each of the sets of process data PD including the melt-pool length feature, the melt-pool width feature and the melt-pool temperature feature of each of the workpiece products. In addition, the sets of process data PD also may include process parameter data PP (such as laser power values, etc.) provided by the controller 160 and sensing data IS (such as flow speed, oxygen density, etc.) provided by the AM tool 100.

(15) In some embodiments, the prediction algorithm used by the VM system 130 may be a neural network algorithm or a multiple regression algorithm. However, another algorithm is also applicable to the disclosure, such as a back propagation neural network (BPNN) algorithm, a general regression neural network (GRNN) algorithm, a radial basis function neural network (RBFNN) algorithm, a simple recurrent network (SRN) algorithm, a support vector data description (SVDD) algorithm, a support vector machine (SVM) algorithm, a multiple regression (MR) algorithm, a partial least squares (PLS) algorithm, a nonlinear iterative partial least Squares (NIPALS) algorithm, or a generalized linear models (GLMs), etc. Thus, the disclosure is not limited thereto.

(16) The simulator 170 is configured to perform a simulation operation based on the sets of process data PD and/or the actual metrology values EM of the workpiece products, thereby generating a set of suggested parameter ranges PR. The compensator 140 is configured to generate a set of process-parameter adjusted values based on the virtual metrology value VM of the next workpiece product, in which the process-parameter adjusted values may be divided into on-line (on the production line) process-parameter adjusted values PA.sub.on and off-line process-parameter adjusted values PA.sub.off. The track planner 150 is configured to generate a set of process-parameter tracking values PT based on the set of off-line process-parameter adjusted values PA.sub.off, the set of suggested parameter ranges PR and a set of parameter design values. The controller 160 is configured to control and adjust the AM tool 100 to process the next workpiece product in accordance with the set of process-parameter tracking values PT. The simulator 170 used in the embodiments of the disclosure may be based on U.S. Patent Publication No. 20190128738, which is hereby incorporated by reference.

(17) Hereinafter, the in-situ metrology system 200 is explained. Referring to FIG. 2A, FIG. 2A is a schematic block diagram of the in-situ metrology system 200 in accordance with some embodiments of the disclosure. The in-situ metrology system 200 includes a coaxial camera 202, a pyrometer 204, an overview camera 206 and an in-situ metrology server 210. The pyrometer 204 is configured to perform a temperature measurement on each of the melt pools on the powder bed during a fabrication of each of the workpiece products, thereby obtaining a temperature of each of the melt pools of each of the workpiece products. In some embodiments, the pyrometer 204 is configured to perform a temperature measurement on each melt pool of each powder layer on the powder bed during a fabrication of each of the workpiece products. The coaxial camera 202 is configured to perform photography on each of the melt pools on the powder bed during the fabrication of each of the workpiece products, thereby obtaining an image of each of the melt pools of each of the workpiece products. The in-situ metrology server 210 includes an image-feature extraction device 220, a multithread allocation device 230, a FTP (File Transfer Protocol) client 240 and melt-pool feature processing devices 232/242. The image-feature extraction device 220 is configured to extract a length and a width of each of the melt pools from the image of each of the melt pools, and extract a melt-pool temperature of each melt pool from the melt-pool temperatures measured by the pyrometer 204. The melt-pool feature processing devices 232/242 are configured to convert the length, the width and the temperature of each melt pool of each workpiece product to a melt-pool length feature, a melt-pool width feature and a melt-pool temperature feature of each workpiece product. After a melt-pool length feature, a melt-pool width feature and a melt-pool temperature feature of each workpiece product are obtained, the VM system uses plural sets of process data and the actual metrology values of the workpiece products to predict a virtual metrology value of a next workpiece product processed by the AM tool in accordance with a prediction algorithm after the workpiece products have been fabricated by the AM tool, the sets of process data comprising the melt-pool length feature, the melt-pool width feature and the melt-pool temperature feature of each of the workpiece products.

(18) There are two computing loading modes in the in-situ metrology system 200, which are a light loading mode and a heavy loading mode. The light loading mode is applicable to workpieces with simple structures, such as the workpieces with no or few supporting pieces. The heavy loading mode is applicable to workpieces with complicated structures, such as the workpieces with a lot of supporting pieces, and the workpieces with diversified geometrical shapes.

(19) The light loading mode and the heavy loading mode depend on the photographing frequency of the coaxial camera 202 and the sampling rate of the image-feature extraction device 220. A user may select a switch C21 or C22 to activate the light loading mode or the heavy loading mode in accordance with actual requirements. In the light loading mode, the features are extracted by conventional image preprocessing, and in contrast, the heavy loading mode uses a CNN (Conventional Neural Network)-based method in parallel computation. In the light loading mode, due to the high sampling rate, the in-situ metrology system 200 uses the multithread allocation device 230 to distribute a large amount of melt-pool images to different cores in a computer. In the heavy loading mode, the in-situ metrology system 200 is built on a parallel processing platform 246 (such as Hadoop). Hadoop is a distributed parallel processing platform for big data, which can start melt pool feature extraction (MPFE) per requests. A CNN-based MPFE can identify widths, lengths, and central locations of melt pools in different isothermal envelopes.

(20) An additive manufacturing (AM) feature extraction method performed by the in-situ metrology system 200 according to some embodiments of the disclosure will be described in the below. Referring to FIG. 2B and FIG. 2C, FIG. 2A is a schematic block diagram of an in-situ metrology system in accordance with some embodiments of the disclosure; and FIG. 2B is a schematic diagram showing additive manufacturing (AM) features in accordance with some embodiments of the disclosure.

(21) At first, during the powder bed fusion process of a workpiece product, the coaxial camera 202 is used at a predetermined frequency (for example, 4 kHz) to perform photograph on the powder bed, so as to obtain n melt-pool images (such as a melt-pool image 260 shown in FIG. 2B), the melt-pool images including an image of each melt pool (such as a melt pool A1 shown in FIG. 2B). Meanwhile, the pyrometer 204 is used at a predetermined frequency (for example, 100 kHz) to perform temperature measurements on the powder bed, thereby obtaining the temperature of each melt pool, and the overview camera is used at a predetermined frequency (for example, 4 kHz) to perform photography on the powder bed layer by layer, thereby obtaining plural work space images. The work space images can be used subsequently to find the locations at which abnormal quality occurs, and thus can be used as the base for quality evaluation.

(22) Thereafter, the image-feature extraction device 220 receives the image and temperature of each melt pool, and the images of work space images. The image-feature extraction device 220 stores these data into a memory 222, and provides instant download through the FTP server 224. Then, the melt-pool feature processing devices 232 or 242 processes the above data at a sample rate (for example 25 images/second), thereby selecting m sample images and their corresponding temperatures T.sub.i from the melt-pool images, where i=1 to m, m>0. Thereafter, the melt-pool feature processing devices 232 or 242 extracts a length Li, a width W.sub.i, and a central location (X.sub.i, Y.sub.i) of each melt pool from the m samples images, in which X and Y are values of coordinates (such as an image 262 shown in FIG. 2B), so as to obtain sample melt-pool data FFi=(W.sub.1, Li, X.sub.i, Y.sub.i, T.sub.i), such as shown in FIG. 2C. Then, the melt-pool feature processing devices 232 or 242 performs a melt-pool feature processing operation to convert the sample melt-pool data FFi=(W.sub.1, Li, X.sub.i, Y.sub.i, T.sub.i) to a melt-pool length feature, a melt-pool width feature and a melt-pool temperature feature of each melt pool of the workpiece product. In the melt-pool feature processing operation, at first, at least one predetermined area S.sub.j is defined at a periphery of the central location (X.sub.i, Y.sub.i), for example, an area extending ±3 pixels from the central location (X.sub.i, Y.sub.i). In some embodiments, the predetermined area S.sub.j is an area containing all of the sample melt-pool data FFi=(W.sub.1, Li, X.sub.i, Y.sub.i, T.sub.i). Then, the melt-pool length feature L.sub.j, the melt-pool width feature W.sub.j, and the melt-pool temperature feature T.sub.j in the predetermined area S.sub.j is calculated. The melt-pool length feature L.sub.j includes a maximum value, a minimum value, a mean value, a variance, a standard deviation, a skewness of statistic distribution, a kurtosis of statistic distribution, a full distance and/or a set of quantile of lengths of the melt pools in the predetermined area S.sub.j. The melt-pool width feature W.sub.j includes a maximum value, a minimum value, a mean value, a variance, a standard deviation, a skewness of statistic distribution, a kurtosis of statistic distribution, a full distance and/or a set of quantile of widths of the melt pools in each of the predetermined area S.sub.j. The melt-pool temperature feature T.sub.j includes a maximum value, a minimum value, a mean value, a variance, a standard deviation, a skewness of statistic distribution, a kurtosis of statistic distribution, a full distance and/or a set of quantile of temperatures of the melt pools in each of the predetermined area S.sub.j. It is understood that the computation methods of the maximum value, the minimum value, the mean value, the variance, the standard deviation, the skewness of statistic distribution, the kurtosis of statistic distribution, the full distance and the set of quantile of data points (such as lengths, widths or temperatures) are well known by those having ordinary knowledge in the art, and thus are not described herein.

(23) Hereinafter, the VM system 130 is described. Referring to FIG. 3, FIG. 3 a schematic block diagram of the VM system 130 in accordance with some embodiments of the disclosure. The VM system 130 used in embodiments of the disclosure can be referenced to U.S. Pat. No. 8,095,484 B2, and embodiments of the disclosure can be combined with a VM system based on U.S. Pat. No. 8,095,484 B2, which is hereby incorporated by reference.

(24) The VM system 130 is divided into a model-building stage and a conjecturing stage. In the model-building stage, the VM system 130 builds a conjecture model by using plural sets of historical process data PD obtained when plural historical workpiece products are fabricated, and actual metrology values EM of the historical workpiece products measured after complete fabrication in accordance with a prediction algorithm. The VM system 130 also builds a process data quality index (DQI.sub.x) model and a global similarity index (GSI) mode by using the sets of historical process data PD of the historical workpiece products, and computes a DQI.sub.X threshold and a GSI threshold. The VM system 130 also builds a metrology data quality index (DQI.sub.y) model by using the actual metrology values EM of the historical workpiece products, and computes a DQI.sub.y threshold. The RI value is designed to gauge the reliance level of a virtual metrology value. The GSI value is used to assess the degree of similarity between the current set of input process data and all of the sets of process data used for building and training a conjecture model. The GSI value is provided to help the RI value gauge the reliance level of the VM system 130. The DQI.sub.x value is used to evaluate whether a set of process data used for producing a workpiece is abnormal, and the DQI.sub.y value is used to evaluate whether the metrology data of the workpiece are abnormal.

(25) In the conjecturing stage, the VM system 130 predicts a virtual metrology value VM of a workpiece product to be measured by using the conjecture model based on a set of process data PD that is obtained when the workpiece product to be measured is fabricated by the AM tool 100. The sets of process data and historical process data PD include the melt-pool length feature, the melt-pool width feature and the melt-pool temperature feature of each of the historical workpiece product and the workpiece product to be measured. Besides, the process data and historical process data PD may also include process parameter data PP (such as laser power values, etc.) provided by the controller 160 and sensing data IS (such as flow speed, oxygen density, etc.) provided by the AM tool 100. It is noted that the VM system 130 may conjecture a VM value of an end-product workpiece or VM values of respective material layers of one product workpiece.

(26) The compensator 140 will be described in the below. Referring to FIG. 4, FIG. 4 a schematic block diagram of the compensator 140 in accordance with some embodiments of the disclosure. The process parameters (such as laser power, scan speed, etc.) of the AM tool 100 can be adjusted by the compensator 140 with virtual metrology values VM based on an evolution optimization method. The compensator 140 includes a parameter optimization device 142 and a fuzzy controller 144. The parameter optimization device 142 selects optimal parameters with, for example, a Hybrid Taguchi-Genetic Algorithm (HTGA) and quality objective parameter ranges. The fuzzy controller 144 suggests the on-line process-parameter adjusted values PA.sub.on through scan rules. Then, the controller 160 modifies its parameters by layers according to the on-line process-parameter adjusted values PA.sub.on.

(27) Hereinafter, an additive manufacturing (AM) method is explained. Referring to FIG. 5, FIG. 5 illustrates a schematic flow chart showing an AM method in accordance with some embodiments of the disclosure. As shown in FIG. 5, step 310 is first performed to use an AM tool to fabricate workpiece products, in which the workpiece products includes first workpiece products (i.e. the historical workpiece products for molding building) and a second workpiece product (the workpiece product to be measured), and the second workpiece product is fabricated after the first workpiece products. An operation of fabricating each of the workpiece products includes placing a powder layer on a powder bed; and directing an energy beam to powder bodies on the powder layer sequentially to melt powder bodies to form melt pools. Qualities of the first workpiece products are measured respectively after the first workpiece products are completely fabricated (step 320), thereby obtaining actual metrology values of the first workpiece products. A temperature measurement is performed on each of the melt pools on the powder bed during a fabrication of each of the workpiece products, thereby obtaining a temperature of each of the melt pools of each of the workpiece products (step 330). Photograph is performed on each of the melt pools on the powder bed during the fabrication of each of the workpiece products (step 340), thereby obtaining an image of each of the melt pools of each of the workpiece products. A length, a width and a central location of each of the melt pools is extracted from the image of each of the melt pools (step 350). Thereafter, a melt-pool feature processing operation (step 360) is performed to convert the length, the width and the temperature of each of the melt pools to a melt-pool length feature, a melt-pool width feature and a melt-pool temperature feature of each of the workpiece products. Thereafter, a conjecture model is built by using plural sets of first process data and the actual metrology values of the first workpiece products in accordance with a prediction algorithm (step 370), in which the sets of first process data include the melt-pool length feature, the melt-pool width feature and the melt-pool temperature feature of each of the first workpiece products. Then, a virtual metrology value of the second workpiece product (the product to be measured) is predicted by using the conjecture model based on a set of second process data (step 380), in which the set of second process data includes the melt-pool length feature, the melt-pool width feature and the melt-pool temperature feature of the second workpiece product.

(28) It is understood that the aforementioned steps described in the embodiments of the disclosure can be combined or skipped, and the order thereof can adjusted according actual requirements. The aforementioned embodiments can be realized as a computer program product, which may include a machine-readable medium on which instructions are stored for programming a computer (or other electronic devices) to perform a process based on the embodiments of the present invention. The machine-readable medium can be, but is not limited to, a floppy diskette, an optical disk, a compact disk-read-only memory (CD-ROM), a magneto-optical disk, a read-only memory (ROM), a random access memory (RAM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), a magnetic or optical card, a flash memory, or another type of media/machine-readable medium suitable for storing electronic instructions. Moreover, the embodiments of the present invention also can be downloaded as a computer program product, which may be transferred from a remote computer to a requesting computer by using data signals via a communication link (such as a network connection or the like).

(29) It can be known from the aforementioned embodiments that, by using the AM system provided by the embodiments of the disclosure, the AM tool can be effectively controlled in time. By using the AM feature extraction method provided by the embodiments of the disclosure, AM features can be effectively extracted form an enormous amount of data, thereby successfully performing virtual metrology on additive manufactured products, thus obtaining the quality of an end product or an product that are being processed layer by layer in time, such that process parameters of an AM tool can be adjusted on a production line for increasing yield.

(30) It will be apparent to those skilled in the art that various modifications and variations can be made to the structure of the disclosure without departing from the scope or spirit of the invention. In view of the foregoing, it is intended that the disclosure cover modifications and variations of this invention provided they fall within the scope of the following claims.