Processed surface state estimation device, estimation program and processed surface state estimation method

Abstract

To shorten and reduce time and labor required for work for setting a learned learning device.SOLUTION: A processed surface state estimation device includes a storage part, a resizing part, and an output part. The storage part stores a learned second learning device 62 learning an image related to an abrasive plane of a grinding wheel having abrasive grains having a predetermined particle diameter G2 as learning data, a photographic image 44 which is an image related to the abrasive plane of the grinding wheel as an object to be estimated, and particle diameter information on a particle diameter G1 of the grinding wheel as the object to be estimated. The resizing part changes an image size of the photographic image 44 with a change rate RG, and generates a resized image. The output part utilizes the resized image, and outputs abrasive grain information indicating the state of the abrasive plane of the grinding wheel as the object to be estimated, from the second learning device 62.SELECTED DRAWING: Figure 11

Description

[Technical field]

[0001] The present invention relates to a machined surface condition estimating device that estimates the condition of a machined surface of a tool, an estimation program used in the device, and a machined surface condition estimating method that determines the condition of a machined surface of a tool. [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 a grinding wheel serving as a grinding tool. Conventionally, Patent Document 1 proposes a measuring device that measures the condition of a grinding surface of a grinding wheel (specifically, the amount of protrusion of abrasive grains) in order to grasp the condition of the grinding surface. In this device, 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.

[0003] A machined surface condition estimation device that estimates the condition of the grinding surface of a grinding wheel using a machine learning model has also been proposed. In this device, a learning device is first trained by machine learning using images of the grinding surface captured by a camera as learning data. When estimating the condition of the grinding surface, the grinding surface of the grinding wheel to be estimated is imaged, and output data is obtained from the trained learning device using the captured images as input data. In the above device, the condition of the grinding surface of the grinding wheel to be estimated is estimated based on this output data. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] JP 2004-45078 A Summary of the Invention [Problem to be solved by the invention]

[0005] Grindstones are available in a variety of sizes and materials. In order to estimate the grinding surface condition of such a wide variety of grindstones, it is possible to prepare a learning machine that has been trained on each of these grindstones separately.

[0006] Here, the task of training the learning device to learn so that the trained learning device becomes appropriate is a cumbersome task. Therefore, when estimating the grinding surface condition for all types of grinding wheels, the task of training the learning device to learn by machine learning, which is already a cumbersome task, must be performed for each type of grinding wheel, which takes a lot of time and effort. The above-mentioned machined surface condition estimation device has problems in this respect.

[0007] Incidentally, such problems can similarly arise when estimating the condition of the machining surface of a tool having a structure in which abrasive grains are fixed, such as when estimating the condition of the machining surface of a wire tool used in machining with a wire saw. [Means for solving the problem]

[0008] A machined surface condition estimating device for solving the above problem is a machined surface condition estimating device that estimates the state of a machined surface of a tool having a structure in which abrasive grains are fixed, and includes: a trained learning device that has been machine-learned using an image of the machined surface of a tool having abrasive grains of a predetermined particle diameter as learning data; a memory unit that stores an estimated image that is an image of the machined surface of the tool to be estimated, and particle diameter information related to the particle diameter of the tool to be estimated; a resizing unit that changes the image size of the estimated image by a change ratio expressed by the formula "G1 / G2" where the predetermined particle diameter is "G1" and the particle diameter in the particle diameter information is "G2"; and an output unit that uses the estimated image whose image size has been changed by the resizing unit to output machined surface information indicating the state of the machined surface of the tool to be estimated from the trained learning device.

[0009] The estimation program for solving the above problem is an estimation program that causes an electronic control device provided in the machining surface condition estimation device to execute the processing of the memory unit, the processing of the resizing unit, and the processing of the output unit provided in the machining surface condition estimation device.

[0010] A machining surface condition estimation method for solving the above problem is a machining surface condition estimation method for estimating the condition of a machining surface of a tool having a structure in which abrasive grains are fixed, and includes: a trained learning device that has been machine-learned using an image of the machining surface of a tool having abrasive grains of a predetermined particle diameter as learning data; a storage process that stores an estimated image that is an image of the machining surface of the tool to be estimated, and particle diameter information related to the particle diameter of the tool to be estimated; a resizing process that changes the image size of the estimated image by a change ratio expressed by the formula "G1 / G2" where the predetermined particle diameter is "G1" and the particle diameter in the particle diameter information is "G2"; and an output process that uses the estimated image whose image size has been changed in the resizing process to output machining surface information indicating the condition of the machining surface of the tool to be estimated from the trained learning device.

[0011] Even if the materials and sizes (external size, grain size, etc.) of the various parts of the tools are different, the basic structures of the machining surfaces of these tools are similar. In the above configuration, a learning device shared by multiple types of tools with different sizes and materials, specifically a learning device corresponding to a tool having abrasive grains of a predetermined grain size, is stored as a trained learning device. Then, when estimating the state of the machining surface, the image size of the estimated image of the machining surface of the tool to be estimated is changed (enlarged or reduced) to a size corresponding to the shared learning device, specifically a size that matches the predetermined grain size, which is the grain size of the abrasive grains in the training data, and then used for the estimation.

[0012] According to the above configuration, even when estimating the machined surface condition of a plurality of types of tools, the estimation can be performed using a common learning device without preparing a trained learning device for each type of tool. Therefore, it is possible to reduce the time and labor required for setting up a trained learning device. Effect of the Invention

[0013] According to the present invention, it is possible to reduce the time and effort required for setting up a trained learning device. [Brief description of the drawings]

[0014] [Figure 1] 1 is a schematic diagram showing a schematic configuration of an automatic grinding device to which a machined surface state estimating device according to an embodiment is applied; [Diagram 2] 1 is a block diagram showing a schematic configuration of a machined surface state estimating device; [Diagram 3] 2 is a schematic diagram showing the structure of a camera unit. [Figure 4] 1 is a schematic diagram showing how an imaging target area of ​​the grinding surface is illuminated by an illumination unit. [Diagram 5] 1 is a schematic diagram conceptually showing the data structure of learning data of a first learning device. [Figure 6] FIG. 13 is a diagram showing an example of learning data corresponding to an evenly abrasive-fell surface; [Figure 7] FIG. 13 is a diagram showing an example of learning data corresponding to an unbalanced abrasive surface; [Figure 8] FIG. 13 is a diagram showing an example of learning data corresponding to a chip welding grinding surface. [Figure 9] 10 is a flowchart showing a procedure for generating a determination image. [Figure 10] 13 is a flowchart showing a procedure for executing a determination process. [Figure 11] 5 is an operational diagram for explaining the operation of the machined surface state estimating device. FIG. [Figure 12] 13 is a flowchart showing an execution procedure of a determination process according to another embodiment. [Figure 13] 13 is a graph showing the relationship between the rotational phase of the grindstone and the integrated value when deterioration of the grindstone progresses. [Figure 14] 13 is a flowchart showing an execution procedure of a determination process according to another embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0015] Hereinafter, an embodiment of a machined surface condition estimating device, an estimating program, and a machined surface condition estimating method will be described with reference to FIGS. <Automatic grinding device> As shown in FIG. 1, the machined surface condition estimation device 30 of this embodiment is applied to an automatic grinding device 20. This automatic grinding device 20 is a numerically controlled (NC) type surface grinding device that grinds the surface of a workpiece (not shown) using a grinding wheel 21 as a tool. 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 by a binder. The grinding wheel 21 is supported by a grinding wheel support part 22 in a rotatable state. The grinding wheel 21 and the grinding wheel support part 22 are movable relative to a base 23 in the vertical direction (hereinafter, Y direction) and the horizontal direction, specifically, the depth direction in FIG. 1 (hereinafter, Z direction). In the automatic grinding device 20, the grinding wheel 21 is brought into contact with the workpiece while being rotationally driven, thereby grinding the surface of the workpiece.

[0016] 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 makes it possible to change the relative positions of the grinding wheel 21 and the workpiece in the X direction.

[0017] 1 and 2, the automatic grinding device 20 has an operation control unit 25 that controls the operation of the automatic grinding device 20. 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.

[0018] The automatic grinding device 20 can change the relative positions of the grindstone 21 and the workpiece in the X direction, the Y direction, and the Z direction, respectively, by moving the grindstone 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 has a ball screw mechanism, a servo motor, and the like, which are not shown. The X-direction position of the table 24 relative to the base 23 is controlled through the operation control of the X-axis drive unit 26. The Y-axis drive unit 27 is a device for moving the grindstone 21 and the grindstone support unit 22 in the Y direction relative to the base 23. The Y-axis drive unit 27 has a ball screw mechanism, a servo motor, and the like, which are not shown. The Y-direction position of the grindstone 21 relative to the base 23 is controlled through the operation control of the Y-axis drive unit 27. The Z-axis drive unit 28 is a device for moving the grindstone 21 and the grindstone 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 Z-direction position of the grindstone 21 with respect to the base 23 is controlled.

[0019] The grindstone driving unit 29 has an electric motor connected to the rotation shaft of the grindstone 21, a rotation phase sensor that detects the rotation phase of the grindstone 21, and the like. In the operation control of the grindstone driving unit 29 (more specifically, the electric motor), the grindstone 21 is basically rotated at a constant speed. The rotation speed of the grindstone 21 is set based on the processing conditions input to the automatic grinding device 20 and is set to a speed that matches the processing conditions.

[0020] <Machine surface condition estimation device> The machined surface condition estimation device 30 of this embodiment is a device that estimates the state of the grinding surface 211 of the grinding wheel 21 to be estimated, using a captured image 44 obtained by capturing an image of the machined surface (hereinafter, grinding surface 211) of the grinding wheel 21 to be estimated, and trained learning devices 61, 62. Furthermore, the machined surface condition estimation device 30 of this embodiment determines the occurrence of a deterioration abnormality in the grinding wheel 21 to be estimated, based on the estimated state of the grinding surface 211.

[0021] <Camera unit> 1 to 3, the machined surface condition estimating device 30 has a camera unit 40. The camera unit 40 captures an image of the grinding surface 211 of the grindstone 21. The camera unit 40 has a camera 41 as an imaging section, and an illumination section 43.

[0022] <Camera> As shown in FIG. 1 and FIG. 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 (specifically, the tangent plane of the grinding surface 211 shown by the dashed line in FIG. 3). In this embodiment, the camera 41 captures the image of the grinding surface 211 at a first time point immediately after the dressing of the grinding wheel 21 is performed. The captured image 44 captured at the first time point is stored in the electronic control device 50, which will be described later, as a basic image 44B. In this embodiment, the camera 41 also captures the image of the grinding surface 211 at a second time point after the first time point, specifically, at any timing during the use of the grinding wheel 21. The captured image 44 captured at the second time point is stored in the electronic control device 50 as a latest image 44N. Among the captured images 44 captured at any timing during use of the grinding wheel 21, previously captured images 44 may be stored as N (N is a natural number) previous images, for example, the captured image 44 captured immediately before may be stored as the previous image. In this embodiment, the grinding wheel 21 attached to the automatic grinding device 20 when capturing an image by the camera 41 corresponds to the tool to be estimated. Also, in this embodiment, the basic image 44B, the latest image 44N, and the Nth previous image correspond to estimated images that are images related to the machining surface of the tool to be estimated.

[0023] <Lighting Department> 3, the illumination unit 43 illuminates the lower end portion of the grinding surface 211, i.e., the area imaged by the camera 41 (hereinafter, image capture target area AR). The illumination unit 43 has a first irradiating unit 45 and a second irradiating unit .

[0024] <1st irradiation section> The first irradiation unit 45 irradiates the above-mentioned imaging target area AR of the grinding surface 211 with a first illumination light 45L having a first emission color (for example, blue) from a direction perpendicular to the grinding surface 211 (specifically, the tangent plane of the grinding surface 211 shown by the dashed line in FIG. 3). Specifically, the first irradiation unit 45 has a first lamp 451 and a reflective translucent member 452. The first lamp 451 is composed of a light-emitting diode. The first lamp 451 is disposed in such a manner that the first illumination light 45L is emitted from a direction perpendicular to the optical axis of the camera 41 toward the optical axis. The reflective translucent member 452 is disposed at a portion where the optical axis of the camera 41 and the optical axis of the first lamp 451 intersect. The reflective translucent member 452 reflects the first illumination light 45L and transmits the reflected light reflected by the grinding surface 211. In this embodiment, the first illumination light 45L emitted from the first lamp 451 is reflected by the reflective light-transmitting member 452 and travels toward the grinding surface 211, thereby irradiating the imaging target area AR on the grinding surface 211. A portion of the reflected light of the first illumination light 45L thus irradiated to the grinding surface 211 is transmitted through the reflective light-transmitting member 452 and enters the camera 41.

[0025] <Second irradiation section> The second irradiating unit 46 irradiates the imaging target area AR of the grinding surface 211 from an oblique direction with respect to the grinding surface 211 (specifically, the tangent plane of the grinding surface 211 shown by the dashed line in FIG. 3) with the second illumination light 46L having a second emission color (for example, white color) different from the first emission color. Specifically, the second irradiating unit 46 has an illumination dome 461 and a second lamp 462. The illumination dome 461 is dome-shaped with an open top, and is disposed so as to cover the lower surface of the grinding wheel 21 (specifically, the imaging target area AR). The second lamp 462 is constituted by a light-emitting diode. A plurality of the second lamps 462 are provided in a line on the inner surface of the illumination dome 461. Each second lamp 462 irradiates the imaging target area AR of the grinding surface 211 with the second illumination light 46L. The second lamp 462 includes a lamp that irradiates the second illumination light 46L onto the imaging target area AR of the grinding surface 211 from a direction along the grinding surface 211 (more specifically, the tangent plane of the grinding surface 211 shown by the dotted line in Figure 3), specifically, from a direction that forms "5 degrees" with respect to the tangent plane of the grinding surface 211.

[0026] <Action by lighting unit> In this embodiment, the camera unit 40 is detachable from the automatic grinding device 20. When estimating the state of the grinding surface 211, the camera unit 40 is attached to the automatic grinding device 20 to obtain a captured image 44 used for the estimation. In the camera unit 40, when the camera 41 captures an image of the grinding surface 211, the illumination unit 43 illuminates an imaging target area AR of the grinding surface 211. Note that in this embodiment, when grinding is performed by the automatic grinding device 20, the camera unit 40 is detached from the automatic grinding device 20.

[0027] 4, in this embodiment, the first illumination light 45L irradiated from the first irradiating unit 45 in a direction perpendicular to the grinding surface 211 can be substantially specularly reflected by the top surface of the grinding wheel 21 (including the top surfaces of the abrasive grains 212) and can be made to enter the camera 41. This allows the color of the portion corresponding to the top surface of the grinding wheel 21 in the captured image 44 captured by the camera 41 to be the first emission color (e.g., blue) of the first illumination light 45L.

[0028] On the other hand, the first illumination light 45L from the first irradiating unit 45 and the second illumination light 46L from the second irradiating unit 46 are diffusely reflected by portions of the grindstone 21 other than the top surface (specifically, the side surfaces of the abrasive grains 212, the surface of the binder, etc.). Then, a portion of the diffusely reflected first illumination light 45L and second illumination light 46L enters the camera 41. As a result, the color of the portions of the grindstone 21 other than the top surface in the captured image 44 captured by the camera 41 becomes a mixture of the first emission color of the first illumination light 45L and the second emission color of the second illumination light 46L.

[0029] According to this embodiment, since the color of the top surface of the grinding wheel 21 in the captured image 44 can be made different from the color of the portion other than the top surface, the boundary between the top surface of the grinding wheel 21 and the portion other than the top surface can be made clear. As a result, an image clearly showing the top surface of the grinding wheel 21 (including the tip portion of the abrasive grains 212), which is a portion that influences the finishing quality of the workpiece, can be obtained as the captured image 44 captured by the camera 41. Therefore, the state of the grinding surface 211 of the grinding wheel 21, specifically the tip portion of the abrasive grains 212, can be estimated with high accuracy using the captured image 44. In addition, the tip portion of the grinding surface 211 (specifically the portion where the abrasive grains 212 function as a cutting edge) can be easily extracted from the captured image 44. Therefore, an extracted image, which is an image in which the tip portion of the grinding surface 211 is extracted from the image of the grinding surface 211, can be easily generated.

[0030] The machined surface condition estimating device 30 of this embodiment includes an electronic control device 50. The electronic control device 50 executes various controls for determining the condition of the grinding surface 211 of the grinding wheel 21. The electronic control device 50 has a CPU 51 , a ROM 52 , a RAM 53 , an input unit 54 , a display unit 55 , and a storage unit 56 .

[0031] The input unit 54 is an input device such as a mouse, a keyboard, a touch panel, or a button. The input unit 54 is operated when performing various settings of the machined surface state estimation device 30 or when operating the machined surface state estimation device 30. In this embodiment, particle size information 66 (specifically, average particle size) regarding the particle size of the grinding wheel 21 to be estimated is input through the operation of the input unit 54. In this embodiment, the operation of the input unit 54 for inputting the particle size information 66 is performed when performing judgment of the grinding wheel 21 (for example, when the grinding wheel 21 to be estimated is attached to the automatic grinding device 20 or when the camera unit 40 is attached to the automatic grinding device 20). In this embodiment, the time when dressing was performed on the grinding wheel 21 to be estimated (dressing information) is input through the operation of the input unit 54.

[0032] The display unit 55 has a display device such as a liquid crystal display, an organic EL display, etc. The display unit 55 displays various information related to the judgment, such as the judgment result of the state of the grinding surface 211. The storage unit 56 is configured with a non-volatile memory that can be written to and read from at any time, such as a hard disk drive or a solid state drive. The storage unit 56 stores various execution programs 60, trained learning devices 61 and 62, and learning data 63 and 64 used for machine learning of the learning devices 61 and 62. The storage unit 56 also stores the captured image 44 captured by the camera unit 40, a judgment image 65 used to estimate the state of the grinding surface 211, particle size information 66 and dressing information input through the operation of the input unit 54.

[0033] The execution program 60 includes a program for executing machine learning by the learning devices 61 and 62, an estimation program for executing various processes related to estimating the state of the grinding surface 211, and a judgment program for executing various processes related to judging the state of the grinding surface 211.

[0034] <First learning unit> The first learning device 61 will be described. In this embodiment, a Generative Adversarial Network (GAN), specifically an image generation model called "pix2pix", is used as the first learning device 61.

[0035] The first learning device 61 is machine-learned using learning data 63. The learning data 63 is data for performing machine learning of the first learning device 61 so as to acquire the ability to generate an extracted image, which is an image obtained by extracting only the tip portion of the grinding surface 211 of the grinding wheel 21 from an image related to the grinding surface 211 of the grinding wheel 21. As shown in FIG. 5, the learning data 63 is composed of an image set in which a pre-conversion image 63B and a post-conversion image 63A form a pair. The pre-conversion image 63B is an image that is expected to be used as input data for the first learning device 61. The post-conversion image 63A is an image that is expected to become output data for the first learning device 61.

[0036] In this embodiment, the first learning device 61 is set to be common to the multiple types of grindstones 21. In this embodiment, all of the multiple types of grindstones 21 are general grindstones having general abrasive grains, and are grindstones 21 having a predetermined particle size (more specifically, the average particle size of the abrasive grains 212 corresponding to the predetermined grain size [#200]).

[0037] In this embodiment, in order to realize such a configuration, a general grinding wheel having abrasive grains 212 of a predetermined particle size is adopted as the grinding wheel 21 used to create the learning data 63. In detail, a grinding wheel 21 having a standard structure is selected from among general grinding wheels, and the selected grinding wheel 21 is used to create the learning data 63.

[0038] The learning data 63 is generated in the following manner. First, a large number of captured images of the grinding surface 211 of the grinding wheel 21 are prepared. The captured images include a first image captured at the first time and a second image captured at the second time. The first image is an image corresponding to the basic image 44B, and the second image is an image corresponding to the latest image 44N. The first image and the second image are acquired, for example, by using the camera unit 40. The first image and the second image are converted to grayscale and divided into a plurality of divided images in a manner that cuts the grinding surface 211 in a lattice shape in the circumferential direction and the rotation axis direction of the grinding wheel 21. In this embodiment, these divided images are used as the pre-conversion image 63B.

[0039] Then, for each divided image, an extracted image is created by extracting only the tip portion of the grinding surface 211 (more specifically, the portion of the grinding surface 211 that functions as a cutting edge) from the divided image. In this embodiment, these extracted images are used as the converted image 63A. The following method can be used to create the extracted image. First, the grinding surface 211 of the grinding wheel 21 before imaging is placed against an ink pad to adhere ink to the tip portion of the grinding surface 211. Then, the grinding surface 211 of the grinding wheel 21 is imaged. Then, only the colored portion to which ink is adhered is extracted from this captured image (more specifically, the divided image) to create the extracted image. According to this method, the boundary between the tip portion of the grinding surface 211 and the other portions in the captured image becomes clear, so that the tip portion of the grinding surface 211 can be easily extracted from the divided image. Therefore, the extracted image can be easily created.

[0040] Thereafter, a large number of image sets (FIG. 5) are created, each pair consisting of a pre-conversion image 63B and a post-conversion image 63A of the same location on the grinding surface 211. In this embodiment, these image sets are used as learning data 63 for the first learning device 61. In detail, the electronic control device 50 extracts one of the multiple image sets constituting the learning data 63, and performs machine learning on the first learning device 61 using the image set as input data. This learning process is repeatedly executed for each image set constituting the learning data 63. Then, the machine learning model constructed through the execution of the machine learning is stored in the storage unit 56 as the trained first learning device 61. Note that in this embodiment, the process of storing the trained first learning device 61 in the storage unit 56 corresponds to the storage process.

[0041] When an image relating to the grinding surface 211 of the grinding wheel 21, more specifically, a captured image 44 capturing the grinding surface 211, is input to the trained first learning device 61, the first learning device 61 outputs an extracted image in which only the tip portion of the grinding surface 211 is extracted from the captured image 44. In this embodiment, a judgment image 65 used to estimate the state of the grinding surface 211 is generated based on the extracted image.

[0042] The second learning device 62 will now be described. In this embodiment, as the second learning device 62, a Convolutional Neural Network (CNN) is adopted.

[0043] The second learning device 62 performs machine learning using the learning data 64. The learning data 64 is data for performing machine learning on the second learning device 62 so that the second learning device 62 acquires the ability to discriminate the state of the abrasive surface 211.

[0044] In this embodiment, the second learning unit 62 is set to be common to the multiple types of grindstones 21. In this embodiment, all of the multiple types of grindstones 21 are general grindstones having general abrasive grains, and are grindstones 21 having a predetermined grain size (specifically, the average grain size of the abrasive grains 212 corresponding to grain size #200).

[0045] In this embodiment, in order to realize such a configuration, a general grinding wheel having abrasive grains 212 of a predetermined particle diameter is adopted as the grinding wheel 21 used to create the learning data 63. More specifically, a grinding wheel 21 having a standard structure is selected from among general grinding wheels, and the selected grinding wheel 21 is used to create the learning data 63. The grinding wheel 21 used to create the learning data 63 is specified by the manufacturer (e.g., Company A), the material of the abrasive grains 212 (e.g., alumina), and the average particle diameter of the abrasive grains 212 (more specifically, the predetermined particle diameter).

[0046] The learning data 64 is basically generated in the following procedure. First, an image set is prepared, which is two captured images of the same location on the grinding surface 211 of the grinding wheel 21, the first image being captured at the first time and the second image being captured at the second time. The first image is an image corresponding to the basic image 44B, and the second image is an image corresponding to the latest image 44N. The first and second images are acquired, for example, by using the camera unit 40. The first and second images are converted to grayscale.

[0047] Thereafter, for each of the first and second grayscale images, an extracted image is created by extracting only the tip portion of the grinding surface 211 (more specifically, the portion of the grinding surface 211 that functions as a cutting edge) from the image. The extracted image can be created using the ink pad described above, using the converted image 63A that constitutes the learning data 64 for the first learning device 61, or using the first learning device 61.

[0048] Then, a difference image is generated that indicates the difference between the extracted image corresponding to the first image and the extracted image corresponding to the second image. In this embodiment, this difference image is used as learning data 64 for the second learning device 62.

[0049] In this embodiment, as the differential images constituting the learning data 64, a large number of images corresponding to three types of grinding surface 211 conditions, namely, "evenly shedding grinding surface", "unbalanced shedding grinding surface", and "chip-welded grinding surface", are prepared.

[0050] The "evenly shedding abrasive surface" is defined as the state of the grinding surface 211 when the abrasive grains 212 are evenly shedding from each part of the grinding surface 211. When generating the learning data 64 corresponding to the evenly shedding abrasive surface, a large number of image sets consisting of the first image and the second image of the grinding wheel 21 having the evenly shedding abrasive surface are prepared, and the above-mentioned difference image is generated based on this image set. In this case, as the difference image, an image showing a part where the tip part of the grinding surface 211 is reduced in the extracted image corresponding to the second image is generated based on the extracted image corresponding to the first image. Then, this difference image is used as the learning data 64 corresponding to the evenly shedding abrasive surface. As an example shown in FIG. 6, the learning data 64 corresponding to the evenly shedding abrasive surface is an image in which the region RT showing the tip part of the grinding surface 211 is evenly distributed over the entire surface of the learning data 64 (more specifically, the above-mentioned difference image).

[0051] The "unbalanced shed grinding surface" is defined as the state of the grinding surface 211 when the portions where the abrasive grains 212 have fallen off are unevenly distributed on the grinding surface 211. When generating the learning data 64 corresponding to the unbalanced shed grinding surface, a large number of image sets consisting of the first image and the second image of the grinding wheel 21 of the unbalanced shed grinding surface are prepared, and the above-mentioned difference image is generated based on this image set. In this case, as the difference image, an image showing a portion where the tip portion of the grinding surface 211 is reduced in the extracted image corresponding to the second image is generated based on the extracted image corresponding to the first image. Then, this difference image is used as the learning data 64 corresponding to the unbalanced shed grinding surface. As an example shown in FIG. 7, the learning data 64 corresponding to the unbalanced shed grinding surface is an image in which the region RT showing the tip portion of the grinding surface 211 is distributed unevenly in a part of the learning data 64 (more specifically, the above-mentioned difference image).

[0052] The "chip-welded grinding surface" is defined as the state of the grinding surface 211 when chips are welded to the grinding surface 211. When generating the learning data 64 corresponding to the chip-welded grinding surface, a large number of image sets consisting of a first image and a second image of the grinding wheel 21 with the chip-welded grinding surface are prepared, and the above-mentioned difference image is generated based on this image set. In this case, as the difference image, an image showing an increased tip portion of the grinding surface 211 in the extracted image corresponding to the second image is generated based on the extracted image corresponding to the first image. Then, this difference image is used as the learning data 64 corresponding to the chip-welded grinding surface. As shown in an example in FIG. 8, the learning data 64 corresponding to the chip-welded grinding surface is an image in which the region RT showing the tip portion of the grinding surface 211 extends over a wide range including a plurality of abrasive grains 212.

[0053] In this embodiment, a learning process in which one of the multiple images constituting the learning data 64 is extracted and the second learning device 62 is made to learn the image by machine learning using the extracted image as input data is repeatedly executed for each image constituting the learning data 64. Then, the machine learning model constructed through the execution of the machine learning is stored in the storage unit 56 as the trained second learning device 62.

[0054] An image (a judgment image 65, described later) relating to the grinding surface 211 of the grinding wheel 21 is input to the second learning device 62 that has been trained in this manner. As a result, the second learning device 62 performs so-called classification, in which the input image is classified into one of an evenly-shed grinding surface (class 1), an unbalancedly-shed grinding surface (class 2), and a chip-welded grinding surface (class 3).

[0055] In this embodiment, the second learning device 62 corresponds to a learned learning device that has undergone machine learning using images relating to the machining surface of a tool having abrasive grains with a predetermined particle diameter as learning data. The machined surface condition estimating device 30 (more specifically, the electronic control device 50) of this embodiment has an extracted image generating section 57 and a determining section 58 as functional sections.

[0056] <Extracted image generation section> The extracted image generation unit 57 uses the basic image 44B, the latest image 44N, and the trained first learning device 61 to generate an extracted image (hereinafter, judgment image 65) that is an image obtained by extracting the tip portion of the grinding surface 211 from a difference image that shows the difference between the basic image 44B and the latest image 44N.

[0057] FIG. 9 shows a procedure for generating the judgment image 65. As shown in FIG. 9, first, the camera unit 40 is attached to the automatic grinding device 20 on which the grinding wheel 21 to be estimated is provided, and the camera unit 40 and the operation control unit 25 of the automatic grinding device 20 are connected to the electronic control device 50 (step S11). Then, the electronic control device 50 controls the operation of the camera unit 40 and the operation control unit 25. In detail, illumination is performed by the illumination unit 43. As a result, the imaging target area AR on the grinding surface 211 is illuminated. In addition, the operation control of each of the driving units 26, 27, 28, and 29 of the automatic grinding device 20 is performed. As a result, the grinding wheel 21 is rotated at a speed suitable for imaging the grinding surface 211, and the relative position between the camera unit 40 and the grinding wheel 21 is changed in a predetermined pattern. Furthermore, the operation control of the camera 41 is performed based on the detection signal of the rotation phase sensor. As a result, a captured image 44 of the grinding surface 211 is acquired. In this embodiment, the grinding surface 211 is divided into a plurality of regions by dividing the grinding surface 211 into a lattice shape in the circumferential direction and the rotation axis direction of the grinding wheel 21. Then, the camera 41 captures an image of the grinding surface 211 for each of the regions. As a result, a plurality of captured images 44 are obtained. In this embodiment, an image including a large number of abrasive grains 212 is obtained as each captured image 44.

[0058] Thereafter, the electronic control unit 50 executes the processes in the following steps S12 to S18. First, based on the multiple captured images 44 acquired in the process of step S11, a resized image 44R is generated, which is an image obtained by changing the image size of the captured image 44 at a change ratio RG (step S12). Here, the predetermined particle size is set to "G1", and the average particle size in the particle size information is set to "G2". In this case, in the process of step S12, the image size of the captured image 44 is changed at the change ratio RG expressed by the formula "G1 / G2". In this embodiment, the process of step S12 corresponds to a resizing step, and the electronic control device 50 that executes the process of step S12 corresponds to a resizing unit. In this embodiment, the multiple captured images 44 acquired in the process of step S11 correspond to estimated images that are images related to the machining surface of the tool to be estimated, and the resized image 44R corresponds to an estimated image whose image size has been changed by the resizing unit.

[0059] Then, it is determined whether it is the first period immediately after dressing of the grinding wheel 21 (step S13). If it is the first period (step S13: YES), the multiple resized images 44R are stored as basic images 44B in the storage unit 56 together with position information on the grinding surface 211 (step S14). In this case, the process is temporarily terminated without executing the processes of steps S15 to S18.

[0060] On the other hand, if it is the second time period that is later than the first time period (step S13: NO), the multiple resized images 44R are stored in the storage unit 56 as the latest image 44N together with the position information on the grinding surface 211 (step S15). In this embodiment, the process of step S14 and the process of step S15 correspond to a storage step.

[0061] In this case, the multiple latest images 44N and the multiple basic images 44B are converted into grayscale separately (step S16). Thereafter, a process is executed in which the first learning device 61 outputs an extracted image (hereinafter, converted basic image) using the grayscale basic image 44B as input data (step S17). Also, a process is executed in which the first learning device 61 outputs an extracted image (hereinafter, converted latest image) using the grayscale latest image 44N as input data. In the process of step S17, in detail, a generation process is repeatedly executed for each of the multiple basic images 44B, such as extracting one of the multiple basic images 44B and causing the first learning device 61 to output a converted basic image using the basic image 44B as input data. Also, a generation process is repeatedly executed for each of the multiple latest images 44N, such as extracting one of the multiple latest images 44N and causing the first learning device 61 to output a converted latest image using the latest image 44N as input data.

[0062] Thereafter, a difference image (hereinafter, judgment image 65) showing the difference between two images (the converted basic image and the converted latest image) corresponding to the same location on the grinding surface 211 is generated (step S18). The judgment image 65 is generated for each imaging position on the grinding surface 211, i.e., for each of the aforementioned regions. Furthermore, as the judgment image 65, an image showing a portion where the tip portion of the grinding surface 211 has decreased in the converted latest image and an image showing a portion where the tip portion has increased are generated based on the converted basic image. The judgment image 65 generated in the processing of step S18 is stored in the memory unit 56. Note that in this embodiment, the processing of steps S17 and S18 correspond to the extraction image generating process.

[0063] <Judgment part> The judgment unit 58 judges the occurrence of a deterioration abnormality in the grinding wheel 21 that is the estimation target, using a plurality of judgment images 65 generated by the extraction image generation unit 57 and the second learning device 62 that has already been trained.

[0064] Here, when the grindstone 21 is used, it is desirable that the condition of the grindstone 211 of the grindstone 21 changes uniformly over the entirety of the grindstone 211. In a general grindstone having general abrasive grains, the condition of the tip of the grindstone 211 changes in such a way that the abrasive grains 212 fall off. As the grindstone 211 deteriorates, the abrasive grains 212 fall off unevenly in each part of the grindstone 211. For this reason, in a general grindstone, when the abrasive grains 212 fall off unevenly, it can be said that the condition of the grindstone 211 is changing in an undesirable way.

[0065] In this embodiment, the machined surface condition estimating device 30 is constructed on the assumption that the occurrence of deterioration abnormality in a general grinding wheel having general abrasive grains is judged. In this embodiment, when the distribution bias of the tip portion of the grinding surface 211 in the judgment image 65 is equal to or greater than a predetermined level, the occurrence of deterioration abnormality in the grinding wheel 21 to be estimated is judged.

[0066] Hereinafter, the execution procedure of the determination process for determining deterioration abnormality of the grinding wheel 21 will be described with reference to Fig. 10. Fig. 10 is a flowchart showing the execution procedure of the determination process. Note that the series of processes shown in this flowchart conceptually show the execution procedure of the determination process, and the actual process is executed by the electronic control device 50 as a process at a predetermined cycle.

[0067] 10, in this process, first, classification (so-called classification) of each judgment image 65 is executed using the plurality of judgment images 65 and the trained second learning device 62 (step S21). In detail, one of the plurality of judgment images 65 is extracted, and the judgment image 65 is used as input data to classify the judgment image 65 by the second learning device 62. This classification process is executed repeatedly for each of the plurality of judgment images 65. Note that in this embodiment, the process of step S21 corresponds to an output step, and the electronic control device 50 that executes the process of step S21 corresponds to an output unit.

[0068] Then, based on the classification result for each judgment image 65 and the position information on the grinding surface 211, the degree of distribution bias of the tip portion of the grinding surface 211 in the judgment image 65 is calculated (step S22). In the process of step S22, first, the proportion R1 of the portion classified as the evenly-shed abrasive surface (class 1) in the process of step S21 is calculated for each rotation phase of the grinding wheel 21. Here, when a predetermined number (N2) of judgment images 65 out of a plurality (N1) of judgment images 65 corresponding to the same rotation phase are classified as the evenly-shed abrasive surface (class 1), the value "N2 / N1" is calculated as the above-mentioned proportion R1. Then, as the degree of bias RR1, the difference ΔR1 (=R1max-R1min) between the maximum value R1max and the minimum value R1min of the above-mentioned proportion R1 calculated for each rotation phase is calculated.

[0069] Thereafter, it is determined whether the difference ΔR1 is equal to or greater than a predetermined value J1 (step S23). As the predetermined value J1, a value capable of properly determining the occurrence of deterioration abnormality in the grinding wheel 21 is determined in advance. In detail, a value capable of properly determining the occurrence of deterioration abnormality in the grinding wheel 21 (predetermined value J1) is obtained based on the results of various experiments and simulations performed by the inventors, and the predetermined value J1 is stored in advance in the storage unit 56.

[0070] Then, when the difference ΔR1 is less than a predetermined value J1 (step S23: NO), it is determined that the distribution bias of the tip portion of the grinding surface 211 in the determination image 65 is less than a predetermined level, and it is determined to be normal (step S24). On the other hand, when the difference ΔR1 is equal to or greater than the predetermined value J1 (step S23: YES), it is determined that the distribution bias of the tip portion of the grinding surface 211 in the determination image 65 is equal to or greater than a predetermined level, and it is determined that the grinding wheel 21 has deteriorated abnormally (step S25). In this case, it is determined that the grinding wheel 21 has deteriorated to such an extent that dressing of the grinding surface 211 is required. In this embodiment, the process of step S23 and the process of step S25 correspond to the determination process.

[0071] The effects of the machined surface state estimating device of this embodiment will be described below. As described above, in the case of the grinding wheel 21, which is a general grinding wheel, if there is a large bias in the shedding of the abrasive grains 212 at various parts of the grinding surface 211, it can be said that the condition of the grinding surface 211 has changed in an undesirable way.

[0072] In this embodiment, an image showing a portion where the tip portion of the grinding surface 211 has been reduced in the latest image 44N (more specifically, the latest converted image) is generated as the judgment image 65, based on the basic image 44B (more specifically, the converted basic image). This judgment image 65 shows the amount of change in the state of the tip portion of the grinding surface 211, which is a portion that determines the finishing quality of the workpiece, more specifically, the amount of abrasive grains that have fallen off from each portion of the grinding surface 211 during the period from the first time period to the second time period. Therefore, based on the position and size of the tip portion of the grinding surface 211 in the judgment image 65, the amount of abrasive grains that have fallen off from each portion of the grinding surface 211 can be ascertained.

[0073] Therefore, according to this embodiment, it can be seen that there is a large bias in the falling off of the abrasive grains 212 at each part of the grinding surface 211 due to the bias in the distribution of the tip parts of the grinding surface 211 in the judgment image 65. In this embodiment, in such a case (step S23 in FIG. 10: YES), it can be determined that the deterioration abnormality of the grinding wheel 21 has occurred.

[0074] Furthermore, according to this embodiment, the judgment image 65 can be generated by using two captured images 44 (basic image 44B and latest image 44N), both of which contain a large number of abrasive grains 212, and the trained first learning device 61. Therefore, the amount of abrasive grains that have fallen off at each part of the grinding surface 211 can be easily grasped in a short time compared to the case where the amount of abrasive grains that have fallen off at each part of the grinding surface 211 is grasped by analyzing the state of the grinding surface 211 for each finely divided area that contains an extremely small number of abrasive grains 212. Therefore, the occurrence of deterioration abnormality in the grinding wheel 21 can be judged in a short time.

[0075] Furthermore, according to this embodiment, by periodically executing the operation of attaching the camera unit 40, the process of generating the judgment image 65, and the judgment process, it is possible to perform grinding processing of the workpiece by the automatic grinding device 20 while checking the condition of the grinding surface 211 at an appropriate timing.

[0076] Here, even if the materials and sizes (external dimensions, particle diameter of the abrasive grains 212) of the various parts of the grindstones 21 are different, the basic structures of the grinding surfaces 211 of these grindstones 21 are similar. In this embodiment, as shown in Figure 11, a learning device shared by multiple grinding wheels 21 of different types, more specifically, a learning device corresponding to a grinding wheel 21 having abrasive grains 212 of a predetermined particle diameter G1, is stored as the trained second learning device 62.

[0077] When estimating (determining) the state of the grinding surface 211, a judgment image 65 to be used as input data for the second learning device 62 is generated based on the captured image 44 of the grinding wheel 21 to be estimated, while changing the image size by the change ratio RG. As a result, an image size corresponding to the predetermined particle diameter G1, more specifically, an image size in which the abrasive grains 212 of the predetermined particle diameter G1 are displayed, is generated as the judgment image 65.

[0078] Therefore, in this embodiment, a judgment image 65 having an image size corresponding to the predetermined particle diameter G1 is used as input data, and the judgment image 65 can be classified by the second learning device 62 corresponding to the grinding wheel 21 having the abrasive grains 212 of the predetermined particle diameter G1. As described above, according to this embodiment, even when estimating (determining) the state of the grinding surface 211 of a plurality of types of grinding wheels 21, the estimation (determination) can be performed by using a common second learning device 62 without preparing a second learning device 62 that has been trained for each type of grinding wheel 21. Therefore, it is possible to reduce the time and effort required for the task of setting the second learning device 62.

[0079] <Action and effect> According to this embodiment, the following advantageous effects can be obtained. (1) The machined surface condition estimation device 30 includes a storage unit 56, a resizing unit, and an output unit. The storage unit 56 stores a second learning device 62 that has learned using as learning data 63 an image related to the grinding surface 211 of the grinding wheel 21 having abrasive grains 212 of a predetermined particle diameter, a captured image 44 of the grinding surface 211 of the grinding wheel 21 to be estimated, and particle diameter information 66 related to the particle diameter of the grinding wheel 21 to be estimated. The resizing unit changes the image size of the captured image 44 at a change ratio RG. The output unit uses a resized image 44R, which is an image obtained by changing the image size of the captured image 44, to output machined surface information (more specifically, the classification result of the judgment image 65) indicating the state of the grinding surface 211 of the grinding wheel 21 to be estimated from the second learning device 62.

[0080] According to the present embodiment, it is possible to reduce the time and effort required for setting the trained second learning device 62. (2) The images constituting the learning data 63, 64 (pre-conversion image 63B, post-conversion image 63A, difference image) and the images used as input data for the learning devices 61, 62 (basic image 44B, judgment image 65) are converted into grayscale images.

[0081] Grindstones 21 come in a variety of colors (red, blue, gray, etc.). Therefore, if the grinding surfaces 211 of multiple types of grindstones 21 are simply imaged to obtain captured images 44, the captured images 44 will include a mixture of grinding surfaces 211 of different colors. The difference in color of the grinding surfaces 211 in the captured images 44 may be a factor in causing a decrease in the generation accuracy of the extracted image by the first learning device 61, or a factor in causing a decrease in the classification accuracy of the judgment image 65 by the second learning device 62.

[0082] According to this embodiment, images of the same color, specifically grayscale images, can be used as images constituting the learning data 63, 64 and images used as input data for the learning devices 61, 62. This makes it possible to suppress the influence of differences in color of the grinding surface 211 represented in each image, specifically, the influence on the generation accuracy of the extracted image by the first learning device 61 and the classification accuracy of the judgment image 65 by the second learning device 62. This makes it possible to suppress a decrease in the generation accuracy of the extracted image by the first learning device 61 and a decrease in the classification accuracy of the judgment image 65 by the second learning device 62.

[0083] (3) The machined surface condition estimating device 30 is constructed on the assumption that it will determine the occurrence of deterioration abnormalities in a general grinding wheel having general abrasive grains. Ordinary grinding stones have substantially the same structure for the grinding surface 211 even if they are of different sizes or materials. Therefore, the state change of the grinding surface 211 is substantially the same even if the ordinary grinding stones are of different sizes or materials. According to this embodiment, when judging such ordinary grinding stones, more specifically, a plurality of types of ordinary grinding stones having different sizes and materials, the judgment can be made by using the common learning machines 61 and 62 without preparing a learning machine for each type of grinding stone 21.

[0084] Moreover, the learning devices 61, 62 used to determine the state of the grinding surface 211 can be trained in a manner appropriate for changes in state of the grinding surface 211 of the grinding wheel 21, which is a general grinding wheel. Therefore, the first learning device 61 can output highly accurate information as information (specifically, an extracted image) indicating the state of the grinding surface of the grinding wheel 21 to be estimated. Moreover, the second learning device 62 can output highly accurate information as information (specifically, a classification result of the judgment image 65) indicating the state of the grinding surface of the grinding wheel 21 to be estimated. Therefore, the state of the grinding surface 211 of the grinding wheel 21, which is a general grinding wheel, can be estimated and determined with high accuracy.

[0085] (4) The machined surface condition estimation device 30 includes a camera 41 that captures an image of the grinding surface 211 from a direction perpendicular to the grinding surface 211, an extracted image generation unit 57 that generates a judgment image 65 based on an image 44 captured by the camera 41, and an illumination unit 43 that illuminates an imaging target area AR on the grinding surface 211. The illumination unit 43 has a first irradiation unit 45 and a second irradiation unit 46. The first irradiation unit 45 irradiates the imaging target area AR with first illumination light 45L having a first emission color from a direction perpendicular to the grinding surface 211. The second irradiation unit 46 irradiates the imaging target area AR with second illumination light 46L having a second emission color different from the first emission color from a direction along the grinding surface 211.

[0086] According to this embodiment, an image clearly showing the top surface of the grinding wheel 21, which is a part that affects the finishing quality of the workpiece, can be obtained as the captured image 44 captured by the camera 41. Therefore, the captured image 44 can be used to accurately estimate the condition of the grinding surface 211 of the grinding wheel 21, more specifically, the tip portion of the abrasive grains 212.

[0087] <Example of change> The above embodiment can be modified as follows: The above embodiment and the following modifications can be combined with each other to the extent that no technical contradiction occurs.

[0088] When generating the judgment image 65, the process of converting each of the latest images 44N and the base images 44B to grayscale (the process of step S15 in FIG. 9) can be omitted. In this case, the process of converting the first image and the second image to grayscale can be omitted when creating the learning data 63 of the first learning device 61. Also, the process of converting the first image and the second image to grayscale can be omitted when creating the learning data 64 of the second learning device 62.

[0089] When creating the learning data 63 for the first learning device 61, the procedure of dividing the first and second images into a plurality of divided images can be omitted. In this case, a large number of image sets, each pair consisting of a captured image 44 of the grinding surface 211 and an extracted image obtained by extracting the tip portion of the grinding surface 211 from the captured image 44, may be prepared, and these image sets may be used as the learning data 63. As in the machined surface condition estimating device 30 of the above embodiment, by dividing the first and second images into a plurality of divided images and using them to create the learning data 63, it becomes possible to create the learning data 63 using an electronic control device 50 with a relatively low processing capacity.

[0090] The manner in which the judgment process (see FIG. 10) is executed can be changed arbitrarily, so long as it is possible to judge that a deterioration abnormality has occurred in the grinding wheel 21 being estimated when the distribution bias of the tip portion of the grinding surface 211 in the judgment image 65 is at or above a predetermined level.

[0091] The determination process can be executed, for example, as the following determination process A, determination process B, and determination process C. <Determination process A> The determination process A can be executed as follows when the grindstone 21 to be estimated is a general grindstone.

[0092] 12, in the judgment process A, first, a plurality of converted judgment images are generated by converting each of the plurality of judgment images 65 into a bitmap image (step S31). Note that in the process of step S31, an image showing a portion where the tip portion of the grinding surface 211 has been reduced in the latest post-conversion image based on the post-conversion basic image is used as the judgment image 65.

[0093] Thereafter, an integrated value PP2 is calculated by integrating the number of pixels (hereinafter, specific pixels) indicating the tip portion of the grinding surface 211 for each rotation phase of the grinding wheel 21 based on the multiple conversion determination images (step S32).

[0094] Then, based on the integrated value PP2 calculated for each rotation phase, a degree of bias in distribution of the tip portions of the grinding surface 211 in the conversion determination image (more specifically, a single image showing the entire grinding surface 211 made up of a plurality of conversion determination images) is calculated (step S33). In the process of step S33, the difference ΔPP2 (=PP2max-PP2ave) between the average value PP2ave and the maximum value PP2max of the integrated value PP2 calculated for each rotation phase is calculated as the degree of bias RR2.

[0095] Thereafter, it is determined whether the difference ΔPP2 is equal to or greater than a predetermined value J2 (step S34). As the predetermined value J2, a value capable of properly determining the occurrence of deterioration abnormality in the grinding wheel 21 is set in advance. In detail, a value (predetermined value J2) capable of properly determining the occurrence of deterioration abnormality in the grinding wheel 21 is obtained based on the results of various experiments and simulations performed by the inventors, and the predetermined value J2 is stored in advance in the storage unit 56.

[0096] If the difference ΔPP2 is less than a predetermined value J2 (step S34: NO), it is determined that the distribution bias of the tip portion of the grinding surface 211 in the conversion assessment image is less than a predetermined level, and a normal determination is made (step S35). On the other hand, if the difference ΔPP2 is equal to or greater than the predetermined value J2 (step S34: YES), it is determined that the distribution bias of the tip portion of the grinding surface 211 in the conversion assessment image is equal to or greater than a predetermined level, and a deterioration abnormality has occurred in the grinding wheel 21 (step S36). In the above configuration, the processes of steps S34 and S36 correspond to the determination process.

[0097] In the above configuration, when the abrasive grains 212 fall off the grindstone 21, this fact appears in the display of the pixel (the specific pixel) in the conversion determination image that corresponds to the part where the abrasive grains 212 have fallen off. Therefore, it is possible to grasp the state in which the abrasive grains 212 have fallen off in each part of the grinding surface 211 based on the position and range of the specific pixel in the conversion determination image.

[0098] In the above configuration, as deterioration of the grindstone 21 progresses, the distribution of the portions (i.e., specific pixels) where the abrasive grains 212 have fallen off across the entire grinding surface 211 becomes more biased. In this case, the variation in the integrated value PP2 calculated for each rotation phase becomes larger, as shown in an example in Fig. 13. In Fig. 13, the solid line indicates the integrated value PP2, and the dashed line indicates the average value PP2ave of the integrated value PP2.

[0099] According to the above configuration, it can be seen that the difference ΔPP2 between the average value PP2ave and the maximum value PP2max of the integrated value PP2 is large, which indicates that the amount of the abrasive grains 212 that have fallen off is largely biased at the tip portion of the grinding surface 211. In the above configuration, in such a case (step S34 in FIG. 12: YES), it can be determined that the grindstone 21 has deteriorated abnormally.

[0100] In the above configuration, the first learning device 61 corresponds to a learned learning device that has undergone machine learning using an image of a machining surface of a tool having abrasive grains of a predetermined particle size as learning data. Also, in the above configuration, the extracted image output from the first learning device 61 corresponds to machining surface information that indicates the state of the machining surface of the tool to be estimated.

[0101] <Determination process B> Judgment process B can be executed as follows when grinding wheel 21 to be estimated is a superabrasive grinding wheel having superabrasive grains. Judgment process B is constructed assuming that occurrence of deterioration abnormality in a superabrasive grinding wheel having superabrasive grains is judged.

[0102] 14, in the judgment process B, first, classification of each judgment image 65 is executed using the multiple judgment images 65 and the trained second learning device 62 (step S41). In detail, one of the multiple judgment images 65 is extracted, and the judgment image 65 is used as input data to classify the judgment image 65 by the second learning device 62. This classification process is executed repeatedly for each of the multiple judgment images 65.

[0103] Then, based on the classification result for each judgment image 65 and the position information on the grinding surface 211, the degree of distribution bias of the tip portion of the grinding surface 211 in the judgment image 65 is calculated (step S42). In the process of step S42, first, the ratio R3 of the portion classified as the chip-welded grinding surface (class 3) in the process of step S41 is calculated for each rotation phase of the grindstone 21. Here, when a predetermined number (N4) of judgment images 65 out of a plurality (N3) of judgment images 65 corresponding to the same rotation phase are classified as the chip-welded grinding surface (class 3), the value "N4 / N3" is calculated as the ratio R3. Then, the difference ΔR3 (=R3max-R3min) between the maximum value R3max and the minimum value R3min of the ratio R3 calculated for each rotation phase is calculated as the degree of bias.

[0104] Thereafter, it is determined whether the difference ΔR3 is equal to or greater than a predetermined value J3 (step S43). As the predetermined value J3, a value capable of properly determining the occurrence of deterioration abnormality in the grinding wheel 21 is set in advance. In detail, a value capable of properly determining the occurrence of deterioration abnormality in the grinding wheel 21 (predetermined value J3) is obtained based on the results of various experiments and simulations performed by the inventors, and the predetermined value J3 is stored in advance in the storage unit 56.

[0105] Then, when the difference ΔR3 is less than a predetermined value J3 (step S43: NO), it is determined that the distribution bias of the tip portion of the grinding surface 211 in the determination image 65 is less than a predetermined level, and it is determined to be normal (step S44). On the other hand, when the difference ΔR3 is equal to or greater than the predetermined value J3 (step S43: YES), it is determined that the distribution bias of the tip portion of the grinding surface 211 in the determination image 65 is equal to or greater than a predetermined level, and it is determined that the deterioration abnormality of the grinding wheel 21 has occurred (step S45). In this case, it is determined that the grinding wheel 21 has deteriorated to such an extent that dressing of the grinding surface 211 is required. In the above configuration, the process of step S43 and the process of step S45 correspond to the determination process.

[0106] In the case of an ultra-abrasive grinding wheel, the condition of the tip of the grinding surface 211 changes in such a way that foreign matter such as cutting powder adheres to the grinding surface 211. For this reason, when the degree of adhesion of foreign matter to each part of the grinding surface 211 is uneven, it can be said that the condition of the grinding surface 211 is changing in an undesirable way.

[0107] In the above configuration, the amount of foreign matter adhering to each part of the grinding surface 211 during the period from the first time to the second time appears in the judgment image 65 (more specifically, an image showing an increased portion of the tip part of the grinding surface 211 in the latest converted image with the converted basic image as a reference). Therefore, the amount of foreign matter adhering to each part of the grinding surface 211 can be grasped from the position and size of the tip part of the grinding surface 211 in the judgment image 65. Therefore, according to the above configuration, it is understood that the deviation in the distribution of the tip parts of the grinding surface 211 in the judgment image 65 is large, and therefore the deviation in the adhesion of foreign matter is large at the tip part of the grinding surface 211. In this embodiment, in such a case (step S43 in FIG. 14: YES), it can be determined that deterioration abnormality has occurred in the grinding wheel 21.

[0108] <Decision process C> Judgment process C can be executed as follows when grinding wheel 21 to be estimated is a superabrasive grinding wheel having superabrasive grains. Judgment process C is constructed assuming that occurrence of deterioration abnormality in a superabrasive grinding wheel having superabrasive grains is judged.

[0109] In the judgment process C, first, a plurality of converted judgment images are created by converting each of the judgment images 65 into a bitmap image. In this example, an image showing an increased portion of the tip of the grinding surface 211 in the latest image after conversion based on the converted base image is used as the judgment image 65.

[0110] Thereafter, an integrated value PP4 is calculated by integrating the number of pixels indicating the tip portion of the grinding surface 211 (hereinafter, specific pixels) for each rotation phase of the grindstone 21 based on the multiple conversion determination images. Then, based on the integrated value PP4 calculated for each rotation phase, a degree of bias in distribution of the tip portions of the grinding surface 211 in the conversion determination image (more specifically, a single image showing the entire grinding surface 211 made up of a plurality of conversion determination images) is calculated. In this process, the difference ΔPP4 (=PP4max-PP4ave) between the average value PP4ave and the maximum value PP4max of the integrated value PP4 calculated for each rotation phase is calculated as the degree of bias RR4.

[0111] Thereafter, it is determined whether the difference ΔPP4 is equal to or greater than a predetermined value J4. As the predetermined value J4, a value capable of properly determining the occurrence of deterioration abnormality in the grinding wheel 21 is set in advance. In detail, a value capable of properly determining the occurrence of deterioration abnormality in the grinding wheel 21 (predetermined value J4) is obtained based on the results of various experiments and simulations performed by the inventors, and the predetermined value J4 is stored in advance in the storage unit 56.

[0112] If the difference ΔPP4 is less than a predetermined value J4, it is determined that the distribution bias of the tip portions of the grinding surface 211 in the conversion assessment image is less than a predetermined level, and it is determined to be normal. On the other hand, if the difference ΔPP4 is equal to or greater than the predetermined value J4, it is determined that the distribution bias of the tip portions of the grinding surface 211 in the conversion assessment image is equal to or greater than a predetermined level, and it is determined that the grinding wheel 21 has deteriorated abnormally.

[0113] In the above configuration, if a foreign substance adheres to the grinding surface 211, this fact will appear in the display of a pixel (the specific pixel) in the conversion determination image that corresponds to the part where the foreign substance adheres. Therefore, the state of adhesion of the foreign substance to each part of the grinding surface 211 can be grasped based on the position and range of the specific pixel in the conversion determination image.

[0114] In the above configuration, as deterioration of the grindstone 21 progresses, the distribution of foreign matter adhering portions (i.e., specific pixels) becomes more uneven across the entire grinding surface 211. In this case, the variation in the integrated value PP4 calculated for each rotation phase becomes larger.

[0115] According to the above configuration, it is understood that the difference ΔPP4 between the average value PP4ave and the maximum value PP4max of the integrated value PP4 is large, and this indicates that the deviation in the amount of foreign matter adhesion is large at the tip portion of the grinding surface 211. In such a case, the above configuration makes it possible to determine that the grinding wheel 21 has deteriorated abnormally.

[0116] In the above configuration, the first learning device 61 corresponds to a learned learning device that has undergone machine learning using an image of a machining surface of a tool having abrasive grains of a predetermined particle size as learning data. Also, in the above configuration, the extracted image output from the first learning device 61 corresponds to machining surface information that indicates the state of the machining surface of the tool to be estimated.

[0117] The determination process may be performed by using the determination image 65 as input data and outputting the classification result from the second learning device 62, or may be performed by using the captured image 44 whose image size has been changed by the change ratio RG as input data and outputting the classification result from the second learning device 62. In this case, the learning data 63 and the first learning device 61 can be omitted. The information output from the second learning device 62 is not limited to the classification result, and any information can be used as long as it is grinding surface information indicating the state of the grinding surface 211 of the grinding wheel 21 to be estimated. As such grinding surface information, for example, information indicating that the grinding surface 211 of the grinding wheel 21 to be estimated is in a good state, or a value indicating the degree of deterioration of the grinding surface 211 of the grinding wheel 21 to be estimated, can be used.

[0118] As a judgment process, a process of judging the state of the grinding surface 211 using a fractal analysis method can be executed. As the particle diameter information on the particle diameter of the grinding wheel 21 to be estimated, in addition to the "average particle diameter", the "grain size of the abrasive grains 212" or the "manufacturer and model of the grinding wheel 21" can be adopted. In short, any information that can identify the "particle diameter of the grinding wheel 21" can be adopted as the particle diameter information 66. In this configuration, the relationship between the particle diameter information 66 and the particle diameter of the abrasive grains 212 may be stored in advance in the storage unit 56. Then, the "particle diameter of the grinding wheel 21" is identified from the above relationship based on the particle diameter information 66, and the identified particle diameter is used in the process of generating the resized image 44R (step S12 in FIG. 9).

[0119] The procedure for generating the judgment image 65 can be as follows. First, a difference image showing the difference between the base image 44B and the latest image 44N is generated. Then, the difference image is converted to grayscale. Then, an extracted image is generated by using the grayscale difference image and a trained learning device that has been trained to output an extracted image in which the tip portion of the grinding surface 211 is extracted from the difference image. Then, a resized image is generated by changing the image size of the extracted image by a change ratio RG. This resized image is used as the judgment image 65.

[0120] The following method can be used to create the learning data 64 for the second learning device 62. First, a difference image showing the difference between the first image and the second image is generated. Then, the difference image is converted to grayscale. Then, an extracted image is generated by extracting the tip portion of the grinding surface 211 from the difference image using the grayscale difference image and a trained learning device that has been trained to output the extracted image. This extracted image is used as the learning data 64 for the second learning device 62.

[0121] As the difference image constituting the judgment image 65, a difference image showing the difference between the converted basic image and the converted latest image can be used, or a difference image showing the difference between the converted latest image and an extracted image corresponding to the Nth previous image (for example, the image one time ago) can be used. In the above configuration, the timing when the grinding surface 211 was imaged N times ago corresponds to the first period, and the Nth previous image corresponds to the first captured image.

[0122] According to the above configuration, it is understood that there is a large bias in the amount of change in the state of the tip portion of the grinding surface 211 from the first period to the second period, because there is a bias in the distribution of the tip portion of the grinding surface 211 in the judgment image 65. In such a case, the above configuration makes it possible to judge that the grinding wheel 21 has deteriorated abnormally.

[0123] A first learning device 61 may be prepared for each type of grinding wheel 21 to be estimated. The structure of the lighting unit 43 can be changed as desired. For example, instead of irradiating a part of the second lamp 462 with the second illumination light 46L from a direction that forms "5 degrees" with respect to the grinding surface 211, the second lamp 462 may be irradiated with the second illumination light 46L from a direction that forms "10 degrees" with respect to the grinding surface 211. Alternatively, the second lamp 462 may be irradiated with the second illumination light 46L from a direction that forms "0 degrees" with respect to the grinding surface 211, that is, from a direction parallel to the tangent plane of the grinding surface 211. In order to clarify the boundary between the top surface of the grinding wheel 21 and the portion other than the top surface in the captured image 44, it is preferable that the angle between the optical axis of the part of the second lamp 462 and the tangent plane in the imaging target area AR of the grinding surface 211 is set to a predetermined angle range (0 degrees≦angle≦10 degrees).

[0124] The second irradiating section 46 may be configured solely by the second lamp 462 that irradiates the imaging target area AR of the grinding surface 211 with the second illumination light 46L from a direction along the grinding surface 211. The second irradiating section 46 can be configured solely by a second lamp 462 that irradiates the imaging target area AR of the grinding surface 211 with the second illumination light 46L from a direction parallel to the tangent plane of the grinding surface 211.

[0125] One of the first irradiating section 45 and the second irradiating section 46 may be omitted. The first emission color of the first illumination light 45L in the first irradiating unit 45 and the second emission color of the second illumination light 46L in the second irradiating unit 46 can be changed arbitrarily. In order to clarify the boundary between the top surface of the grinding wheel 21 and a portion other than the top surface in the captured image 44, it is preferable to determine colors different from the first emission color and the second emission color.

[0126] The camera unit 40 may be disposed to the side of the grindstone 21 or above the grindstone 21. In this case, the camera 41 may be disposed so as to capture an image of the grindstone 211 from a direction perpendicular to the grindstone 211. The illumination unit 43 may be disposed so as to illuminate the side or upper end of the grindstone 211, i.e., the area imaged by the camera 41.

[0127] The camera unit 40 may be provided integrally with the automatic grinding device 20 in a non-detachable manner. According to this configuration, the operation of capturing an image of the grinding surface 211 and the operation of storing the captured image 44 in the electronic control device 50 can be easily performed without attaching or detaching the camera unit 40 to the automatic grinding device 20, while the grinding wheel 21 is attached to the automatic grinding device 20. In addition, it is possible to execute a series of combined automatic controls, including control for estimating and determining the state of the grinding surface 211, control for grinding the workpiece by the automatic grinding device 20, and control for dressing the grinding wheel 21 by the automatic grinding device 20. Therefore, by periodically executing the process for generating the determination image 65 and the determination process, the state of the grinding surface 211 can be checked at an appropriate timing while grinding the workpiece by the automatic grinding device 20 and dressing the grinding wheel 21.

[0128] When the above-mentioned configuration is adopted, it is preferable to provide a shutter section that opens and closes the space between the camera unit 40 and the grindstone 21. According to this configuration, when performing grinding processing by the automatic grinding device 20, the shutter section can be closed to create a closed state in which the space between the camera unit 40 and the grindstone 21 is partitioned. This makes it possible to prevent foreign matter (such as cutting chips and oil) from adhering to the camera unit 40. On the other hand, when capturing an image of the grinding surface 211 by the camera unit 40, the shutter section can be opened to create an open state in which the space between the camera unit 40 and the grindstone 21 is not partitioned. This makes it possible to capture an image of the grinding surface 211 by the camera unit 40.

[0129] The task of storing the learned learning devices 61, 62 in the electronic control device 50 can be performed in any manner, such as the following (task A) to (task C). (Task A) Using the automatic grinding device 20 on which the grinding wheel 21 to be estimated is mounted, learning data 63, 64 are acquired, and the learning devices 61, 62 are trained by machine learning using the learning data 63, 64.

[0130] (Work B) The learning data 63, 64 corresponding to the grinding wheel 21 that is actually used is provided by the manufacturer of the automatic grinding device 20 or the manufacturer of the grinding wheel 21. The learning data 63, 64 is then stored in the electronic control device 50 of the machined surface condition estimation device 30 used by the user, thereby allowing the learners 61, 62 to perform machine learning.

[0131] (Operation C) When manufacturing the machined surface condition estimating device 30, the trained learning devices 61, 62 are stored in the electronic control device 50. The first learning device 61 may be a type of generative adversarial network other than "pix2pix", such as "cycleGAN" or "CGAN". Also, the first learning device 61 may be an image generation model other than a generative adversarial network (GAN), such as a variational autoencoder (VAE). In short, any image generation model that can generate an extracted image, which is an image in which only the tip portion of the grinding surface 211 of the grinding wheel 21 is extracted from an image related to the grinding surface 211, may be used as the first learning device 61.

[0132] An object detection model called YOLO (You Only Look Once) can be used as the second learning device 62. In addition, a general forward propagation type neural network having a multi-layer structure, a support vector machine, or the like can be used as the second learning device 62. In short, any object detection model that can determine (estimate) the state of the grinding surface 211 can be used as the second learning device 62.

[0133] The machined surface condition estimating device, the estimation program, and the machined surface condition estimating method according to the above-described embodiments can also be applied to a grinding wheel having a structure in which a large number of abrasive grains are fixed to the bottom surface of a cylindrical base material by a binder.

[0134] The machined surface condition estimating device, the estimation program, and the machined surface condition estimating method according to the above-described embodiments can be applied to a grinding wheel, as well as to any other tool having a structure in which abrasive grains are fixed, such as a wire tool in a wire saw.

[0135] <Additional Notes> The above embodiment includes the configurations described in the following supplementary notes. [Appendix 1] A machined surface condition estimation device that estimates the condition of a machined surface of a tool having a structure in which abrasive grains are fixed, comprising: a trained learning device that has been machine-learned using an image of a machined surface of a tool having abrasive grains of a predetermined particle diameter as learning data; a memory unit that stores an estimated image that is an image of the machined surface of the tool to be estimated, and particle diameter information regarding the particle diameter of the tool to be estimated; a resizing unit that changes the image size of the estimated image by a change ratio expressed by the formula "G1 / G2", where "G1" is the predetermined particle diameter and "G2" is the particle diameter in the particle diameter information; and an output unit that uses the estimated image whose image size has been changed by the resizing unit to output machined surface information indicating the condition of the machined surface of the tool to be estimated from the trained learning device.

[0136] [Appendix 2] The machined surface condition estimating device according to [Appendix 1], wherein the images constituting the learning data and the estimated image are grayscale images. [Appendix 3] The machined surface condition estimating device according to [Appendix 1] or [Appendix 2], wherein the tool is a grinding wheel for grinding.

[0137] [Appendix 4] The machined surface condition estimating device according to [Appendix 3], wherein the grindstone is a general grindstone having a structure in which general abrasive grains are fixed. [Appendix 5] The machined surface condition estimating device according to [Appendix 3], wherein the grindstone is a superabrasive grindstone having a structure in which superabrasive grains are fixed.

[0138] [Appendix 6] The machining surface state estimating device includes an imaging unit that images the machining surface from a direction perpendicular to the machining surface, and an illumination unit that illuminates an area on the machining surface to be imaged by the imaging unit, wherein the illumination unit includes a first irradiation unit that irradiates the imaging target area with a first illumination light having a first emission color from a direction perpendicular to the machining surface, and a second irradiation unit that irradiates the imaging target area with a second illumination light having a second emission color different from the first emission color from a direction along the machining surface. The machining surface state estimating device described in any one of [Appendix 1] to [Appendix 5].

[0139] [Appendix 7] [Appendix 1] to [Appendix 6]. An estimation program that causes an electronic control device provided in the machining surface state estimating device to execute the processing of the memory unit, the processing of the resizing unit, and the processing of the output unit provided in the machining surface state estimating device.

[0140] [Appendix 8] A machined surface condition estimation method for estimating the condition of a machined surface of a tool having a structure in which abrasive grains are fixed, comprising: a trained learning device that has been machine-learned using an image of a machined surface of a tool having abrasive grains of a predetermined particle diameter as learning data; a storage step that stores an estimated image that is an image of the machined surface of the tool to be estimated, and particle diameter information regarding the particle diameter of the tool to be estimated; a resizing step that changes the image size of the estimated image by a change ratio represented by the formula "G1 / G2" where the predetermined particle diameter is "G1" and the particle diameter in the particle diameter information is "G2"; and an output step that uses the estimated image whose image size has been changed in the resizing step to output machined surface information indicating the condition of the machined surface of the tool to be estimated from the trained learning device. [Explanation of symbols]

[0141] 20...Automatic grinding device 21...Whetstone 211...Abrasive surface 212…Abrasive grain 22...Whetstone 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... Machined surface condition estimation device 40…Camera unit 41...Camera 43…Lighting section 44…Image 44R…Resized image 44B...Basic image 44N...Latest images 45...First irradiation section 451…First ramp 452...Reflective translucent member 45L…First lighting 46…Second irradiation section 461…Lighting dome 462…2nd Ramp 46L…Second illumination light 50...Electronic control device 51…CPU 52...ROM 53…RAM 54...Input section 55...Display section 56...Storage section 57...Extracted image generating unit 58…Judgment section 60...Executing program 61…First learning unit 62…Second learning unit 63…Learning data 63B…Image before conversion 63A…Converted image 64…Learning data 65...Judgment image 66…Particle size information

Claims

1. A machined surface condition estimation device that estimates a condition of a machined surface of a tool having a structure in which abrasive grains are fixed, comprising: a memory unit that stores an estimated image, which is an image of the machining surface of a tool having abrasive grains of a predetermined particle diameter, and particle diameter information regarding the particle diameter of the tool to be estimated; a resizing unit that changes an image size of the estimated image at a change ratio expressed by a formula "G1 / G2" where the predetermined particle size is "G1" and the particle size in the particle size information is "G2"; and an output unit that uses the estimated image whose image size has been changed by the resizing unit to output, from the trained learning device, machining surface information indicating the state of the machining surface of the tool to be estimated.

2. The images constituting the learning data and the estimated image are grayscale images. The machined surface state estimating device according to claim 1 .

3. The tool is a grinding wheel. The machined surface state estimating device according to claim 1 or 2.

4. The grinding wheel is a general grinding wheel having a structure in which general abrasive grains are fixed. The machined surface state estimating device according to claim 3 .

5. The grinding wheel is a superabrasive grinding wheel having a structure in which superabrasive grains are fixed. The machined surface state estimating device according to claim 3 .

6. The machined surface state estimating device comprises: an imaging unit that images the processed surface from a direction perpendicular to the processed surface; an illumination unit that illuminates an area to be imaged by the imaging unit on the processing surface, The illumination unit includes a first irradiation unit that irradiates the imaging target area with a first illumination light having a first emission color from a direction perpendicular to the processing surface, and a second irradiation unit that irradiates the imaging target area with a second illumination light having a second emission color different from the first emission color from a direction along the processing surface. The machined surface state estimating device according to claim 1 or 2.

7. 3. An estimation program that causes an electronic control device provided in the machined surface condition estimating device to execute the processing of the memory unit, the processing of the resizing unit, and the processing of the output unit provided in the machined surface condition estimating device according to claim 1 or 2.

8. A method for estimating a state of a machined surface of a tool having a structure in which abrasive grains are fixed, comprising: a storage step for storing a trained learning device that has been machine-learned using an image of a machining surface of a tool having abrasive grains of a predetermined grain size as training data, an estimated image that is an image of a machining surface of a tool to be estimated, and particle size information regarding the grain size of the tool to be estimated; a resizing step of changing an image size of the estimated image at a change ratio represented by a formula "G1 / G2" where the predetermined particle size is "G1" and the particle size in the particle size information is "G2"; and an output process of outputting, from the trained learning device, machining surface information indicating the state of the machining surface of the tool to be estimated, using the estimated image whose image size has been changed in the resizing process.

Images