Abnormal region determination device and computer readable storage medium

Abstract

The abnormal region determination device includes: a first determination unit that determines whether or not an abnormal portion is included in a determination target region; a division unit that, when it is determined by the first determination unit that an abnormal portion is included in the region to be determined, divides the region to be determined, which is determined by the first determination unit that the abnormal portion is included, into a plurality of regions; a second determination unit that determines whether or not an abnormal portion is included in a plurality of regions divided by the division portion; and an abnormal region specifying unit that specifies the plurality of regions as abnormal regions when it is determined by the second determining unit that the abnormal portion is not included in the plurality of regions.

Description

Technical Field

[0001] This disclosure relates to an anomalous region determination apparatus and a computer-readable storage medium. Background Technology

[0002] Conventionally, machining surface data is used to evaluate whether there are abnormal parts on the machining surface (e.g., Patent Document 1). For example, it is determined whether there are abnormal parts in multiple regions generated by dividing the area shown by the machining surface data into predetermined sizes.

[0003] Existing technical documents

[0004] Patent Document 1: Japanese Patent Application Publication No. 2021-105825 Summary of the Invention

[0005] The problem that the invention aims to solve

[0006] However, existing technologies cannot detect which location within each region contains anomalies. Therefore, a technology is needed to accurately determine the locations of anomalies formed on machined surfaces.

[0007] Methods for solving problems

[0008] The abnormal region determination device disclosed herein includes: a first determination unit that determines whether an abnormal part is contained in a determination object area of ​​the processing surface data; a segmentation unit that, when the first determination unit determines that an abnormal part is contained in the determination object area, segments the determination object area into multiple regions; a second determination unit that determines whether an abnormal part is contained in the multiple regions segmented by the segmentation unit; and an abnormal region determination unit that, when the second determination unit determines that an abnormal part is not contained in the multiple regions, determines the multiple regions as abnormal regions.

[0009] The computer-readable storage medium of this disclosure stores commands that enable a computer to perform the following steps: determining whether an abnormal portion is contained in a determination object area of ​​the processed surface data; if the determination object area is determined to contain an abnormal portion, dividing the determination object area containing the abnormal portion into multiple regions; determining whether the multiple regions contain abnormal portions; and if the multiple regions are determined not to contain abnormal portions, identifying the multiple regions as abnormal regions. Attached Figure Description

[0010] Figure 1 This is a diagram representing an example of processing surface data.

[0011] Figure 2A This is an example of a machined surface as shown in the machined surface data.

[0012] Figure 2B It is a cross-sectional view of a portion of the machined surface.

[0013] Figure 3A It is a diagram used to illustrate the segmentation of the processing surface data.

[0014] Figure 3B It is a diagram used to illustrate the segmentation of the processing surface data.

[0015] Figure 3C It is a diagram used to illustrate the segmentation of the processing surface data.

[0016] Figure 4 This is a block diagram illustrating an example of the hardware structure of an abnormal region determination device.

[0017] Figure 5 This is a block diagram illustrating an example of the function of an abnormal area determination device.

[0018] Figure 6 This is a diagram illustrating an example of a region of a judgment object that is divided by a segment.

[0019] Figure 7 This is an example of machining surface data generated by the abnormal region determination department.

[0020] Figure 8 This is a flowchart illustrating an example of the processing performed by the abnormal region determination device.

[0021] Figure 9 This is a block diagram illustrating an example of an abnormal region determination device having functions similar to a judgment unit and an abnormality determination unit.

[0022] Figure 10A This is an example of machining surface data representing the speed at which the tool moves during machining.

[0023] Figure 10B This is an example of identifying the processing surface data of an abnormal area.

[0024] Figure 11A This is an example of machining surface data representing the amount of backlash correction during machining.

[0025] Figure 11B This is an example of identifying the processing surface data of an abnormal area.

[0026] Figure 12A It is a graph representing the processing surface data containing the first abnormal region.

[0027] Figure 12B It is a graph representing the processing surface data containing the second abnormal region.

[0028] Figure 12C It is a graph representing the processing surface data containing the third abnormal region.

[0029] Figure 13 This is a flowchart illustrating an example of the processing performed by the abnormal region determination device. Detailed Implementation

[0030] Hereinafter, the abnormal region determination apparatus and computer-readable storage medium according to embodiments of the present disclosure will be described with reference to the accompanying drawings. Furthermore, in the following description, structures having the same or similar functions will be labeled with the same reference numerals. Also, repeated descriptions of these structures will sometimes be omitted.

[0031] In this application, "based on XX" means "at least based on XX," but also includes cases where it is based on other elements besides XX. Furthermore, "based on XX" is not limited to the direct use of XX, but also includes cases where XX has been processed or manipulated. "XX" can be any element (e.g., any information).

[0032] <First Implementation>

[0033] An anomaly region determination device is a device for determining anomaly regions in machined surface data. Machined surface data is two-dimensional data representing information related to the machined surface. Information related to the machined surface includes, for example, the unevenness or concavity of the machined surface.

[0034] Figure 1 This is a diagram illustrating an example of machined surface data. Machined surface data is recorded by associating the numerical values ​​N1, N2, and N3, representing the height of the machined surface, with each region divided into a grid. Although the diagram is omitted, the numerical values ​​representing the height of the machined surface are similarly associated with other regions. Thus, the machined surface data can represent the unevenness or convexity of the machined surface.

[0035] Machining surface data can be generated, for example, through machining simulation. Machining simulation can be, for example, a simulation of cutting processes performed by a machining center.

[0036] Machining simulation is a process that uses virtual models of machining machines, machining programs, and machining conditions to generate machining surface data.

[0037] Virtual models include, for example, models of the structures that make up the machining machine and models of the workpiece. The model of the structure is generated based on information such as its shape, weight, strength, and material. The model of the workpiece is generated based on information such as its shape, weight, strength, and material.

[0038] Machining surface data, which represents information related to the machined surface, can be generated based on the measurement results of the machined surface actually machined using a machining program on a machining machine. When the machined surface is actually machined on a machining machine, it can be measured using a 3D scanner, laser confocal microscope, white interference microscope, etc.

[0039] Figure 2A This is an example of a machined surface as shown in the machined surface data. Figure 2B This is a cross-sectional view of a portion of the machined surface. The machined surface includes abnormal areas. Abnormal areas are, for example, areas with scratches or marks.

[0040] Scratches are formed, for example, due to problems with the instructions specifying the tool's movement path in the machining program generated by CAM (Computer Aided Manufacturing). Scratches are thin, elongated depressions. The depth of a scratch is, for example, about 1 μm.

[0041] Next, a summary of the method by which the abnormal region determination device determines abnormal regions will be described. The abnormal region determination device divides the machined surface data into multiple regions and determines whether each region contains an abnormal portion. Furthermore, the device further divides the regions containing abnormal portions into multiple regions to determine the location of the abnormal portions. By repeatedly performing this process, the device determines the location of abnormal portions within the machined surface.

[0042] However, if the area containing the abnormal portion is divided into too small regions, it may be impossible to detect whether each region contains the abnormal portion. That is, if the area containing the abnormal portion is divided too small when there are scratches on the machined surface, the height difference of the machined surfaces within the region becomes small, making it impossible to detect the abnormality.

[0043] For example, the width of the region containing the abnormal part is Figure 2B In the case of the width shown in box F1, the region also includes normal parts other than the abnormal parts. That is, the size of the region containing the abnormal parts is inappropriate, so the location of the abnormal parts cannot be determined with high precision.

[0044] Additionally, the width of the region containing the abnormal portion is Figure 2B With the width shown in box F2, only the anomalous portion is included in this area. That is, because the size of the area containing the anomalous portion is appropriate, the location of the anomalous portion can be determined with high accuracy.

[0045] Additionally, the width of the region containing the abnormal portion is Figure 2B In the case of the width shown in box F3, only a portion of the anomalous part is included in that area. That is, the size of the area containing the anomalous part is too small, so the anomalous part is not detected.

[0046] Figures 3A-3C This is a diagram used to illustrate the segmentation of the processing surface data. The anomaly region determination device determines which segmented regions contain the anomaly. However, the anomaly region determination device cannot determine the exact location of the anomaly within each region.

[0047] exist Figure 3A In the example shown, the segmented regions are relatively large. Therefore, the accuracy of determining the location of the anomaly is not very high.

[0048] exist Figure 3B In the example shown, the size of each segmented region is an appropriate size consistent with the size of the anomaly. Therefore, the accuracy of identifying the anomaly is high.

[0049] exist Figure 3C In the example shown, the sizes of the segmented regions are too small. Therefore, the abnormal region determination device cannot determine which region contains the abnormal part.

[0050] Therefore, when the abnormal region determination device cannot detect any abnormal part in multiple regions generated by segmenting a region containing an abnormal part, it can determine the multiple regions as abnormal regions.

[0051] Figure 4 This is a block diagram illustrating an example of the hardware structure of an anomaly region determination device. The anomaly region determination device 1 is, for example, installed in a numerical control device, a PC (Personal Computer), a server, a tablet terminal, etc. The anomaly region determination device 1 includes, for example, a hardware processor 101, a bus 102, a ROM (Read Only Memory) 103, a RAM (Random Access Memory) 104, non-volatile memory 105, and an input / output device 106.

[0052] The hardware processor 101 is a processor that uses a system program to control the entire abnormal area determination device 1. The hardware processor 101 reads the system program and the like stored in the ROM 103 via the bus 102. The hardware processor 101 is, for example, a CPU (Central Processing Unit) or an electronic circuit.

[0053] Bus 102 is a communication path that connects the various hardware components of the anomaly region determination device 1 to each other. The various hardware components of the anomaly region determination device 1 exchange data via bus 102.

[0054] ROM103 is a storage device for storing system programs, etc. ROM103 is a computer-readable storage medium.

[0055] RAM 104 is a storage device for temporary storage of various data. RAM 104 functions as the working area of ​​the hardware processor 101 for processing various data.

[0056] Non-volatile memory 105 is a storage device that retains data even when the power supply to the abnormal region determination device 1 is cut off. Non-volatile memory 105 stores, for example, processing surface data. Non-volatile memory 105 is a computer-readable storage medium. Non-volatile memory 105 may be, for example, a battery-backed memory or an SSD (Solid State Drive).

[0057] Input / output device 106 receives various data from hardware processor 101, for example, and displays various data on the display. Additionally, input / output device 106 accepts various data inputs and sends various data, for example, to hardware processor 101.

[0058] The input / output device 106 is, for example, a touch panel. When the input / output device 106 is a touch panel, it is, for example, a capacitive touch panel. The touch panel is not limited to capacitive touch panels; it can also be other types of touch panels.

[0059] Figure 5 This is a block diagram illustrating an example of the function of the abnormal region determination device 1. The abnormal region determination device 1 includes a processing surface data acquisition unit 111, a first judgment unit 112, a segmentation unit 113, a second judgment unit 114, a region setting unit 115, an abnormal region determination unit 116, and an output unit 117.

[0060] The processing surface data acquisition unit 111, the first judgment unit 112, the segmentation unit 113, the second judgment unit 114, the area setting unit 115, the abnormal area determination unit 116, and the output unit 117 are implemented, for example, by the hardware processor 101 using the system program stored in the ROM 103 and various programs and data stored in the non-volatile memory 105 for calculation and processing.

[0061] The machining surface data acquisition unit 111 acquires machining surface data. For example, the machining surface data acquisition unit 111 acquires machining surface data from an external simulation device. The machining surface data acquisition unit 111 may also acquire machining surface data from a server, PC, numerical control device, etc., connected to the abnormal area determination device 1. For example, the machining surface data acquisition unit 111 acquires... Figure 2A The data for the machined surfaces shown.

[0062] The first determination unit 112 determines whether the determination object area of ​​the machining surface data contains an abnormal portion. The determination object area is the area that the first determination unit 112 determines to be the object of determining whether there is an abnormal portion. The determination object area is, for example, the entire area of ​​the machining surface shown by the machining surface data obtained by the machining surface data acquisition unit 111. The determination object area may also be a part of the machining surface shown by the machining surface data.

[0063] An abnormal portion is, for example, a portion where at least one of the arithmetic mean of the values ​​represented by the machining surface data and the value obtained by subtracting the minimum value from the maximum value represented by the machining surface data exceeds a predetermined threshold. The arithmetic mean of the values ​​represented by the machining surface data and the value obtained by subtracting the minimum value from the maximum value represented by the machining surface data are, for example, surface roughness Sa and maximum height Sz. The first judgment unit 112 determines whether an abnormal portion is contained in the judgment object area by evaluating whether at least one of the surface roughness Sa and maximum height Sz in the judgment object area exceeds a predetermined threshold.

[0064] If the first determination unit 112 determines that the judgment object region contains an abnormal part, the segmentation unit 113 segments the judgment object region that the first determination unit 112 determines contains an abnormal part into multiple regions. That is, each region is a region formed by segmenting the judgment object region.

[0065] Figure 6 This diagram illustrates an example of a judgment object region divided by the segmentation unit 113. For example, the segmentation unit 113 divides the judgment object region A1 into four regions a11 to a14.

[0066] The second determination unit 114 determines whether any of the multiple regions a11-a14 generated by the segmentation unit 113 contain abnormal parts. The second determination unit 114 determines whether at least one of the multiple regions contains an abnormal part by evaluating the surface characteristics of the multiple regions a11-a14. As described above, the surface characteristics are, for example, surface roughness Sa or maximum height Sz. That is, the second determination unit 114 determines whether each region a11-a14 contains an abnormal part by determining whether the surface roughness Sa or maximum height Sz of each region a11-a14 is above a predetermined threshold.

[0067] If the second determination unit 114 determines that any one of the multiple regions a11 to a14 contains an abnormal part, the region setting unit 115 sets the region determined to contain the abnormal part as the determination target region. Figure 6 In the example shown, the second determination unit 114 determines, for example, that an abnormal portion is contained in region a14. Alternatively, the second determination unit 114 determines that no abnormal portion is contained in regions a11 to a13. In this case, the region setting unit 115 sets region a14 as the determination target region A2.

[0068] The segmentation unit 113 divides the region that is set as the judgment target region A2 by the region setting unit 115 into multiple regions a21 to a24.

[0069] The second determination unit 114 determines whether any of the multiple regions a21 to a24 segmented by the segmentation unit 113 contain abnormal portions. For example, the second determination unit 114 determines that regions a21 and a24 contain abnormal portions. Alternatively, the second determination unit 114 determines that regions a22 and a23 do not contain abnormal portions. In this case, the region setting unit 115 sets region a21 as the determination target region A3. Furthermore, although not illustrated, the region setting unit 115 sets region a24 as another determination target region.

[0070] The segmentation unit 113 divides the region A3, which is set as the judgment target region by the region setting unit 115, into multiple regions. The segmentation unit 113 divides the judgment target region A3 into multiple regions a31 to a34. Similarly, the segmentation unit 113 also divides other judgment target regions into multiple regions.

[0071] The second determination unit 114 determines whether any of the multiple regions a31 to a34 segmented by the segmentation unit 113 contain abnormal portions. For example, the second determination unit 114 determines that regions a31 and a33 contain abnormal portions. Alternatively, the second determination unit 114 determines that regions a32 and a34 do not contain abnormal portions. In this case, the region setting unit 115 sets region a31 as the determination target region A4. Furthermore, although not illustrated, the region setting unit 115 sets region a33 as another determination target region.

[0072] The segmentation unit 113 divides the region A4, which is set as the judgment target region by the region setting unit 115, into multiple regions. The segmentation unit 113 divides the judgment target region A4 into multiple regions a41 to a44. Similarly, the segmentation unit 113 divides other judgment target regions into multiple regions.

[0073] The second determination unit 114 determines whether any of the multiple regions a41 to a44 segmented by the segmentation unit 113 contain an abnormal portion. For example, the second determination unit 114 determines that no abnormal portion is contained in the multiple regions a41 to a44. That is, by meticulously segmenting the determination object region by the segmentation unit 113, abnormalities in the determination object region are no longer detected.

[0074] If the second determination unit 114 determines that no abnormal portion is contained in the multiple regions a41 to a44, the abnormal region determination unit 116 determines the multiple regions a41 to a44 as abnormal regions. The abnormal region determination unit 116, for example, encloses the determined abnormal region with a rectangular frame. In other words, the abnormal region determination unit 116 generates machining surface data that encloses the abnormal region with a rectangular frame.

[0075] Figure 7This is an example of machining surface data generated by the abnormal region determination unit 116. The abnormal regions in the machining surface data are enclosed by rectangular boxes.

[0076] The output unit 117 outputs the machining surface data generated by the abnormal area determination unit 116. The output unit 117 outputs the machining surface data, for example, to the input / output device 106. The input / output device 106 displays the machining surface data on a display. Thus, the user can quantitatively evaluate the machining surface based on the machining surface data.

[0077] Figure 8 This is a flowchart illustrating an example of the processing performed by the abnormal region determination device 1. In the abnormal region determination device 1, firstly, the machining surface data acquisition unit 111 acquires machining surface data (step S1).

[0078] Next, the first determination unit 112 determines whether the determination target area contains an abnormal part (step S2). If the first determination unit 112 determines that the determination target area does not contain an abnormal part (step S2: no), the output unit 117 outputs the processing surface data (step S7), and the process ends.

[0079] If the first determination unit 112 determines that the judgment object area contains an abnormal part (step S2: yes), the segmentation unit 113 divides the judgment object area into multiple areas (step S3).

[0080] Next, the second determination unit 114 determines whether an abnormal part is contained in the multiple regions (step S4).

[0081] If an abnormal portion is found in one or more of the multiple regions (step S4: Yes), the region setting unit 115 sets the region containing the abnormal portion as the judgment target region (step S5). Then, the processing after step S3 is executed.

[0082] On the other hand, if it is determined that multiple regions do not contain abnormal parts (step S4: No), the abnormal region determination unit 116 determines these multiple regions as abnormal regions (step S6). That is, the abnormal region determination unit 116 generates machining surface data that has determined the abnormal regions. After that, the output unit 117 outputs the machining surface data (step S7), and the process ends.

[0083] <Second Implementation>

[0084] In the first embodiment described above, an example was given where the machining surface data represents the unevenness or concavity of the machining surface. However, the machining surface data can also be data representing information related to the machining surface other than unevenness or concavity.

[0085] The machining surface data may be, for example, data representing at least one of the following: the tool's moving speed during machining, a value calculated based on the moving speed, a correction amount during machining, a value calculated based on the correction amount, a detection value of a detection signal during machining, a value calculated based on the detection value, a command value of a command signal, and a value calculated based on the command value.

[0086] Correction parameters include, for example, backlash correction, pitch error correction, spatial error correction, and thermal displacement correction. Command signals include, for example, valid command signals and command signals to operate external devices. External devices include, for example, coolants, fans, and chip handling devices. Detection signals include feedback signals for valid command signals, feedback signals from external devices, and resource utilization signals.

[0087] The values ​​calculated based on the moving speed, correction amount, detection value, and command value can be the differential or integral value of the moving speed, the differential or integral value of the correction amount, the differential or integral value of the detection value, and the differential or integral value of the command value.

[0088] When the machining surface data represents information related to the machining surface other than its unevenness, such as... Figure 1 As shown, the numerical values ​​are also recorded in association with each region divided into a grid. Therefore, even when the machining surface data represents information other than the unevenness of the machining surface, the abnormal region determination device 1 can also determine the abnormal region by judging the abnormal parts shown in the machining surface data.

[0089] The abnormal region determination device 1 can also determine the abnormal region based on the machining surface data representing any one of the aforementioned machining surface-related information, other than the concavity and convexity. For example, when the machining surface data represents backlash correction amount, the abnormal region determination device 1 determines the abnormal region representing the abnormal portion of the backlash correction amount.

[0090] The abnormal area determination device 1 may further include: a similarity determination unit that determines the similarity between an abnormal area determined by the abnormal area determination unit 116 when the processing surface data is data representing first information and an abnormal area determined by the abnormal area determination unit 116 when the processing surface data is data representing second information; and an abnormality determination unit that determines the cause of the abnormality of the abnormal part based on the determination result of the similarity determination unit.

[0091] Figure 9 This is a block diagram illustrating an example of the function of an anomaly region determination device 1, which has a similar judgment unit and an anomaly determination unit. Figure 9 The abnormal region determination device 1 shown has functions other than the judgment unit 118 and the abnormal determination unit 119. Figure 5The abnormal area determination device 1 shown has the same function. Therefore, here, the similar judgment unit 118 and the abnormal determination unit 119 will be described, and the description of other functions will be omitted.

[0092] In addition to the processing surface data acquisition unit 111, the first judgment unit 112, the segmentation unit 113, the second judgment unit 114, the region setting unit 115, the abnormal region determination unit 116, and the output unit 117, the abnormal region determination device 1 also has a similar judgment unit 118 and an abnormal determination unit 119.

[0093] Similar to the judgment unit 118 and the exception determination unit 119, for example, they are implemented by the hardware processor 101 using the system program stored in the ROM 103 and various programs and data stored in the non-volatile memory 105 for calculation and processing.

[0094] The machining surface data acquisition unit 111 acquires machining surface data. The machining surface data is data representing first information. This first information may be, for example, information representing the height of the machining surface. In this case, as described in the first embodiment, the abnormal region determination unit 116 determines an abnormal region containing abnormal portions related to the unevenness of the machining surface.

[0095] The machining surface data acquisition unit 111 acquires machining surface data that represents information related to the machining surface, excluding unevenness. The machining surface data is data representing second information. This second information may be, for example, information representing the tool's movement speed during machining.

[0096] Figure 10A This is an example of machining surface data representing the tool's movement speed during machining. When machining surface data is displayed on the screen, for example, darker colors are used to show areas where the tool moves slowly, while lighter colors are used to show areas where the tool moves quickly. Furthermore, in... Figure 10A And the following Figure 10B In the image, for convenience, darker colored areas are displayed using shaded rectangular blocks.

[0097] The first judgment unit 112, the segmentation unit 113, the second judgment unit 114, and the abnormal region determination unit 116, for example, execute... Figure 8 The processing steps S2 to S6 are shown. This identifies an abnormal region containing abnormal portions related to the tool's movement speed during machining.

[0098] Figure 10B This is an example of processing surface data where an abnormal region has been identified. The region identified as abnormal is, for example, enclosed by a rectangular frame.

[0099] The machining surface data acquisition unit 111 acquires another machining surface data that represents information related to the machining surface, other than the unevenness. The machining surface data is data that represents third information. The third information is, for example, information representing the backlash correction amount during machining.

[0100] Figure 11A This is an example of machining surface data representing the amount of backlash correction during machining. When the machining surface data is displayed on the screen, areas with a large amount of backlash correction are shown in a darker color, while areas with a small amount of backlash correction are shown in a lighter color. Furthermore, in... Figure 11A And the following Figure 11B In the image, for convenience, darker colored areas are displayed using shaded rectangular blocks.

[0101] The first judgment unit 112, the segmentation unit 113, the second judgment unit 114, and the abnormal region determination unit 116, for example, execute... Figure 8 The processing steps S2 to S6 are shown. This identifies an abnormal region containing abnormal portions related to the backlash correction amount during machining.

[0102] Figure 11B This is an example of processing surface data where an abnormal region has been identified. The region identified as abnormal is, for example, enclosed by a rectangle.

[0103] The similarity determination unit 118 determines the similarity between an anomaly region determined by the anomaly region determination unit 116 when the processed surface data represents first information and an anomaly region determined by the anomaly region determination unit 116 when the processed surface data represents second information. Furthermore, the similarity determination unit 118 determines the similarity between an anomaly region determined by the anomaly region determination unit 116 when the processed surface data represents second information and an anomaly region determined by the anomaly region determination unit 116 when the processed surface data represents third information and an anomaly region determined by the anomaly region determination unit 116 when the processed surface data represents first information. Moreover, the types of processed surface data that are the objects of similarity determination are not limited to three, but can also be two or four or more.

[0104] Figure 12A It is a graph representing the processing surface data containing the first abnormal region. Figure 12B It is a graph representing the processing surface data containing the second abnormal region. Figure 12C This is a graph representing the processing surface data containing the third anomaly region. Figures 12A-12C In the image, the abnormal areas are the parts that have been shaded.

[0105] The similarity determination unit 118 compares the processing surface data containing the first abnormal region, the processing surface data containing the second abnormal region, and the processing surface data containing the third abnormal region to determine the similarity.

[0106] The similarity determination unit 118 uses, for example, CBIR (Content Based Information Retrieval) to determine similarity. The similarity determination unit 118 determines, for example, the similarity of the distribution of anomalous regions contained in each processing surface data. In other words, the similarity determination unit 118 determines similarity by comparing the positions of anomalous regions contained in the processing surface data.

[0107] Similarly, the judgment unit 118 can also judge the similarity by comparing the feature quantities represented by the processing surface data of each abnormal region with each other using CBIR.

[0108] The regions compared by the similar judgment unit 118 are regions located in corresponding positions. For example, Figure 12A and Figure 12C The areas surrounded by thick lines in the abnormal regions shown are the first and third abnormal regions, which are located in corresponding positions.

[0109] Features can be, for example, histograms, average hashes, or SIFT (Scale-Invariant Feature Transform). The similarity determination unit 118 uses an evaluation method corresponding to the type of feature to determine similarity. The evaluation method can be, for example, Hamming distance or cosine similarity.

[0110] The anomaly determination unit 119 determines the cause of the anomaly in the abnormal portion based on the determination result of the similar determination unit 118. For example, if the location of the first abnormal region included in the machining surface data is similar to the location of the third abnormal region, the anomaly of unevenness in the first abnormal region is highly likely to be caused by an abnormality in the backlash correction amount. In this case, the anomaly determination unit 119 determines that the cause of the abnormal portion is the backlash correction amount. That is, the anomaly determination unit 119 determines the cause of the anomaly.

[0111] Furthermore, if the features shown in the first abnormal region are similar to those shown in the third abnormal region, the anomaly in the first abnormal region is highly likely due to an anomaly in the backlash correction amount. In this case, the anomaly determination unit 119 determines that the anomaly is due to the backlash correction amount.

[0112] The output unit 117 outputs data indicating the cause of the abnormality determined by the abnormality determination unit 119. For example, the output unit 117 outputs the data indicating the cause of the abnormality to the display of the input / output device 106. Thus, the operator can confirm the cause of the abnormality on the machined surface.

[0113] Figure 13 This is a flowchart illustrating an example of the processing performed by the anomaly region determination device 1. The anomaly region determination device 1 first performs a process to determine an anomaly region (step SA1). The processing of step SA1 is similar to... Figure 8 The processes in steps S1 to S6 of the flowchart shown are the same. The abnormal area determination device 1, for example, acquires machining surface data representing first information, machining surface data representing second information, and machining surface data representing third information, and determines the abnormal areas in each machining surface data.

[0114] Next, the similarity judgment unit 118 judges the similarity of each abnormal area (step SA2). Next, the abnormality determination unit 119 determines the cause of the abnormality (step SA3). Finally, the output unit 117 outputs the processed surface data and the data indicating the cause of the abnormality (step SA4), and the process ends.

[0115] As described above, the abnormal region determination device 1 includes: a first determination unit 112 that determines whether an abnormal portion is contained in the judgment object area of ​​the processed surface data; a segmentation unit 113 that, when the first determination unit 112 determines that the judgment object area contains an abnormal portion, divides the judgment object area into multiple regions; a second determination unit 114 that determines whether the multiple regions segmented by the segmentation unit 113 contain an abnormal portion; and an abnormal region determination unit 116 that, when the second determination unit 114 determines that the multiple regions do not contain an abnormal portion, determines the multiple regions as abnormal regions. Therefore, the abnormal region determination device 1 can determine the position of abnormal portions formed on the processed surface with high accuracy.

[0116] Furthermore, the abnormal region determination device 1 also includes a region setting unit 115, which, when the second determination unit 114 determines that an abnormal part is contained in any one of the multiple regions, sets the region determined to contain the abnormal part as the judgment target region, and the segmentation unit 113 divides the region set as the judgment target region by the region setting unit 115 into multiple regions. That is, the abnormal region determination device 1 sometimes repeatedly performs the segmentation of the judgment target region and the determination of whether the segmented regions contain an abnormal part. Therefore, the abnormal region determination device 1 can determine the location of the abnormal part with high accuracy.

[0117] Furthermore, the abnormal portion is the portion where at least one of the arithmetic mean of the values ​​represented by the machining surface data and the value obtained by subtracting the minimum value from the maximum value is above a predetermined threshold. Therefore, the abnormal region determination device 1 can, for example, accurately determine the positions of portions with coarse surface roughness Sa and high maximum height Sz on the machining surface. Alternatively, the abnormal region determination device 1 can accurately determine the positions on the machining surface where the tool movement speed varies greatly, etc.

[0118] Furthermore, the abnormal region determination device 1 also includes: a similarity judgment unit 118, which determines the similarity between an abnormal region determined by the abnormal region determination unit 116 when the machining surface data represents first information and an abnormal region determined by the abnormal region determination unit 116 when the machining surface data represents second information; and an abnormality determination unit 119, which determines the cause of the abnormality based on the judgment result of the similarity judgment unit 118. Therefore, the abnormal region determination device 1 is capable of determining the cause of the abnormality.

[0119] This disclosure has been described in detail, but it is not limited to the various embodiments described above. Various additions, substitutions, modifications, and partial deletions can be made to these embodiments without departing from the spirit of this disclosure, or from the spirit of this disclosure derived from the content described in the claimed scope and its equivalents. Furthermore, these embodiments can also be implemented in combination.

[0120] The following are notes regarding embodiments of this disclosure.

[0121] Postscript [1]

[0122] An abnormal region determination apparatus includes: a first determination unit that determines whether an abnormal portion is contained in a determination object region of processed surface data; a segmentation unit that, when the first determination unit determines that the determination object region contains the abnormal portion, segments the determination object region into multiple regions; a second determination unit that determines whether the abnormal portion is contained in the multiple regions generated by the segmentation unit; and an abnormal region determination unit that, when the second determination unit determines that the multiple regions do not contain the abnormal portion, determines the multiple regions as abnormal regions.

[0123] Postscript [2]

[0124] According to the abnormal region determination device described in Appendix [1], the abnormal region determination device further includes: a region setting unit, which sets the region that is determined to contain the abnormal part as the judgment object region when the second judgment unit determines that any region among the plurality of regions contains the abnormal part, and the segmentation unit divides the region that is set as the judgment object region by the region setting unit into a plurality of regions.

[0125] Postscript [3]

[0126] According to the abnormal region determination device described in Appendix [2], the abnormal portion is the portion of at least one of the arithmetic mean of the values ​​represented by the processing surface data and the value obtained by subtracting the minimum value from the maximum value of the values ​​being above a predetermined threshold.

[0127] Postscript [4]

[0128] According to the appendix [1], the abnormal region determination device further comprises: a similarity determination unit that determines the similarity between the abnormal region determined by the abnormal region determination unit when the processing surface data is data representing first information and the abnormal region determined by the abnormal region determination unit when the processing surface data is data representing second information; and an abnormality determination unit that determines the abnormality cause of the abnormal part based on the determination result of the similarity determination unit.

[0129] Postscript [5]

[0130] A computer-readable storage medium storing commands that enable a computer to perform the following steps: determining whether an abnormal portion is contained in a determination object area of ​​processed surface data; if the determination object area contains the abnormal portion, dividing the determination object area containing the abnormal portion into multiple regions; determining whether the abnormal portion is contained in the multiple regions; and if the determination object does not contain the abnormal portion, identifying the multiple regions as abnormal regions.

[0131] Explanation of reference numerals in the attached figures

[0132] 1. Abnormal Area Determination Device

[0133] 101 Hardware Processor

[0134] 102 bus

[0135] 103ROM

[0136] 104 RAM

[0137] 105 non-volatile memory

[0138] 106 Input / Output Devices

[0139] 111 Machining Surface Data Acquisition Department

[0140] 112 First Judgment Department

[0141] 113 divisions

[0142] 114 Second Judgment Department

[0143] 115 Area Setting Department

[0144] 116 Anomaly Area Determination Department

[0145] 117 Output Section

[0146] 118 Similar Judgment Department

[0147] 119 Anomaly Determination Department.

Claims

1. An anomalous region determination device, characterized in that, The abnormal region determination device includes: The first judgment unit determines whether the judgment object area of ​​the processing surface data contains an abnormal part; The segmentation unit, when the first determination unit determines that the judgment object region contains the abnormal part, divides the judgment object region that the first determination unit determines contains the abnormal part into multiple regions; The second determination unit determines whether the abnormal portion is contained in the plurality of regions generated by the segmentation; as well as An abnormal region determination unit determines the plurality of regions as abnormal regions when the second determination unit determines that the abnormal portion is not included in the plurality of regions.

2. The abnormal region determination device according to claim 1, characterized in that, The abnormal region determination device further includes a region setting unit, which, when determined by the second determination unit to contain the abnormal portion in any one of the plurality of regions, sets the region determined to contain the abnormal portion as the determination target region. The segmentation unit divides any one of the regions that the region setting unit has set as the region to be judged into multiple regions.

3. The abnormal region determination device according to claim 2, characterized in that, The abnormal portion is the portion of the numerical values ​​represented by the processed surface data that is above a predetermined threshold, which is the arithmetic mean of the values ​​and the value obtained by subtracting the minimum value from the maximum value of the values.

4. The abnormal region determination device according to claim 1, characterized in that, The abnormal region determination device also includes: A similar determination unit determines the similarity between the abnormal region determined by the abnormal region determination unit when the processing surface data is data representing first information and the abnormal region determined by the abnormal region determination unit when the processing surface data is data representing second information; as well as The anomaly determination unit determines the cause of the anomaly based on the judgment result of the similar judgment unit.

5. A computer-readable storage medium, characterized in that, Store commands that cause the computer to perform the following steps: Determine whether the judgment object area of ​​the processing surface data contains abnormal parts; If it is determined that the judgment object region contains the abnormal part, the judgment object region that is determined to contain the abnormal part is divided into multiple regions; Determine whether the abnormal portion is contained in the segmented multiple regions; as well as If it is determined that the multiple regions do not contain the abnormal part, the multiple regions are identified as abnormal regions.

Images