Abrasive plane information acquisition device, acquisition program, and abrasive plane information acquisition method

Abstract

To acquire height position information in each part of an abrasive plane in a short time.SOLUTION: A storage part 56 stores an input image 31 which is constituted of a photographic image obtained by photographing an abrasive plane of a grinding wheel as an acquisition object. The storage part 56 stores a machine-learned learning unit 32 using teacher data 33 including example data 331 and correct answer data 332. The example data 331 is constituted of a photographic image obtained by photographing the abrasive plane of the grinding wheel for teacher data acquisition. The correct answer data 332 is constituted of an image which indicates the abrasive plane of the grinding wheel for teacher data acquisition, and indicates height position information in each part of the abrasive plane. An output part 57 outputs an output image 34 which indicates the abrasive plane corresponding to the input image 31, the output image 34 indicating the height position information in each of the parts of the abrasive plane, using the input image 31 as input data, from the learned learning unit 32 stored in the storage part 56.SELECTED DRAWING: Figure 2

Description

[Technical Field]

[0001] The present invention relates to a grinding surface information acquisition device, an acquisition program, and a grinding surface information acquisition method. [Background technology]

[0002] In grinding processing using a grinding device, the finish quality of the machined surface of a workpiece depends on the condition of the machining surface (so-called grinding surface) of the rotating grinding wheel used as a grinding tool. Conventionally, in order to grasp the condition of the grinding surface of a grinding wheel, grinding surface information acquisition devices that acquire information related to the condition of the grinding surface have been proposed (for example, Patent Document 1). In the device described in Patent Document 1, the grinding surface is imaged using a metallurgical microscope equipped with a camera, and the condition of the grinding surface is measured based on the image data. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Laid-Open No. 2004-45078 Summary of the Invention [Problem to be solved by the invention]

[0004] Although electron microscopes can be used to observe the surface properties of the grinding surface in detail, the observation range of an electron microscope is very narrow, so it takes a long time to measure the condition of the grinding surface over the entire surface using an electron microscope. [Means for solving the problem]

[0005] The grinding surface information acquisition device for solving the above problem is a grinding surface information acquisition device that acquires information related to the state of the grinding surface of a rotary grinding wheel, and is equipped with: an input unit that stores input images composed of captured images of the grinding surface of the rotary grinding wheel to be acquired; a memory unit that stores a trained learning device that has been machine-learned using teacher data that includes example data composed of captured images of the grinding surface of the rotary grinding wheel for acquiring teacher data; and correct answer data composed of images that show the grinding surface of the rotary grinding wheel for acquiring the teacher data, and that show height position information for each part of the grinding surface; and an output unit that uses the input image as input data and outputs from the trained learning device an image that shows the grinding surface that corresponds to the input image and that shows height position information for each part of the grinding surface.

[0006] The acquisition program for solving the above problem is an acquisition program that causes an electronic control device provided in the grinding surface information acquisition device to execute the processing of each of the above parts provided in the grinding surface information acquisition device.

[0007] The grinding surface information acquisition method for solving the above problem is a grinding surface information acquisition method for acquiring information related to the state of the grinding surface of a rotary grinding wheel, and includes: an input process for storing an input image, which is an image of the grinding surface of the rotary grinding wheel to be acquired, in an input unit of a grinding surface information acquisition device; a storage process for storing the learning machine in a memory unit of the grinding surface information acquisition device after machine learning using teacher data including example data, which is an image of the grinding surface of the rotary grinding wheel for acquiring teacher data, and correct answer data, which is an image of the grinding surface of the rotary grinding wheel for acquiring the teacher data, and which shows height position information of each part of the grinding surface; and an output process for using the input image as input data, from the trained learning machine stored in the memory unit, to output an image of the grinding surface corresponding to the input image, which shows height position information of each part of the grinding surface.

[0008] According to the grinding surface information acquisition device, acquisition program, and grinding surface information acquisition method, an image showing height position information of each part of the grinding surface can be acquired by acquiring an image of the grinding surface of the grinding wheel to be acquired, more specifically, an input image, and using a learning machine that has been trained in advance by machine learning. This eliminates the need to measure the height position of each finely divided area of ​​the grinding surface of the grinding wheel, and makes it possible to acquire height position information of each part of the grinding surface in a short time. [Effects of the Invention]

[0009] According to the present invention, height position information for each part of the grinding surface can be obtained in a short time. [Brief explanation of the drawings]

[0010] [Figure 1] 1 is a schematic diagram showing a schematic configuration of an automatic grinding device to which an abrasive surface information acquisition device according to an embodiment is applied; [Figure 2] FIG. 2 is a block diagram showing a schematic configuration of the grinding surface information acquisition device. [Figure 3] 1 is a schematic diagram showing the structure of a camera unit. [Figure 4] 1 is a schematic diagram showing an input image. [Figure 5] 1 is a schematic diagram showing training data. [Figure 6] FIG. 10 is an enlarged view of a portion of the correct answer data. [Figure 7] 10 is a flowchart showing the execution procedure of an image acquisition process. [Figure 8] 1 is a schematic diagram showing the relationship between the grinding surface of the grindstone and the imaging range of the camera. [Figure 9] FIG. 10 is a block diagram showing an execution procedure of an image acquisition process according to a modified example. DETAILED DESCRIPTION OF THE INVENTION

[0011] Hereinafter, an embodiment of a grinding surface information acquisition device, an acquisition program, and a grinding surface information acquisition method will be described with reference to FIGS. <Automatic grinding device 20> As shown in FIG. 1, the grinding surface information acquisition device 30 of this embodiment is applied to an automatic grinding machine 20. This automatic grinding machine 20 is a numerically controlled (NC) surface grinding machine that uses a rotary grinding wheel (hereinafter referred to as grinding wheel 21) to grind the surface of a workpiece (not shown). The grinding wheel 21 for grinding has an outer peripheral surface that forms a grinding surface 211. Specifically, the grinding wheel 21 has a structure in which a large number of abrasive grains are fixed to the outer peripheral surface of a cylindrical base material with a binder. The grinding wheel 21 is rotatably supported by a grinding wheel support part 22. The grinding wheel 21 and the grinding wheel support part 22 are movable relative to a base 23 in the vertical direction (hereinafter referred to as the Y direction) and the horizontal direction, specifically the depth direction in FIG. 1 (hereinafter referred to as the Z direction). In the automatic grinding machine 20, the grinding wheel 21 is brought into contact with the workpiece while being rotationally driven, thereby grinding the surface of the workpiece.

[0012] The automatic grinding device 20 has a table 24 as a support base for supporting a workpiece. The table 24 is movable in a horizontal direction perpendicular to both the Z direction and the Y direction, specifically in the left-right direction in FIG. 1 (hereinafter referred to as the X direction). In the automatic grinding device 20, the workpiece on the table 24 can be moved by moving the table 24 in the X direction. This allows the relative positions of the grinding wheel 21 and the workpiece in the X direction to be changed.

[0013] 1 and 2, the automatic grinding device 20 has an operation control unit 25 that controls the operation of the device. The operation control unit 25 has an X-axis drive unit 26, a Y-axis drive unit 27, a Z-axis drive unit 28, and a grindstone drive unit 29.

[0014] The automatic grinding device 20 can change the relative positions of the grinding wheel 21 and the workpiece in the X direction, the Y direction, and the Z direction, respectively, by moving the grinding wheel 21 in the Y direction and the Z direction and by moving the table 24 in the X direction. The X-axis drive unit 26 is a device for moving the table 24 in the X direction relative to the base 23. The X-axis drive unit 26 includes a ball screw mechanism, a servo motor, and the like (not shown). The X-direction position of the table 24 relative to the base 23 is controlled by controlling the operation of the X-axis drive unit 26. The Y-axis drive unit 27 is a device for moving the grinding wheel 21 and the grinding wheel support unit 22 in the Y direction relative to the base 23. The Y-axis drive unit 27 includes a ball screw mechanism, a servo motor, and the like (not shown). The Y-direction position of the grinding wheel 21 relative to the base 23 is controlled by controlling the operation of the Y-axis drive unit 27. The Z-axis drive unit 28 is a device for moving the grinding wheel 21 and the grinding wheel support unit 22 in the Z direction relative to the base 23. The Y-axis driving unit 27 has a ball screw mechanism, a servo motor, etc. (not shown). Through the operation control of the Y-axis driving unit 27, the position of the grinding wheel 21 in the Z direction relative to the base 23 is controlled.

[0015] The grinding wheel driving unit 29 includes an electric motor connected to the rotation shaft of the grinding wheel 21, a rotation phase sensor that detects the rotation phase of the grinding wheel 21, and the like. In the operation control of the grinding wheel driving unit 29 (more specifically, the electric motor), the grinding wheel 21 is basically rotated at a constant speed. The rotation speed of the grinding wheel 21 is set based on the processing conditions input to the automatic grinding device 20 and is a speed that matches the processing conditions.

[0016] <Abrasive surface information acquisition device 30> The grinding surface information acquisition device 30 of this embodiment will be described in detail below. The grinding surface information acquisition device 30 is a device for acquiring information relating to the state of the grinding surface 211 of the grinding wheel 21, specifically, height position information. In this embodiment, based on the acquired height position information of each part of the grinding surface 211, it becomes possible to check, for example, the state of the grinding surface 211 of the grinding wheel 21. The grinding surface information acquisition device 30 includes a camera unit 40 and an electronic control device 50.

[0017] <Camera Unit 40> 1 to 3, the camera unit 40 captures an image of the grinding surface 211 of the grindstone 21. The camera unit 40 includes a camera 41 as an imaging unit, and an illumination unit 43.

[0018] <Camera 41> As shown in FIGS. 1 and 3, the camera 41 is disposed below the grinding wheel 21. The camera 41 captures an image of the grinding surface 211 of the grinding wheel 21 from a direction perpendicular to the grinding surface 211 (more specifically, the tangent plane of the grinding surface 211 indicated by the dashed line in FIG. 3). In this embodiment, the camera 41 captures an image of the grinding surface 211 while the grinding wheel 21 is rotating at a predetermined speed VW. The captured image captured by the camera 41 is stored as an input image 31 in the electronic control device 50, which will be described later. In this embodiment, the grinding wheel 21 attached to the automatic grinding machine 20 when the camera 41 captures an image corresponds to the rotating grinding wheel to be acquired.

[0019] <Lighting Department 43> As shown in FIG. 3, the illumination unit 43 illuminates the lower end portion of the grinding surface 211, i.e., the area to be imaged by the camera 41 (hereinafter, referred to as the image-capturing area RE). The illumination unit 43 includes a first illumination unit 45 and a second illumination unit 46. The first illumination unit 45 irradiates the image-capturing area RE of the grinding surface 211 with first illumination light 45L having a first emission color (e.g., blue) from a direction perpendicular to the grinding surface 211 (more specifically, the tangent plane of the grinding surface 211 shown by the dashed-dotted line in FIG. 3). The second illumination unit 46 irradiates the image-capturing area RE of the grinding surface 211 with second illumination light 46L having a second emission color (e.g., white) different from the first emission color from a direction oblique to the grinding surface 211 (more specifically, the tangent plane of the grinding surface 211 shown by the dashed-dotted line in FIG. 3).

[0020] In this embodiment, the camera unit 40 is detachable from the automatic grinding apparatus 20. The camera unit 40 is attached to the automatic grinding apparatus 20 when imaging the grinding surface 211. In the camera unit 40, when imaging the grinding surface 211 using the camera 41, the illumination unit 43 illuminates the imaging target area RE of the grinding surface 211. Note that in this embodiment, when grinding is performed by the automatic grinding apparatus 20, the camera unit 40 is detached from the automatic grinding apparatus 20.

[0021] <Electronic control device 50> The electronic control device 50 executes various controls to obtain information relating to the state of the grinding surface 211 of the grinding wheel 21.

[0022] The electronic control device 50 includes a PU 51, a ROM 52, a RAM 53, an operation input unit 54, a display unit 55, and a memory unit 56. The PU 51 is a processing unit such as a CPU, a GPU, and a TPU. The operation input unit 54 is an input device such as a mouse, a keyboard, a touch panel, and buttons. The operation input unit 54 is operated when configuring various settings for the grinding surface information acquisition device 30 or when operating the grinding surface information acquisition device 30. The display unit 55 includes a display device such as an LCD display or an organic EL display. The display unit 55 displays various information related to the acquisition of images, such as images of the grinding surface 211 acquired through the image acquisition process described below. The memory unit 56 is composed of non-volatile memory such as a hard disk drive or solid-state drive that can be written to and read from as needed. The memory unit 56 includes a memory area for storing various execution programs 35, a memory area for storing training data 33 used in machine learning by the learner 32, and a memory area for storing trained learners 32. The storage unit 56 also has a storage area as an input unit that stores an image (the input image 31) of the grinding surface 211 of the grinding wheel 21 to be acquired. The execution program 35 includes a program for causing the learning device 32 to execute machine learning, and an acquisition program for causing the learning device 32 to execute various processes related to acquiring information related to the grinding surface 211 of the grinding wheel 21.

[0023] The electronic control device 50 includes an output unit 57 as a functional unit. The output unit 57 uses the input image 31 as input data and outputs, from the trained learning device 32 stored in the memory unit 56, an image (hereinafter, output image 34) showing the grinding surface 211 corresponding to the input image 31, and also showing height position information of each part of the grinding surface 211.

[0024] <Image capture processing> In this embodiment, in order to acquire the input image 31, an imaging process is executed in which the camera 41 captures an image of the grinding surface 211 of the grindstone 21.

[0025] In the imaging process, first, the grinding wheel 21 to be acquired is attached to the automatic grinding device 20, and the grinding wheel 21 is driven to rotate. Then, in this state, an image of the grinding surface 211 is captured by the camera 41. In this embodiment, patterns for the rotational drive pattern of the grinding wheel 21, the position control pattern of the camera 41, and the imaging pattern of the camera 41 that enable the camera 41 to efficiently capture the entire surface of the grinding surface 211 are determined in advance and stored in the electronic control device 50.

[0026] Possible methods for storing the above patterns in the memory unit 56 include the following (Method A) and (Method B). (Method A) After the user of the automatic grinding device 20 installs the grinding wheel 21 that will actually be used, the user operates the automatic grinding device 20 to determine the above patterns suitable for the grinding wheel 21, and stores these patterns in the electronic control device 50. (Method B) Based on the results of various experiments and simulations, the manufacturer of the automatic grinding device 20 determines in advance the above patterns that will enable efficient imaging of the entire grinding surface 211 of the grinding wheel 21. Data related to these patterns is then stored in the automatic grinding device 20 before shipment, or in an automatic grinding device 20 installed in the user's factory.

[0027] When capturing an image of the grinding surface 211 of the grinding wheel 21, the operation of the grinding wheel driver 29 is controlled based on the rotational drive pattern of the grinding wheel 21, and the operation of the X-axis driver 26, the Y-axis driver 27, and the Z-axis driver 28 is controlled based on the position control pattern of the camera 41. Furthermore, the camera 41 captures an image of the grinding surface 211 based on the image capturing pattern of the camera 41. The electronic control device 50 then captures image data of the grinding surface 211 captured by the camera 41 and stores the image data in the memory 56. Specifically, the camera 41 captures images of the grinding surface 211 multiple times. The captured images are then combined in a predetermined order, vertically and horizontally, to form a single image (input image 31) showing the entire grinding surface 211, as shown in FIG. 4 . The electronic control device 50 stores the input image 31 thus generated in the memory 56.

[0028] In the grinding surface information acquisition device 30 of this embodiment, the camera 41 captures an image of the grinding surface 211 of the grinding wheel 21 while the grinding wheel 21 is rotating at a predetermined speed VW. This makes it possible to capture an image of the entire grinding surface 211 of the grinding wheel 21 in a short period of time.

[0029] <Learning Module 32> The learning device 32 will be described in detail below. A Generative Adversarial Network (GAN), more specifically an image generation model called "pix2pix," is used as the learning device 32. The learning device 32 performs machine learning using training data 33. The training data 33 is an image showing the grinding surface 211 corresponding to the input image 31, and is data for performing machine learning on the learning device 32 so that the learning device 32 acquires the ability to generate an image showing height position information for each part of the grinding surface 211 based on the input image 31.

[0030] <Teacher Data 33> As shown in FIG. 5, the training data 33 is composed of an image data set in which example data 331 and correct answer data 332 are paired.

[0031] <Example data 331> The example data 331 is an image composed of captured images of the grinding surface 211 of the grinding wheel 21. The example data 331 can be generated, for example, by the following procedure. First, the grinding wheel 21 for creating the training data is attached to the automatic grinding device 20 (FIG. 1). Then, the imaging process is executed in this state. The captured image acquired through the imaging process is used as the example data 331. Alternatively, it is also possible to use a separate device different from the automatic grinding device 20 to capture an image of the grinding surface 211 of the grinding wheel 21 while rotating the grinding wheel 21 at a predetermined speed VW, and use the captured image as the example data 331. As the example data 331, a single image showing the entire grinding surface 211 is generated.

[0032] <Correct answer data 332> The correct answer data 332 is an image showing the grinding surface 211 of the grinding wheel 21, and is composed of an image showing height position information of each part of the grinding surface 211. As shown in an enlarged view of a portion in Fig. 6, the correct answer data 332 is composed of an image that represents the height position information of each part of the grinding surface 211 by color, a so-called color map. Note that Fig. 6 shows the correct answer data 332 as a grayscale image, but in reality the correct answer data 332 is a color image.

[0033] The correct data 332 can be generated, for example, by the following procedure. First, a measuring device such as a three-dimensional measuring machine is used to measure the height position of each part of the grinding surface 211 of the grinding wheel 21 used to create the training data. In this embodiment, the height position of each part of the grinding surface 211 is measured relative to the outermost peripheral surface of the grinding surface 211. Then, based on the measured height positions of each part of the grinding surface 211, a color map is generated, which is an image showing the grinding surface 211 of the grinding wheel 21 used to create the training data and which also shows height position information of each part of the grinding surface 211. The color map generated in this manner is used as the correct data 332. As the correct data 332, a single image showing the entire grinding surface 211 is generated.

[0034] As shown in FIG. 5 , in this embodiment, a large number of image data sets are created, each pair consisting of example data 331 and correct answer data 332. Then, as shown in FIG. 2 , these image data sets are used as training data 33 for the learner 32. More specifically, the electronic control device 50 extracts one of the multiple image data sets that make up the training data 33 and uses this as input data to cause the learner 32 to perform machine learning. This learning process is repeatedly performed for each image data set that makes up the training data 33. Then, the machine learning model constructed through the execution of machine learning is stored in the storage unit 56 as the trained learner 32. Note that in this embodiment, the process of storing the trained learner 32 in the storage unit 56 corresponds to the storage process.

[0035] When the trained learning device 32 receives the input image 31, which is an image of the grinding surface 211 of the grinding wheel 21 to be acquired, it outputs an image showing the grinding surface 211 corresponding to the input image 31, and also an image showing the height position information of each part of the grinding surface 211.

[0036] <Image acquisition process> The following will specifically describe the process (image acquisition process) for acquiring images showing height position information for each part of the grinding surface 211. Figure 7 shows the execution procedure for the image acquisition process. The series of processes shown in the flowchart of Figure 7 are executed by the electronic control unit 50 as processes at predetermined intervals.

[0037] 7, in this process, first, an image (input image 31) of the grinding surface 211 of the grinding wheel 21 attached to the automatic grinding device 20 is stored in the storage unit 56 (step S11). Specifically, the imaging process is executed. Then, the input image 31 is formed based on the image data acquired by the imaging process, and the input image 31 is stored in the storage unit 56. In this embodiment, the process of step S11 corresponds to an input step.

[0038] Thereafter, using the input image 31 stored in the memory unit 56 as input data, an image showing the grinding surface 211 corresponding to the input image 31 (hereinafter referred to as output image 34) is generated and output from the trained learning device 32 stored in the memory unit 56 (step S12). In this embodiment, the output image 34 is an image showing the grinding surface 211 corresponding to the input image 31, and also an image showing height position information of each part of the grinding surface 211, more specifically, a color map that represents the height position information of each part of the grinding surface 211 by color. In this embodiment, the processing of step S12 corresponds to the output step.

[0039] <Actions and Effects of This Embodiment> The operation and effects of this embodiment will be described. (1) The grinding surface information acquisition device 30 includes an input unit, a memory unit 56, and an output unit 57. The input unit stores an input image 31 composed of a captured image of the grinding surface 211 of the grinding wheel 21 to be acquired. The memory unit 56 stores a trained learning device 32 that has undergone machine learning using teacher data 33 including example data 331 and correct answer data 332. The example data 331 is composed of a captured image of the grinding surface 211 of the grinding wheel 21 used to acquire the teacher data. The correct answer data 332 is composed of an image of the grinding surface 211 of the grinding wheel 21 used to acquire the teacher data, and an image showing height position information of each part of the grinding surface 211. The output unit 57 uses the input image 31 as input data and outputs, from the trained learning device 32 stored in the memory unit 56, an output image 34 that shows the grinding surface 211 corresponding to the input image 31 and that also shows height position information of each part of the grinding surface 211.

[0040] According to the above configuration, by acquiring an input image 31 capturing an image of the grinding surface 211 of the grinding wheel 21 to be acquired, and using a learning device 32 that has undergone machine learning in advance, it is possible to acquire an output image 34 showing height position information for each part of the grinding surface 211. This eliminates the need for a time-consuming task of measuring the height position for each finely divided region of the grinding surface 211 of the grinding wheel 21 to be acquired, in order to acquire height position information for each part of the grinding surface 211. Therefore, height position information for each part of the grinding surface 211 can be acquired in a short time.

[0041] (2) Each of the input image 31, the example data 331, and the correct answer data 332 is a single image showing the entire grinding surface 211. According to the above configuration, with a simple configuration in which a single input image 31 capturing the entire grinding surface 211 is used as input data, height position information for each part of the grinding surface 211 can be obtained throughout the entire grinding surface 211.

[0042] (3) The grinding wheel 21 has an outer peripheral surface that forms a grinding surface 211 . As shown in FIG. 8 , in this embodiment, the grinding surface 211 of the grinding wheel 21 is curved in one direction. Therefore, if the height position of each part of the grinding surface 211 is measured using a measuring device, the height direction of the grinding surface 211 (specifically, the radial direction of the grinding wheel 21) will be misaligned with the measurement direction of the grinding surface 211 (the up-down direction in FIG. 8 ) at both end portions P2 of the measurement range P1 in the curvature direction. Therefore, if the measurement range P1 for one measurement is made too wide, the height of the grinding surface 211 cannot be measured accurately due to the misalignment between the height direction and the imaging direction. Therefore, in a grinding wheel 21 whose outer circumferential surface is the grinding surface 211, the measurement range P1 for one measurement is likely to be narrow, and the time required to measure the grinding surface 211 is likely to be long.

[0043] According to this embodiment, by using the input image 31 and the trained learning device 32, it is possible to acquire an output image 34 including height position information for each portion of the grinding surface 211 of the grinding wheel 21 to be acquired, without being affected by a misalignment between the height direction and the imaging direction in the input image 31. Therefore, when the grinding surface 211 of the grinding wheel 21 to be acquired is imaged by the camera 41 to form the input image 31, a misalignment between the height direction and the imaging direction is allowed. This makes it possible to widen the measurement range P1 in a single image acquisition, thereby shortening the time required to acquire the input image 31. Therefore, according to this embodiment, even when a grinding wheel 21 whose outer circumferential surface becomes the grinding surface 211 is used, it is possible to acquire an output image 34 indicating height position information for each portion of the grinding surface 211 in a short time.

[0044] (4) As the output image 34, an image that represents the height position information of each part of the grinding surface 211 by color, that is, a so-called color map, can be obtained. <Example of change> The above embodiment can be modified as follows: The above embodiment and the following modifications can be combined with each other within the scope of technical compatibility.

[0045] In order to obtain the captured image that serves as the basis for the input image 31 and the example data 331, the grinding surface 211 of the grinding wheel 21 may be imaged with the grinding wheel 21 stopped from rotating or with the grinding wheel 21 rotating at a relatively slow speed (slower than the predetermined speed VW). Even with this configuration, when obtaining height position information for each part of the grinding surface 211 of the grinding wheel 21 to be obtained, it is not necessary to measure the grinding surface 211 each time using a measuring device such as a three-dimensional measuring machine. Therefore, height position information for each part of the grinding surface 211 can be obtained in a short time.

[0046] The grinding wheel 21 used to form the correct answer data 332 may be a grinding wheel 21 with debris such as chips and grinding fluid still attached to the grinding surface 211, or a grinding wheel 21 with the debris removed from the grinding surface 211. When a grinding wheel 21 with debris still attached is used, an output image 34 showing the grinding surface 211 with the debris attached can be obtained as an output image 34 from the trained learning device 32. The state of the grinding surface 211 can be confirmed based on this output image 34. On the other hand, when a grinding wheel 21 with debris removed from the grinding surface 211 is used, an output image 34 showing the grinding surface 211 with no debris attached can be obtained as an output image 34 from the trained learning device 32. The state of the grinding surface 211 can be confirmed based on this output image 34.

[0047] The correct data 332 may be formed based on measurement data obtained by measuring the grinding surface 211 of the grinding wheel 21 using a scanning electron microscope (SEM). Instead of configuring the correct answer data 332 as a color map that represents the height position information of each part of the grinding surface 211 with color, the correct answer data 332 may be configured as an image that represents the height position information of each part of the grinding surface 211 with shades of the same color, that is, a so-called grayscale image. With this configuration, the output image 34 is an image showing the grinding surface 211 that corresponds to the input image 31, and is a grayscale image that represents the height position information of each part of the grinding surface 211 with shades of the same color.

[0048] The camera unit 40 may be configured as one unit with the automatic grinding device 20. In this configuration, an output image 34 including height position information of each part of the grinding surface 211 can be acquired while the grinding wheel 21 is rotating between grinding processes of the workpiece by the automatic grinding device 20. Then, the state of the grinding surface 211 of the grinding wheel 21 can be confirmed based on this output image 34. With the above configuration, the automatic grinding device 20 can be operated efficiently while the state of the grinding wheel 21 is confirmed at appropriate times.

[0049] The camera unit 40 may be disposed to the side of the grindstone 21 or above the grindstone 21. The structure of the illumination unit 43 can be changed as desired. For example, one of the first illumination unit 45 and the second illumination unit 46 may be omitted. The first emission color of the first illumination light 45L from the first illumination unit 45 and the second emission color of the second illumination light 46L from the second illumination unit 46 can be changed as desired.

[0050] A separate device other than the automatic grinding device 20 and a camera included in the device may be used to capture an image of the grinding surface 211 of the grinding wheel 21 to be acquired, and the input image 31 may be formed based on the captured image. In this case, in step S11 of the image acquisition process (FIG. 7), the input image 31 formed as described above may be stored in the memory unit 56 of the electronic control device 50. When this configuration is adopted, the camera unit 40 may be omitted.

[0051] The work of storing the learned learning device 32 in the electronic control device 50 can be performed in any manner, such as the following (Work A) to (Work C). (Task A) Using the automatic grinding device 20 and grinding surface information acquisition device 30 used by the user, teacher data 33 is acquired, and the learner 32 is trained by machine learning using the teacher data 33.

[0052] (Work B) The manufacturer of the automatic grinding device 20 or the manufacturer of the grinding wheel 21 provides the training data 33 corresponding to the grinding wheel 21 that is actually used. The training data 33 is then stored in the electronic control device 50 of the grinding surface information acquisition device 30 used by the user, thereby allowing the learning device 32 to perform machine learning.

[0053] (Operation C) When manufacturing the grinding surface information acquisition device 30, the learned learning device 32 is stored in the electronic control device 50. The grinding wheel 21 can be a general grinding wheel containing general abrasive grains or a superabrasive grinding wheel containing superabrasive grains. Because superabrasive grains are smaller than general abrasive grains, capturing a high-magnification image of the grinding surface of a superabrasive grinding wheel is essential to accurately assess the condition of the grinding surface. Therefore, when capturing an image of a superabrasive grinding wheel, the capture range per capture tends to be narrower than when capturing an image of a general grinding wheel, and the time required to capture an image of the grinding surface tends to be longer. According to the above embodiment, even when such a superabrasive grinding wheel is used as the grinding wheel 21, an output image 34 containing height position information for each portion of the grinding surface 211 of the target grinding wheel 21 can be captured in a short time.

[0054] The input image 31 is not limited to a single image showing the entire grinding surface 211, but may also be a single image showing a portion (e.g., half) of the grinding surface 211, or multiple images obtained by dividing an image showing the entire grinding surface 211 into multiple parts. When multiple images are used as the input image 31, the image acquisition process (see FIG. 7) may be performed for each of the multiple images.

[0055] The input image 31 captured by the camera unit 40 can be used as input data either at the size at which it was captured or after enlarging or reducing it. This configuration allows for a high degree of freedom in the imaging process for acquiring the input image 31. For example, the following configurations (Configuration A) and (Configuration B) are conceivable.

[0056] (Configuration A) The example data 331 and the correct answer data 332 are constructed from captured images of the grinding surface 211 taken at a high magnification (M1). The input image 31 is constructed from captured images of the grinding surface 211 taken at a relatively low magnification (M2). The input image 31 is enlarged by a predetermined ratio R1 (R1=M1 / M2) and used as input data.

[0057] Here, when the abrasive grains of the grinding wheel 21 are small, it is preferable to image the grinding surface 211 at a high magnification in order to capture the characteristics of the grinding surface 211. However, when the grinding surface 211 is imaged at a high magnification, the imaging range in one image capture becomes narrower, which creates a trade-off in that it takes a long time to image the entire grinding surface 211.

[0058] According to the above configuration A, an input image 31, which is an image of the grinding surface 211 captured at a relatively low magnification M2, is used as input data, and an output image 34 equivalent to an image of the grinding surface 211 captured at a high magnification M1 is generated and output from the trained learning device 32. Therefore, when the abrasive grains of the grinding wheel 21 are small, an image equivalent to an image of the grinding surface 211 captured at a high magnification can be obtained as the output image 34, even if the grinding surface 211 is not captured at a high magnification to obtain the input image 31.

[0059] (Configuration B) The example data 331 and the correct answer data 332 are constructed from images of the grinding surface 211 captured at a low magnification (M3). The input image 31 is constructed from images of the grinding surface 211 captured at a relatively high magnification (M4). The input image 31 is reduced by a predetermined ratio R2 (R2 = M4 / M3) and used as input data.

[0060] According to the above configuration B, an input image 31, which is an image of the grinding surface 211 captured at a relatively high magnification M4, is used as input data, and an output image 34 equivalent to an image of the grinding surface 211 captured at a low magnification M3 is generated and output from the trained learning device 32. Therefore, when the abrasive grains of the grinding wheel 21 are large, an image equivalent to an image of the grinding surface 211 captured at a low magnification can be obtained as the output image 34, even if the grinding surface 211 is not captured at a low magnification to obtain the input image 31.

[0061] 9, two learning devices 61 and 62 may be used based on an input image 31 to generate and output an output image 34 indicating height position information for each part of the grinding surface 211. In this case, the output image 34 can be output, for example, in the following procedure.

[0062] First, using the input image 31 as input data, the first learning device 61 generates and outputs an image (hereinafter, intermediate image 63) showing the grinding surface 211 corresponding to the input image 31, which also shows the grinding surface 211 corresponding to the example data 331. The first learning device 61 is a trained learning device that has been machine-learned to acquire the ability to generate the intermediate image 63 based on the input image 31.

[0063] Thereafter, the second learning device 62 uses the intermediate image 63 as input data to generate and output an output image 34 indicating height position information for each part of the grinding surface 211. The second learning device 62 is a trained learning device that has been machine-learned to acquire the ability to generate the output image 34 based on the intermediate image 63.

[0064] Here, if the input data and the example data are image data captured in different imaging environments, a learning device trained by machine learning using the same teacher data may not be able to generate and output an appropriate image. For example, such a case may occur when the input image 31 is composed of an image captured by a camera and the example data 331 is composed of measurement data obtained by a scanning electron microscope.

[0065] According to the above configuration, even if the input image 31 and the example data 331 are image data captured in different imaging environments, by setting two learning devices 61 and 62, it is possible to reduce the difference between the input data and the example data for each of the learning devices 61 and 62. Then, by using the first learning device 61 and the second learning device 62, it is possible to generate and output an appropriate image as the output image 34 based on the input image 31.

[0066] As the learning device 32, any image generation model other than "pix2pix" can be used as long as it can generate an output image 34 showing height position information for each part of the grinding surface 211 from an input image 31 capturing the grinding surface 211. It is also possible to use an image generation model other than a generative adversarial network as the learning device 32.

[0067] The grinding surface information acquisition device, acquisition program, and grinding surface image acquisition method according to the above-described embodiments can be applied to a rotating grinding wheel for circumferential grinding, in which the outer peripheral surface of a cylindrical substrate serves as the grinding surface, as well as to a rotating grinding wheel for front grinding, in which the bottom surface of a cylindrical substrate serves as the grinding surface.

[0068] <Additional Notes> The above embodiment includes the configurations described in the following supplementary notes. [Appendix 1] A grinding surface information acquisition device for acquiring information related to the state of the grinding surface of a rotary grinding wheel, comprising: an input unit for storing input images composed of captured images of the grinding surface of the rotary grinding wheel to be acquired; a memory unit for storing a trained learning device that has been machine-learned using teacher data including example data composed of captured images of the grinding surface of the rotary grinding wheel for acquiring teacher data; and correct answer data composed of images of the grinding surface of the rotary grinding wheel for acquiring the teacher data, the correct answer data being an image of the grinding surface of the rotary grinding wheel for acquiring the teacher data, and showing height position information of each part of the grinding surface; and an output unit that uses the input image as input data and outputs from the trained learning device an image of the grinding surface corresponding to the input image, and showing height position information of each part of the grinding surface.

[0069] [Appendix 2] The grinding surface information acquisition device according to [Appendix 1], wherein each of the input image, the example data, and the correct answer data is a single image showing the entire grinding surface. [Appendix 3] The grinding surface information acquisition device according to [Appendix 1] or [Appendix 2], wherein the rotating grindstone has an outer peripheral surface that serves as a grinding surface.

[0070] [Appendix 4] The grinding surface information acquisition device according to any one of [Appendix 1] to [Appendix 3], wherein the correct answer data is an image that represents height position information of each part of the grinding surface by color. [Appendix 5] [Appendix 1] to [Appendix 4]. An acquisition program that causes an electronic control device provided in the grinding surface information acquisition device to execute the processing of each of the units provided in the grinding surface information acquisition device.

[0071] [Appendix 6] A grinding surface information acquisition method for acquiring information related to the state of the grinding surface of a rotary grinding wheel, comprising: an input step of storing an input image, composed of an image of the grinding surface of the rotary grinding wheel to be acquired, in an input unit of a grinding surface information acquisition device; a storage step of storing the learning machine in a memory unit of the grinding surface information acquisition device after machine learning using teacher data including example data composed of an image of the grinding surface of the rotary grinding wheel for acquiring teacher data and ground truth data composed of an image of the grinding surface of the rotary grinding wheel for acquiring the teacher data, which is an image of the grinding surface of the rotary grinding wheel for acquiring the teacher data and indicates height position information of each part of the grinding surface; and an output step of outputting, using the input image as input data, an image of the grinding surface corresponding to the input image and indicating height position information of each part of the grinding surface from the trained learning machine stored in the memory unit. [Explanation of symbols]

[0072] RE: Image target area IM…Image P1: Measurement range P2: Both ends AR…Range 20...Automatic grinding device 21...Grinding stone 211...Abrasive surface 22...Grinding stone support part 23...Foundation 24...Table 25...Operation control unit 26...X-axis drive unit 27...Y-axis drive unit 28...Z-axis drive unit 29...Grinding wheel drive unit 30…Abrasive surface information acquisition device 31...Input image 32...Learning unit 33…Teacher data 331...Example data 332...Correct data 34...Output image 35...Execution program 40...Camera unit 41...Camera 43...Lighting section 45...1st irradiation section 45L...First lighting 46…Second irradiation section 46L…Second illumination light 50...Electronic control device 51...CPU 52...ROM 53...RAM 54...Operation input section 55...Display section 56...Storage section 57...Output section 61...First learning unit 62...Second learning unit 63...Intermediate image

Claims

1. A grinding surface information acquisition device for acquiring information on the state of a grinding surface of a rotating grinding wheel, an input unit that stores an input image formed by capturing an image of the grinding surface of the grinding wheel to be acquired; a storage unit that stores a trained learning device that has been machine-learned using teacher data including example data that is configured by captured images of the grinding surface of the rotary grindstone for acquiring teacher data, and correct answer data that is configured by images that show the grinding surface of the rotary grindstone for acquiring the teacher data and that indicate height position information of each part of the grinding surface; an output unit that uses the input image as input data and outputs, from the trained learning device, an image showing the grinding surface corresponding to the input image and showing height position information of each part of the grinding surface; A grinding surface information acquisition device comprising:

2. Each of the input image, the example data, and the correct answer data is a single image showing the entire grinding surface. The grinding surface information acquisition device according to claim 1 .

3. The rotating grindstone has an outer circumferential surface that serves as a grinding surface. The grinding surface information acquisition device according to claim 1 or 2.

4. The correct answer data is an image that represents height position information of each part of the grinding surface by color. The grinding surface information acquisition device according to claim 1 or 2.

5. 3. An acquisition program that causes an electronic control device provided in the grinding surface information acquisition device to execute processing of each of the units provided in the grinding surface information acquisition device according to claim 1 or 2.

6. A grinding surface information acquisition method for acquiring information on the condition of a grinding surface of a rotating grinding wheel, comprising: an input step of storing an input image, which is composed of an image of the grinding surface of the grinding wheel to be acquired, in an input unit of the grinding surface information acquisition device; a storage process in which a learning machine uses training data including example data composed of captured images of the grinding surface of the rotary grindstone for acquiring training data, and ground truth data composed of images showing the grinding surface of the rotary grindstone for acquiring training data and showing height position information of each part of the grinding surface, and then stores the learning machine in a storage unit of the grinding surface information acquisition device; an output step of using the input image as input data and outputting, from a trained learning device stored in the storage unit, an image showing the grinding surface corresponding to the input image and showing height position information of each part of the grinding surface; A grinding surface information acquisition method comprising:

Images