Anomaly area identification device and computer-readable storage medium

Abstract

This anomaly area identification device comprises a first determination unit that determines whether an abnormal section is contained in a target area; a subdivision unit that, if the first determination unit determines that an abnormal section is contained in the target area, subdivides the target area, which the first determination unit has determined to contain an abnormal section, into several areas; a second determination unit that determines whether the abnormal section is contained in the several areas subdivided by the subdivision unit; and an anomaly area identification unit that identifies the several areas as anomaly areas if the second determination unit has determined that the abnormal section is not contained in the several areas.

Description

TECHNICAL AREA

[0001] The present disclosure relates to an anomaly area identification device and a computer-readable storage medium. GENERAL STATE OF THE ART

[0002] Traditionally, data relating to a machined surface are used to assess whether or not an abnormal section is present on that surface (see, for example, patent document 1). For instance, it is determined whether or not an abnormal section is contained within multiple areas created by subdividing a region specified by data relating to a machined surface to a predetermined size. LITERATURE LIST PATENT DOCUMENTS

[0003] Patent document 1: JP 2021 - 105 825 A REVELATION OF THE INVENTION PROBLEM THAT THE INVENTION IS SUPPOSED TO SOLVE

[0004] However, conventional technology cannot detect the precise location of an abnormal section within a given area. Therefore, there is a need for a technology that can accurately identify an abnormal section formed on a machined surface. MEANS TO SOLVENT THE PROBLEM

[0005] An anomaly area identification device of the disclosure comprises a first determination unit configured to determine whether an abnormal section is contained in a target area of ​​data relating to a processed surface; a subdivision unit configured to subdivide the target area, which the first determination unit has determined to contain an abnormal section, into multiple areas; a second determination unit configured to determine whether the multiple areas generated by the subdivision unit contain the abnormal section; and an anomaly area identification unit configured to identify the multiple areas as anomaly areas.if the second unit of determination has determined that the multiple areas do not contain the abnormal section, then...

[0006] A computer-readable storage medium of the disclosure stores instructions that cause a computer to determine whether an abnormal section is contained in a target area of ​​data relating to a processed surface, in the case of a determination that an abnormal section is contained in the target area, to subdivide the target area, for which the first determination unit has determined that it contains an abnormal section, into several areas, to determine whether the several subdivided areas contain the abnormal section or not, and to identify the several areas as anomaly areas if it has been determined that the several areas do not contain the abnormal section. BRIEF DESCRIPTION OF THE DRAWINGS Fig. 1 is a diagram showing an example of data relating to a processed area; Fig. 2A is an example of a processed area, specified by the data regarding the processed area; Fig. 2B is a sectional view of a section of the work area; Fig. 3A is a diagram to describe the subdivision of the data with respect to the processed area; Fig. 3B is a diagram to describe the subdivision of the data with respect to the processed area; Fig. 3C is a diagram for describing the subdivision of the data with respect to the processed area; Fig. Figure 4 is a block diagram showing an example of a hardware setup for the anomaly area identification device; Fig. Figure 5 is a block diagram showing an example of the functions of the anomaly area identification device; Fig. Figure 6 is a diagram showing an example of a target area subdivided by a subdivision unit; Fig. Figure 7 is an example of data relating to the processed area generated by an anomaly area identification unit. Fig. Figure 8 is a flowchart showing an example of the processing performed by the anomaly area identification device; Fig. Figure 9 is a block diagram showing an example of the functions of an anomaly area identification device with a similarity determination unit and an anomaly identification unit; Fig. 10A is an example of data relating to the machined area, indicating a tool's movement speed during machining; Fig. 10B is an example of data regarding the processed area in which an anomaly area was identified; Fig. 11A is an example of data relating to the machined area, which specifies a setback correction amount during machining; Fig. 11B is an example of data regarding the processed area in which an anomaly area was identified; Fig. 12A is a diagram showing data relating to the processed area containing a first anomaly region; Fig. 12B is a diagram showing data regarding the processed area, which contains a second anomaly area; Fig. 12C is a diagram showing data regarding the processed area containing a third anomaly region; and Fig. Figure 13 is a flowchart showing an example of the processing performed by the anomaly area identification device. METHOD OF IMPLEMENTATION OF THE INVENTION

[0007] With reference to the drawings, an anomaly zone identification device and a computer-readable storage medium according to embodiments of the disclosure are described below. It should be noted that in the following description, components with identical or similar functions are designated by the same reference numerals. Furthermore, in some cases, duplicate descriptions of these components will be omitted.

[0008] In this application, "based on XX" means "based on at least XX" and includes the case where, in addition to XX, another element is used. Furthermore, "based on XX" is not limited to the case where XX is used directly, but also includes the case where another element is used that is obtained by performing a calculation or processing on XX. "XX" is any element (for example, any piece of information). First embodiment

[0009] An anomaly area identification device is a device for identifying an anomaly area in data relating to a processed area. The data relating to the processed area is two-dimensional data that provides information related to the processed area. This information might include, for example, an irregularity within the processed area.

[0010] Fig. Figure 1 is a block diagram showing an example of data relating to the processed area. This data consists of numerical values ​​N1, N2, and N3, representing the elevations of the processed area, linked to corresponding grid-like sections. Although not explicitly shown, numerical values ​​representing elevations of the processed area are also linked to the other sections. This allows the data to indicate irregularities within the processed area.

[0011] The data regarding the machined area is data generated, for example, by a machining simulation. A machining simulation is, for example, a simulation of a cutting process using a machining device.

[0012] Machining simulation is a process for generating data regarding the machined surface using a virtual model, a machining program, a machining condition, etc. of the machining device.

[0013] The virtual model contains, for example, a model of a setup within the machining device and a model of a workpiece. The setup model is generated based on information such as the setup's shape, weight, thickness, material, etc. The workpiece model is also generated based on information such as the workpiece's shape, weight, thickness, material, etc.

[0014] The data relating to the machined area, which provides information related to the machined area, can be generated based on a measurement result of the machined area, which was actually machined by the machining device using a machining program. If the machined area was indeed machined by the machining device, it can be measured using a 3D scanner, a confocal laser microscope, a white light interference microscope, and so on.

[0015] Fig. 2A is an example of the processed area, which is specified by the data regarding the processed area. Fig. 2B is a sectional view of a section of the machined surface. The machined surface contains an abnormal section. For example, the abnormal section is a section where a stripe has formed.

[0016] The stripe is formed, for example, by a problem with a command that defines a tool movement path in a machining program generated by CAM (computer-aided manufacturing). The stripe is an elongated depression. The depth of the stripe is, for example, 1 µm.

[0017] Next, a description of the procedure by which the anomaly area identification device identifies an anomaly area will be given. The anomaly area identification device divides the data relating to the processed area into several areas and determines whether each area contains an abnormal section. Furthermore, the anomaly area identification device further divides an area containing an abnormal section into several sub-areas and identifies the location of the abnormal section. The anomaly area identification device performs this processing repeatedly to determine the location of an abnormal section on the processed area.

[0018] However, if an area containing an abnormal section is subdivided into excessively small areas, in some cases it will not be detected whether or not each of these areas contains an abnormal section. In other words, if a strip is formed on the processed surface, a height difference in one area will be small, and an anomaly will not be detected, if the area containing the abnormal section is subdivided to an excessively small size.

[0019] For example, if the width of the area containing the abnormal section is a width defined by a frame F1 in Fig. As indicated in 2B, the area contains a normal section next to the abnormal section. In other words, the size of the area containing the abnormal section is unsuitable, and therefore the position of the abnormal section cannot be accurately identified.

[0020] However, if the width of the area containing the abnormal section is a width defined by a frame F2 in Fig. As indicated in 2B, the area contains only the abnormal section. In other words, the size of the area containing the abnormal section is appropriate, and therefore the position of the abnormal section can be accurately identified.

[0021] And if the width of the area containing the abnormal section is a width defined by a frame F3 in Fig. As indicated in 2B, only a portion of the abnormal section is contained within that area. In other words, the size of the area containing the abnormal section is excessively small, and therefore the abnormal section is not detected.

[0022] Fig. Figures 3A to 3C are diagrams describing the subdivision of the data with respect to the processed area. The anomaly area identification device identifies in which subdivided area the abnormal section is contained. However, the anomaly area identification device cannot identify the position within that area where the abnormal section is located.

[0023] In the example that is in Fig. As shown in Figure 3A, the size of the individual compartments is relatively large. For this reason, the accuracy of identifying the abnormal section is not very high.

[0024] In the example that is in Fig. As shown in Figure 3B, the size of each sectioned area is a suitable size that corresponds to the size of the abnormal section. Therefore, the accuracy of identifying the abnormal section is high.

[0025] In the example that is in Fig. As shown in Figure 3C, the size of the individual compartmentalized areas is excessively small. For this reason, the anomaly area identification device cannot identify the location of the abnormal section.

[0026] Therefore, if the abnormal section is no longer detected in several areas created by subdividing the area containing the abnormal section, the anomaly area identification device can identify these several areas as anomaly areas.

[0027] Fig. Figure 4 is a block diagram showing an example of a hardware configuration for the anomaly region identification device. The anomaly region identification device 1 is, for example, implemented in a numerical controller, a PC (personal computer), a server, or a tablet terminal. The anomaly region identification device 1 includes, for example, a hardware processor 101, a bus 102, a ROM (read-only memory) 103, a RAM (random access memory) 104, a non-volatile memory 105, and an input / output device 106.

[0028] Hardware processor 101 is a processor that controls the entire anomaly area identification device 1 using a system program. Hardware processor 101 reads the system program, which is stored in ROM 103, via bus 102. Hardware processor 101 is, for example, a CPU (central processing unit) or an electronic circuit.

[0029] Bus 102 is a communication path that connects the individual hardware elements in the anomaly area identification device 1. The individual hardware elements in the anomaly area identification device 1 exchange data via bus 102.

[0030] The ROM 103 is a storage device that stores the system program, etc. The ROM 103 is a computer-readable storage medium.

[0031] The RAM 104 is a memory device for temporarily storing various types of data. The RAM 104 acts as a workspace for the hardware processor 101 to process different data.

[0032] The non-volatile memory 105 is a storage device that retains data even when the anomaly area identification device 1 is switched off. The non-volatile memory 105 stores, for example, data relating to the machined area. The non-volatile memory 105 is a computer-readable storage medium. The non-volatile memory 105 is implemented, for example, as battery-backed storage or as a solid-state drive (SSD).

[0033] The input / output device 106 receives various data from the hardware processor 101, for example, and displays this data. The input / output device 106 also receives input of various data and then sends this data, for example, to the hardware processor 101.

[0034] The input / output device 106 is, for example, a touch panel. If the input / output device 106 is a touch panel, then the input / output device 106 is, for example, a capacitive touch panel. The touch panel is not limited to a capacitive touch panel, but can be another type of touch panel.

[0035] Fig. Figure 5 is a block diagram showing an example of the functions of the anomaly area identification device 1. The anomaly area identification device 1 has a unit 111 for obtaining data regarding the processed area, a first determination unit 112, a subdivision unit 113, a second determination unit 114, an area definition unit 115, an anomaly area identification unit 116, and an output unit 117.

[0036] The unit 111 for obtaining data regarding the processed area, the first determination unit 112, the subdivision unit 113, the second determination unit 114, the area determination unit 115, the anomaly area identification unit 116 and the output unit 117 are implemented, for example, by the hardware processor 101 performing arithmetic operations using the system program stored in the ROM 103 and various programs and data stored in the non-volatile memory 105.

[0037] Unit 111 for obtaining data regarding the processed area obtains the data regarding the processed area. Unit 111 for obtaining data regarding the processed area obtains the data regarding the processed area, for example, from an external simulation device. Unit 111 for obtaining data regarding the processed area can obtain the data regarding the processed area from a server, a PC, a numerical control, etc., which is connected to the anomaly area identification device 1. Unit 111 for obtaining data regarding the processed area obtains, for example, the data in Fig. 2A shows the data regarding the processed area.

[0038] The first unit of determination 112 determines whether or not an abnormal section is contained within a target area of ​​the data relating to the processed area. The target area is a region that serves as the objective for the first unit of determination 112 to determine whether or not an abnormal section is present. For example, the target area is the entire area of ​​the processed area specified by the data relating to the processed area obtained by unit 111. Alternatively, the target area may be a sub-area of ​​the processed area specified by the data relating to the processed area.

[0039] For example, an abnormal section is a section in which at least one of the arithmetic mean of the numerical values ​​specified by the data relating to the machined area, or a value obtained by subtracting a minimum value from a maximum value of the numerical values ​​specified by the data relating to the machined area, is equal to or greater than a predetermined threshold. The arithmetic mean of the numerical values ​​specified by the data relating to the machined area, and the value obtained by subtracting the minimum value from the maximum value of the numerical values ​​specified by the data relating to the machined area, are, for example, the surface roughness Sa and a maximum height Sz.The first determination unit 112 determines, for example, by evaluating whether at least one of the surface roughness Sa or the maximum height Sz in the target area is equal to or greater than the predetermined threshold value, or whether an abnormal section is present in the target area.

[0040] If the first determination unit 112 determines that the target area contains an abnormal section, the subdivision unit 113 subdivides the target area, which the first determination unit 112 has determined to contain an abnormal section, into several areas. That is, each of these areas is a region formed by subdividing the target area.

[0041] Fig. Figure 6 is a diagram showing an example of a target area subdivided by the subdivision unit 113. For example, the subdivision unit 113 subdivides a target area a1 into four areas a11 to a14.

[0042] The second unit of determination 114 determines whether several of the areas a11 to a14, generated by subdivision by the subdivision unit 113, contain an abnormal section. The second unit of determination 114 determines, by evaluating the surface properties of the several areas a11 to a14, whether at least one of the several areas contains an abnormal section. The surface properties are, for example, as described above, the surface roughness Sa or the maximum height Sz. That is, the second unit of determination 114 determines, by determining whether the surface roughness Sa or the maximum height Sz of the individual areas a11 to a14 is equal to or greater than a predetermined threshold, whether an abnormal section is contained in the respective areas a11 to a14.

[0043] If the second determination unit 114 has determined that any of the several areas a11 to a14 contains an abnormal section, the area determination unit 115 designates the area determined to contain an abnormal section as the target area. In the example shown in Fig. As shown in Figure 6, the second determination unit 114 determines, for example, that an abnormal section is contained in area a14. Furthermore, the second determination unit 114 determines that the abnormal section is not contained in areas a11 to a13. In this case, the area-defining unit 115 defines area a14 as the target area A2.

[0044] The subdivision unit 113 subdivides the area, which was defined as target area A2 by the area definition unit 115, into several areas a21 to a24.

[0045] The second determination unit 114 determines whether or not an abnormal section is contained within the multiple areas a21 to a24, which were subdivided by the subdivision unit 113. For example, the second determination unit 114 determines that the abnormal section is contained in areas a21 and a24. Furthermore, the second determination unit 114 determines that the abnormal section is not contained in areas a22 and a23. In this case, the area-defining unit 115 designates area a21 as the target area A3. Although not explicitly stated, the area-defining unit 115 also designates area a24 as another target area.

[0046] Subdivision unit 113 subdivides the area defined by area definition unit 115 as target area A3 into several areas. Subdivision unit 113 subdivides target area A3 into several areas a31 to a34. Similarly, subdivision unit 113 subdivides the other target area into several areas.

[0047] The second determination unit 114 determines whether or not an abnormal section is contained within the multiple areas a31 to a34, which were subdivided by the subdivision unit 113. For example, the second determination unit 114 determines that the abnormal section is contained in areas a31 and a33. Furthermore, the second determination unit 114 determines that the abnormal section is not contained in areas a32 and a34. In this case, the area-defining unit 115 designates area a31 as the target area A4. Although not explicitly stated, the area-defining unit 115 also designates area a33 as another target area.

[0048] Subdivision unit 113 divides the area defined by area definition unit 115 as target area A4 into several areas. Subdivision unit 113 subdivides target area A4 into several areas a41 to a44. Similarly, subdivision unit 113 subdivides the other target area into several areas.

[0049] The second unit of determination 114 determines whether the multiple areas a41 to a44, which were subdivided by the subdivision unit 113, contain the abnormal section or not. For example, the second unit of determination 114 determines that the multiple areas a41 to a44 do not contain the abnormal section. In other words, by subdividing the target area into smaller areas using the subdivision unit 113, an anomaly in the target area is no longer detected.

[0050] If the second determination unit 114 has determined that the abnormal section is not contained within the multiple areas a41 to a44, the anomaly area identification unit 116 identifies each of the multiple areas a41 to a44 as an anomaly area. The anomaly area identification unit 116 encloses the identified anomaly area, for example, with a rectangular frame. In other words, the anomaly area identification unit 116 generates data regarding the processed area in which the anomaly area is surrounded by a rectangular frame.

[0051] Fig. Figure 7 is an example of data regarding the processed area generated by the anomaly area identification unit 116. The anomaly area in the data regarding the processed area is surrounded by a rectangular frame.

[0052] Output unit 117 outputs the data regarding the processed area generated by the anomaly area identification unit 116. Output unit 117 outputs this data to, for example, input / output device 106. Input / output device 106 displays the data regarding the processed area on its screen. In this way, the user can quantitatively assess the processed area based on this data.

[0053] Fig. Figure 8 is a flowchart showing an example of the processing performed by the anomaly area identification device 1. In the anomaly area identification device 1, unit 111 first obtains data regarding the processed area (step S1).

[0054] Next, the first determination unit 112 determines whether an abnormal section is contained in a target area (step S2). If the first determination unit 112 determines that no abnormal section is contained in the target area (if "No" in step S2), the output unit 117 outputs the data regarding the processed area (step S7), thus ending the process.

[0055] If the first determination unit 112 determines that an abnormal section is contained in the target area (in case of JA in step S2), the subdivision unit 113 divides the target area into several areas (step S3).

[0056] Then the second determination unit 114 determines whether the abnormal section is included in the multiple areas or not (step S4).

[0057] If the abnormal section is contained in one or more of the multiple areas (if yes in step S4), the area definition unit 115 defines the area containing the abnormal section as the target area (step S5). Processing then proceeds from step S3.

[0058] If, on the other hand, it is determined that the abnormal section is not included in the multiple areas (in case of "No" in step S4), the anomaly area identification unit 116 identifies the multiple areas as anomaly areas (step S6). That is, the anomaly area identification unit 116 generates data regarding the processed area in which the anomaly areas are identified. Subsequently, the output unit 117 outputs the data regarding the processed area (step S7), thus concluding the process. Second embodiment

[0059] In the first embodiment described above, an example was provided in which the data relating to the machined area are data indicating an irregularity of the machined area. However, the data relating to the machined area can be data indicating other information related to the machined area besides an irregularity.

[0060] For example, the data relating to the machined area can be data that specifies at least one of the following: the movement speed of the tool during machining, a numerical value calculated based on the movement speed, a correction amount during machining, a numerical value calculated based on the correction amount, a detection value of a detection signal during machining, a numerical value calculated based on the detection signal, a command value of a command signal, or a numerical value calculated based on the command value.

[0061] The correction factor includes, for example, a backlash correction factor, a pitch error correction factor, a space error correction factor, and a thermal expansion correction factor. The command signal includes, for example, a command signal to activate a function and a command signal to operate an external device. The external device is, for example, a coolant, a fan, or a chip transport device. The detection signal includes a feedback signal for the command signal to activate a function, a feedback signal from the external device, and a resource utilization rate signal.

[0062] The numerical values, each calculated on the basis of the movement speed, correction magnitude, detection value, and command value, can be a difference value or an integral value of the movement speed, a difference value or an integral value of the correction magnitude, a difference value or an integral value of the detection value, and a difference value or an integral value of the command value.

[0063] Even if the data relating to the processed area are data that provide information other than an irregularity related to the processed area, as in Fig. Figure 1 shows numerical values ​​recorded in association with respective areas that are divided into grid sections. Therefore, even if the data relating to the processed area are data that indicate information other than an irregularity related to the processed area, the anomaly area identification device 1 can determine and identify as an anomaly area an abnormal section that appears in the data relating to the processed area.

[0064] If the data relating to the machined area is any of the aforementioned information elements other than the irregularity, the anomaly area identification device 1 can identify the anomaly area based on the machined area data specifying that particular information element. For example, if the machined area data specifies a recoil correction magnitude, the anomaly area identification device 1 identifies an anomaly area that specifies an abnormal portion of the recoil correction magnitude.

[0065] The anomaly area identification device 1 may further include a similarity determination unit for determining the similarity between an anomaly area identified by the anomaly area identification unit 116 when the data relating to the processed area were data providing initial information, and an anomaly area identified by the anomaly area identification unit 116 when the data relating to the processed area were data providing second information, and an anomaly identification unit for identifying a reason for an anomaly of the abnormal section based on a determination result of the similarity determination unit.

[0066] Fig. Figure 9 is a block diagram showing an example of the functions of an anomaly area identification device 1 with a similarity determination unit and an anomaly identification unit. The other functions of the device are described in Figure 1. Fig. The anomaly area identification device 1 shown in Figure 9, namely the similarity determination unit 118 and the anomaly identification unit 119, are those of the anomaly area identification device 1 shown in Figure 9. Fig. As shown in Figure 5, the similarity determination unit 118 and the anomaly identification unit 119 will be described in this context, and a description of functions other than these will be omitted.

[0067] The anomaly area identification device 1 includes, in addition to the unit 111 for obtaining data regarding the processed area, the first determination unit 112, the subdivision unit 113, the second determination unit 114, the area definition unit 115, the anomaly area identification unit 116 and the output unit 117, the similarity determination unit 118 and the anomaly identification unit 119.

[0068] The similarity determination unit 118 and the anomaly identification unit 119 are implemented, for example, by the hardware processor 101 performing arithmetic operations using the system program stored in the ROM 103 and the various programs and data stored in the non-volatile memory 105.

[0069] Unit 111, for obtaining data regarding the processed area, obtains data concerning the processed area. This data provides initial information, such as the height of the processed area. In this case, the anomaly area identification unit 116, as described in the first embodiment, identifies an anomaly area containing an abnormal section associated with an irregularity in the processed area.

[0070] Unit 111, used to obtain data regarding the machined area, retrieves data that provides information other than irregularity. This data includes a second piece of information, such as the tool's movement speed during machining.

[0071] Fig. 10A is an example of data regarding the machined area, indicating the tool's movement speed during machining. When the machined area data is displayed on a screen, for example, a section where the tool's movement speed is slow is shown in a dark color. Similarly, a section where the tool's movement speed is fast is shown in a light color. It should be noted that in Fig. 10A and Fig. 10B, which will be described later, dark colored sections are represented for simplicity by means of hatched rectangular blocks.

[0072] The first identification unit 112, the subdivision unit 113, the second identification unit 114 and the anomaly area identification unit 116, for example, carry out the processing of the in Fig. The 8 steps S2 to S6 shown are used. In this way, an anomaly area is identified in which an abnormal section related to the movement speed of the tool during machining is contained.

[0073] Fig. 10B is an example of data regarding the processed area in which anomaly areas were identified. Areas identified as anomaly areas are, for example, surrounded by a rectangular frame.

[0074] Unit 111, used to obtain data regarding the machined area, obtains separate data concerning the machined area that provides information other than an irregularity. This machined area data provides a third piece of information. For example, this third piece of information indicates the amount of recoil correction applied during machining.

[0075] Fig. 11A is an example of data regarding the machined area that indicates a recoil correction amount during machining. When the machined area data is displayed on a screen, for example, a section where the recoil correction amount is large is shown in a dark color. Similarly, a section where the recoil correction amount is small is shown in a light color. Note that in Fig. 11A and Fig. 11B, which will be described later, dark colored sections are represented for simplicity by means of hatched rectangular blocks.

[0076] The first identification unit 112, the subdivision unit 113, the second identification unit 114 and the anomaly area identification unit 116, for example, carry out the processing of the in Fig. The 8 steps S2 to S6 shown are performed. In this way, an anomaly area is identified in which an abnormal section related to the recoil correction extent during machining is contained.

[0077] Fig. 11B is an example of data regarding the processed area in which anomaly areas were identified. Areas identified as anomaly areas are, for example, surrounded by a rectangular frame.

[0078] The similarity determination unit 118 determines the similarity between anomaly areas identified by the anomaly area identification unit 116 when the data relating to the processed area were data specifying the first piece of information, and anomaly areas identified by the anomaly area identification unit 116 when the data relating to the processed area were data specifying the second piece of information. Furthermore, the similarity determination unit 118 determines the similarity between anomaly areas identified by the anomaly area identification unit 116 when the data relating to the processed area were data specifying the second piece of information, and anomaly areas identified by the anomaly area identification unit 116 when the data relating to the processed area were data specifying the third piece of information.Furthermore, the similarity determination unit 118 determines the similarity between anomaly areas identified by the anomaly area identification unit 116 when the data relating to the processed area were data specifying the third piece of information, and anomaly areas identified by the anomaly area identification unit 116 when the data relating to the processed area were data specifying the first piece of information. It should be noted that the number of types of data relating to the processed area that are subjected to the similarity determination is not limited to three, but may be two, four, or more.

[0079] Fig. 12A is a diagram showing data relating to the processed area containing an initial anomaly area. Fig. 12B is a diagram showing data regarding the processed area, which contains a second anomaly area. Fig. 12C is a diagram showing data regarding the processed area, which contains a third anomaly region. Fig. Sections 12A to 12C represent the individual anomaly areas, shaded sections.

[0080] The similarity determination unit 118 compares the respective data regarding the processed area containing the first anomaly area, data regarding the processed area containing the second anomaly area, and data regarding the processed area containing the third anomaly area, and determines the degree of similarity.

[0081] The similarity determination unit 118 determines the degree of similarity, for example, using content-based information retrieval (CBIR). Specifically, similarity determination unit 118 determines the degree of similarity of a distribution of anomaly regions contained in the individual elements of the data with respect to the processed area. In other words, similarity determination unit 118 determines the degree of similarity by comparing the positions of the anomaly regions contained in the data with respect to the processed area.

[0082] The similarity determination unit 118 can determine the degree of similarity using the CBIR by comparing feature sizes specified by the data relating to the processed area for each anomaly area.

[0083] The respective areas compared by the similarity determination unit 118 are areas at corresponding positions. For example, the areas surrounded by thick lines are among the anomaly areas that are in Fig. 12A and Fig. Figure 12C shows the first anomaly area and the third anomaly area at corresponding positions.

[0084] The feature parameters are, for example, a histogram, an average image hash, or a scale-invariant feature transform (SIFT). The similarity determination unit 118 can determine the degree of similarity using an evaluation procedure according to the type of feature parameter. The evaluation procedure is, for example, an evaluation procedure using Hamming distance, a degree of cosine similarity, etc.

[0085] The anomaly identification unit 119 identifies a cause for the anomaly of an anomaly area based on a determination result of the similarity determination unit 118. For example, if the position of the first anomaly area and the position of the third anomaly area, contained in the data relating to the machined area, are similar, the anomaly of irregularity of the first anomaly area is most likely caused by the anomaly in the kickback correction magnitude. In this case, the anomaly identification unit 119 determines that the kickback correction magnitude is the cause of the anomaly area. In other words, the anomaly identification unit 119 identifies the cause of the anomaly.

[0086] If a property specified by the first anomaly region and a property specified by the third anomaly region are similar, the anomaly of irregularity in the first anomaly region is most likely caused by the anomaly in the recoil correction magnitude. In this case, the anomaly identification unit 119 determines that the recoil correction magnitude is the cause of the anomaly.

[0087] Output unit 117 outputs data indicating the cause of the anomaly identified by anomaly identification unit 119. Output unit 117 transmits this data, for example, to a display on input / output device 106. This allows an operator to determine the cause of the anomaly in the area being worked.

[0088] Fig. Figure 13 is a flowchart showing an example of the processing performed by the anomaly area identification device 1. First, the anomaly area identification device 1 performs a process to identify an anomaly area (step SA1). The processing of step SA1 is the same as the processing of steps S1 through S6 of the flowchart shown in Fig. Figure 8 is shown. The anomaly area identification device 1, for example, obtains data regarding the processed area that provides the first information, data regarding the processed area that provides the second information, and data regarding the processed area that provides the third information, and identifies anomaly areas in the respective data regarding the processed area.

[0089] Next, the similarity determination unit 118 determines the degree of similarity of each anomaly area (step SA2). Then, the anomaly identification unit 119 identifies the cause of an anomaly (step SA3). Finally, the output unit 117 outputs the data relating to the processed area and data indicating the cause of the anomaly (step SA4), thus concluding the process.

[0090] As described above, the anomaly area identification device 1 comprises the first determination unit 112 to determine whether or not an abnormal section is contained in the target area of ​​data relating to a processed surface, the subdivision unit 113 to subdivide the target area, which the first determination unit 112 has determined to contain an abnormal section, into several areas, the second determination unit 114 to determine whether or not the several areas subdivided by the subdivision unit 113 contain the abnormal section, and the anomaly area identification unit 116 to identify the several areas as anomaly areas if the second determination unit 114 has determined thatthat the multiple areas do not include the abnormal section.

[0091] Furthermore, the anomaly area identification device 1 also includes the area determination unit 115 to define, in the event that the second determination unit 114 determines that an abnormal section is contained in any of the multiple areas, the area determined to contain the abnormal section as a target area, wherein the subdivision unit 113 subdivides each area designated as a target area by the area determination unit 115 into multiple areas. That is to say, in some cases, the anomaly area identification device 1 repeatedly subdivides the target area and determines whether the abnormal section is contained in the areas created by the subdivision. For this reason, the anomaly area identification device 1 can accurately identify the location of an abnormal section.

[0092] Furthermore, an abnormal section is a section in which at least one of the arithmetic mean values ​​of numerical values ​​specified by the data relating to the machined area, or a value obtained by subtracting a minimum value from a maximum value of the numerical values, is equal to or greater than a predetermined threshold. Therefore, the anomaly area identification device 1 can, for example, accurately identify the position of a section on the machined surface where the surface roughness Sa is rough, and the position of a section on the machined surface where the maximum height Sz is high. Alternatively, the anomaly area identification device 1 can accurately identify a position on the machined surface where the tool movement speed varies significantly, and so on.

[0093] Furthermore, the anomaly area identification device 1 also includes the similarity determination unit 118 to determine the degree of similarity between an anomaly area identified by the anomaly area identification unit 116 when the data relating to the processed area provided initial information, and an anomaly area identified by the anomaly area identification unit 116 when the data relating to the processed area provided secondary information, and the anomaly identification unit 119 to identify the cause of the anomaly of the abnormal section based on the determination result by the similarity determination unit 118. Therefore, the anomaly area identification device 1 can identify the cause of the anomaly of the abnormal section.

[0094] Although the disclosure has been described in detail, it is not limited to the individual embodiments mentioned above. Various additions, substitutions, modifications, partial omissions, etc., are possible in these embodiments without deviating from the core of the disclosure or from the core of the disclosure derived from the content described in the claims and their equivalents. Furthermore, these embodiments can be implemented in combination.

[0095] The following are supplementary remarks on the embodiments of the present disclosure. Supplementary note [1]

[0096] An anomaly area identification device comprises a first determination unit configured to determine whether or not an abnormal section is contained in a target area of ​​data relating to a processed surface; a subdivision unit configured to subdivide the target area, which the first determination unit has determined to contain an abnormal section, into multiple areas; and a second determination unit configured to determine whether or not the multiple areas generated by the subdivision unit contain the abnormal section.and an anomaly area identification unit configured to identify the multiple areas as anomaly areas when the second identification unit has determined that the multiple areas do not contain the abnormal section. Supplementary note [2]

[0097] The anomaly area identification device according to Supplementary Note 1 further comprises an area determination unit configured to designate, in the event of a determination by the second determination unit that the abnormal section is contained in any of the multiple areas, each area determined to contain the abnormal section as the target area, the subdivision unit subdividing each area designated as the target area by the area determination unit into multiple areas. Supplementary note [3]

[0098] In the anomaly area identification device according to Supplementary Note [2], the abnormal section is a section in which at least one of the arithmetic mean of numerical values ​​specified by the data relating to the area processed, or of a value obtained by subtracting a minimum value from a maximum value of the numerical values, is equal to or greater than a predetermined threshold. Supplementary note [4]

[0099] The anomaly area identification device according to Supplementary Note [1] further comprises a similarity determination unit configured to determine a degree of similarity between an anomaly area identified by the anomaly area identification unit when the data relating to the processed area were data providing first information and an anomaly area identified by the anomaly area identification unit when the data relating to the processed area were data providing second information; and an anomaly identification unit configured to identify, on the basis of the determination result by the similarity determination unit, the cause of the anomaly of the abnormal section. Supplementary note [5]

[0100] A computer-readable storage medium stores instructions that cause a computer to determine whether an abnormal section is contained in a target area of ​​data relating to a processed surface; if determined to contain an abnormal section, to subdivide the target area, which the first determination unit has determined to contain an abnormal section, into multiple areas; to determine whether the multiple subdivided areas contain the abnormal section; and to identify the multiple areas as anomaly areas if determined to not contain the abnormal section. EXPLANATION OF REFERENCE SYMBOLS 1 ANOMALIC AREA IDENTIFICATION DEVICE 101 HARDWARE PROCESSOR 102 BUS 103 ROM 104 RAM 105 NON-FLAMMABLE STORAGE 106 INPUT / OUTPUT DEVICE 111 UNIT FOR OBTAINING DATA REGARDING THE PROCESSED AREA 112 FIRST UNIT OF DETERMINATION 113 SUBDIVISION UNIT 114 SECOND UNIT OF DETERMINATION 115 AREA DEFINITION UNIT 116 ANOMALIC AREA IDENTIFICATION UNIT 117 OUTPUT UNIT 118 SIMILARITY DETERMINATION UNIT 119 ANOMAL IDENTIFICATION UNIT QUOTES INCLUDED IN THE DESCRIPTION

[0000] This list of documents cited by the applicant was automatically generated and is included solely for the reader's convenience. The list is not part of the German patent or utility model application. The DPMA accepts no liability for any errors or omissions. Cited patent literature

[0000] JP 2021 - 105 825 A

[0003]

Claims

[1] Anomaly area identification device comprising a first determination unit that is set up to determine whether or not an abnormal section is contained in a target area of ​​data relating to a processed area; a subdivision unit which is set up in such a way that, in the event of a determination by the first determination unit that an abnormal section is contained in the target area, it subdivides the target area, which has been determined by the first determination unit to contain an abnormal section, into several areas; a second determining unit configured to determine whether the multiple areas produced by subdivision by the subdivision unit contain the abnormal section or not; and an anomaly area identification unit configured to identify the multiple areas as anomaly areas when the second identification unit has determined that the multiple areas do not contain the abnormal section. [2] Anomaly area identification device according to claim 1, further comprising an area determination unit configured such that, in the event of a determination by the second determination unit that the abnormal section is contained in any of the multiple areas, it designates each area for which it has been determined that it contains the abnormal section as the target area, wherein the subdivision unit subdivides each area designated by the area determination unit as the target area into multiple areas. [3] Anomaly area identification device according to claim 2, wherein the abnormal section is a section in which at least one of an arithmetic mean of numerical values ​​specified by the data relating to the processed area, or a value obtained by subtracting a minimum value from a maximum value of the numerical values, is equal to or greater than a predetermined threshold. [4] Anomaly area identification device according to claim 1, further comprising a similarity determination unit configured to determine a degree of similarity between an anomaly area identified by the anomaly area identification unit when the data relating to the processed area were data providing initial information, and an anomaly area identified by the anomaly area identification unit when the data relating to the processed area were data providing secondary information; and an anomaly identification unit that is configured to identify the cause of the anomaly of the abnormal section based on the determination result by the similarity determination unit. [5] Computer-readable storage medium that stores instructions that cause a computer to, to determine whether an abnormal section is contained in a target area of ​​data relating to a processed area; In the event of a determination that the target area contains an abnormal section, the target area which has been determined to contain an abnormal section should be subdivided into several areas; to determine whether the multiple compartmentalized areas contain the abnormal section or not; and to identify the multiple areas as anomaly areas if it has been determined that the multiple areas do not contain the abnormal section.

Images