Abnormality determination system, abnormality determination method and control program

Abstract

To provide an abnormality determination system, an abnormality determination method and a control program capable of highly accurately determining the presence or absence of abnormality in a cutting tool.SOLUTION: An abnormality determination system according to the present invention determines the presence or absence of an abnormality in a cutting tool attached to a machining apparatus. The cutting tool performs cutting on a plurality of regions included in a workpiece. The abnormality determination system includes a sensor and a controller. The sensor detects a physical quantity related to vibration of the machining apparatus. The control unit determines the presence or absence of the abnormality on the basis of region information indicating in which region of the plurality of regions the cutting is performed, and the physical quantity.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to an abnormality determination system, an abnormality determination method, and a control program. [Background technology]

[0002] Japanese Patent Laid-Open Publication No. 2002-59342 (Patent Document 1) discloses a wear detection device for a cutting tool, which extracts frequency components within a predetermined range from the cutting sound of a cutting machine, and determines that the cutting tool is worn when the signal level of the frequency components within the predetermined range is equal to or greater than a set value (see Patent Document 1). [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Laid-Open No. 2002-59342 Summary of the Invention [Problem to be solved by the invention]

[0004] If machining of a workpiece continues while an abnormality occurs in a cutting tool attached to a processing device, damage to the workpiece may occur. On the other hand, if the cutting tool is replaced even though there is no abnormality in the cutting tool, the processing cost will increase more than necessary. Therefore, it is important to determine with high accuracy whether or not there is an abnormality in the cutting tool. The technology disclosed in the above Patent Document 1 has room for improvement, for example, in terms of the accuracy of determining whether or not there is an abnormality in the cutting tool.

[0005] The present invention has been made to solve such problems, and its purpose is to provide an abnormality determination system, an abnormality determination method, and a control program that can determine with higher accuracy whether or not there is an abnormality in a cutting tool. [Means for solving the problem]

[0006] An abnormality determination system according to one aspect of the present invention determines whether or not an abnormality exists in a cutting tool attached to a processing device. The cutting tool performs cutting processing on multiple regions included in a workpiece. The abnormality determination system includes a sensor and a control unit. The sensor detects a physical quantity related to vibrations of the processing device. The control unit determines whether or not the abnormality exists based on region information indicating which of the multiple regions is being cut and the physical quantity.

[0007] The inventor(s) discovered that the physical quantity changes depending on the state of the cutting tool, and that the physical quantity differs for each region of the workpiece. In this abnormality determination system, the presence or absence of an abnormality in the cutting tool is determined based on the physical quantity and on region information indicating which of multiple regions included in the workpiece has been cut. Therefore, according to this abnormality determination system, the presence or absence of an abnormality is determined based on the physical quantity while taking into account which of multiple regions included in the workpiece has been cut, so that the presence or absence of an abnormality can be determined with higher accuracy.

[0008] In the above-mentioned abnormality determination system, the multiple regions may include a first region and a second region, and the abnormality determination system may further include a memory unit that stores a first reference value associated with the first region and a second reference value associated with the second region, and the control unit may determine the presence or absence of the abnormality based on the first reference value and the physical quantity when the region information indicates the first region, and may determine the presence or absence of the abnormality based on the second reference value and the physical quantity when the region information indicates the second region.

[0009] In this abnormality determination system, when the region information indicates a first region, the presence or absence of the abnormality is determined based on the first reference value and the physical quantity, while when the region information indicates a second region, the presence or absence of the abnormality is determined based on the second reference value and the physical quantity. Therefore, according to this abnormality determination system, a reference value appropriate for each region where cutting work has been performed is provided, so that the presence or absence of the abnormality can be determined with higher accuracy.

[0010] In the above-mentioned abnormality determination system, the control unit may acquire region information by inputting a spectrogram generated based on the above-mentioned physical quantity into a trained model, and the trained model may be generated through machine learning using, as training data, multiple spectrograms generated based on physical quantities detected by a sensor during cutting processing on multiple regions, and may output region information in response to the spectrogram being input.

[0011] In this anomaly determination system, region information is acquired by inputting a spectrogram generated based on the physical quantities into a trained model. Therefore, with this anomaly determination system, it is possible to determine which of multiple regions included in the workpiece has been subjected to cutting processing, even if the processing device does not have a function for identifying the coordinate position of the cutting tool.

[0012] In the above abnormality determination system, cutting processing may be performed by fixing the relative positional relationship between the cutting tool and the workpiece along a first axis and changing the positional relationship along a second axis perpendicular to the first axis, and the multiple regions may be aligned along the first axis.

[0013] In the abnormality determination system, the control unit may execute a process for stopping the processing device when it is determined that an abnormality exists.

[0014] According to this abnormality determination system, the machining device stops when it is determined that an abnormality exists, thereby preventing damage to the workpiece caused by an abnormality in the cutting tool.

[0015] In the abnormality determination system, the processing device may be a groove cutting machine, the cutting tool may be a cutter, and the object to be processed may be a lapping plate before groove cutting.

[0016] According to another aspect of the present invention, there is provided an anomaly determination method for determining whether or not an anomaly exists in a cutting tool attached to a processing device. The cutting tool performs cutting on multiple regions included in a workpiece. The anomaly determination method includes detecting a physical quantity related to vibrations of the processing device, and determining whether or not the anomaly exists based on the physical quantity and region information indicating which of the multiple regions is being cut.

[0017] According to this abnormality determination method, the presence or absence of the abnormality is determined based on the physical quantity, taking into account which of the multiple regions included in the workpiece has been subjected to cutting processing, thereby making it possible to determine the presence or absence of the abnormality with greater accuracy.

[0018] A control program according to another aspect of the present invention causes a computer to execute a process for determining whether or not an abnormality exists in a cutting tool attached to a processing device. The cutting tool performs cutting on multiple regions included in a workpiece. The control program causes the computer to execute a process for detecting a physical quantity related to vibration of the processing device, and a process for determining whether or not the abnormality exists based on the physical quantity and area information indicating which of the multiple regions is being cut.

[0019] According to this control program, the presence or absence of the abnormality is determined based on the physical quantity, taking into account which of the multiple regions included in the workpiece has been subjected to cutting processing, thereby making it possible to determine the presence or absence of the abnormality with greater accuracy. [Effects of the Invention]

[0020] According to the present invention, it is possible to provide an abnormality determination system, an abnormality determination method, and a control program that can determine with higher accuracy whether or not there is an abnormality in a cutting tool. [Brief explanation of the drawings]

[0021] [Figure 1] FIG. 1 is a diagram for explaining an abnormality determination system. [Figure 2] FIG. 2 is a diagram schematically illustrating a plan view of a groove cutting machine. [Figure 3] FIG. 10 is a diagram schematically showing a plane of the lapping plate after grooving. [Figure 4] FIG. 2 is a diagram schematically illustrating the vicinity of a cutter shaft from the side. [Figure 5] FIG. 2 is a block diagram illustrating a schematic configuration of a server. [Figure 6] FIG. 1 is a block diagram schematically illustrating the configuration of a notebook PC (Personal Computer). [Figure 7] FIG. 10 is a diagram comparing the transition of vibration acceleration during the first operation with the transition of vibration acceleration during the tenth operation. [Figure 8] FIG. 10 is a diagram showing vibration acceleration during grooving in each pass in the first operation. [Figure 9] FIG. 10 is a diagram showing a spectrogram generated based on vibration acceleration data collected during the fourth operation. [Figure 10] 10 is a flowchart showing a procedure for collecting vibration acceleration data. [Figure 11] 10 is a flowchart showing a procedure for determining an abnormality. [Figure 12] FIG. 10 is a diagram schematically illustrating a reference value table. [Figure 13] FIG. 10 is a diagram for explaining a plurality of regions defined in the thickness direction. DETAILED DESCRIPTION OF THE INVENTION

[0022] An embodiment according to one aspect of the present invention (hereinafter also referred to as "the present embodiment") will be described in detail below with reference to the drawings. Note that identical or corresponding parts in the drawings are designated by the same reference numerals, and their description will not be repeated. Furthermore, for ease of understanding, each drawing is drawn in a schematic manner with objects appropriately omitted or exaggerated. Furthermore, the X-axis, Y-axis, and Z-axis in each drawing are mutually orthogonal.

[0023] [1. Configuration of the anomaly detection system] FIG. 1 is a diagram illustrating an abnormality determination system 10 according to the present embodiment. As shown in FIG. 1, the abnormality determination system 10 includes a sensor 60, a laptop PC 200, and a server 100. The sensor 60 is attached to a groove cutting machine 50 that includes a cutter 54. The output of the sensor 60 is transmitted to the laptop PC 200. The laptop PC 200 and the server 100 are capable of communicating with each other via a network N1. As will be described in detail later, the abnormality determination system 10 is configured to determine the presence or absence of an abnormality in the cutter 54 based on the output of the sensor 60. The abnormality determination system 10, for example, displays information related to the determination result on a display 300. The groove cutting machine 50, the sensor 60, the laptop PC 200, and the display 300 are, for example, located in the same factory F1.

[0024] Fig. 2 is a diagram schematically illustrating a plan view of the groove cutting machine 50. Referring to Fig. 2, the groove cutting machine 50 is configured to form a plurality of grooves on a lapping plate 70, for example, during the manufacturing process of the lapping plate 70. The lapping plate 70 is a member used, for example, in lapping to polish an object to be processed. The groove cutting machine 50 has a gate-shaped structure and includes a column 51, a cross rail 52, a cutter shaft 53, a plurality of cutters 54, a bed 55, and a surface plate 56.

[0025] The column 51 is a gate-shaped member and includes two pillar members and a connecting member connecting the two pillar members. The connecting member extends along the Y-axis. One of the two pillar members extends downward along the Z-axis from one end of the connecting member on the Y-axis, and the other of the two pillar members extends downward along the Z-axis from the other end of the connecting member on the Y-axis. The cross rail 52 is fixed to the front of the column 51 (connecting member) and extends along the Y-axis. The cutter shaft 53 is attached to the cross rail 52 and is configured to move on the cross rail 52 along the Y-axis. A plurality of cutters 54 are attached to the cutter shaft 53. Each of the plurality of cutters 54 has a substantially circular shape and has sawtooth formed on its outer periphery. Each of the plurality of cutters 54 rotates in accordance with the rotation of the cutter shaft 53. Grooving is performed with a carbide tip (not shown) attached to each tooth of the cutter 54.

[0026] The bed 55 extends along the X-axis and is disposed so as to penetrate the space surrounded by the columns 51. The surface plate 56 is configured to move on the bed 55 along the X-axis. For example, a lapping plate 70 is fixed to the surface plate 56. With the lapping plate 70 fixed to the surface plate 56 and the lapping plate 70 being cut by the multiple cutters 54, the surface plate 56 moves along the X-axis. As a result, multiple grooves are formed on the lapping plate 70.

[0027] That is, in the groove cutting machine 50, the relative positional relationship between the multiple cutters 54 and the lapping plate 70 is fixed along the Y axis, and the relative positional relationship between the multiple cutters 54 and the lapping plate 70 is changed along the X axis, thereby cutting grooves in the lapping plate 70. When the surface plate 56 moves to the target position along the X axis, the cutter shaft 53 moves along the Y axis. Thereafter, while the multiple cutters 54 are cutting the lapping plate 70, the surface plate 56 moves again along the X axis. As a result, multiple new grooves are formed on the lapping plate 70. With the position of the cutter shaft 53 fixed along the Y axis, the surface plate 56 moves along the X axis, and the cutter shaft 53 moves along the Y axis, repeatedly. As a result, multiple grooves extending along the X axis are formed at approximately equal intervals across the entire surface of the lapping plate 70.

[0028] Thereafter, for example, the surface plate 56 rotates 90° around the Z axis, causing the lapping plate 70 to rotate 90° around the Z axis. Then, with the position of the cutter shaft 53 on the Y axis fixed, the surface plate 56 moves along the X axis, and the cutter shaft 53 moves along the Y axis, repeatedly. As a result, multiple grooves, each perpendicular to one of the multiple grooves formed earlier, are formed at approximately equal intervals on the lapping plate 70.

[0029] 3 is a diagram schematically illustrating a plane of the lapping plate 70 after grooving. As shown in FIG. 3, the lapping plate 70 has a plurality of grooves C1 extending along the X-axis and a plurality of grooves C1 extending along the Y-axis. The region in which the plurality of grooves C1 are formed by one movement of the surface plate 56 along the X-axis is also referred to as a "pass." Before and after the lapping plate 70 rotates 90 degrees around the Z-axis, a plurality of passes are aligned along the Y-axis.

[0030] FIG. 4 is a diagram schematically illustrating the vicinity of the cutter shaft 53 from the side. As shown in FIG. 4, a sensor 60 is attached to the cutter shaft 53. The sensor 60 is configured to detect acceleration. For example, the sensor 60 detects the acceleration of vibrations of the groove cutting machine 50 when cutting the lapping plate 70 (hereinafter also referred to as "vibration acceleration"). Details will be described later, but the abnormality determination system 10 determines whether or not there is an abnormality in the cutter 54 based on the vibration acceleration of the groove cutting machine 50.

[0031] Fig. 5 is a block diagram showing a schematic configuration of server 100. Server 100 is realized by, for example, a general-purpose computer. As shown in Fig. 5, server 100 includes a control unit 110, a communication I / F (interface) 130, and a storage unit 120. Each component is electrically connected via a bus.

[0032] The control unit 110 includes a central processing unit (CPU) 112, a random access memory (RAM) 114, a read only memory (ROM) 116, and the like, and is configured to control each component in accordance with information processing.

[0033] The communication I / F 130 is configured to communicate with the notebook PC 200 (FIG. 1) via the network N1. The communication I / F 130 is configured, for example, by a wired LAN (Local Area Network) module or a wireless LAN module.

[0034] The storage unit 120 is configured, for example, with an auxiliary storage device such as a hard disk drive or a solid state drive. The storage unit 120 stores, for example, a control program 122, a trained model 124, and a reference value table 126. The control program 122 is executed by the CPU 112 to realize various functions of the server 100. The trained model 124 and the reference value table 126 will be described in detail later.

[0035] Fig. 6 is a block diagram showing a schematic configuration of the notebook PC 200. As shown in Fig. 6, the notebook PC 200 includes a control unit 210, a communication I / F 230, an operation unit 240, a display 250, and a storage unit 220. In the notebook PC 200, each component is electrically connected via a bus.

[0036] The control unit 210 includes a CPU, RAM, ROM, etc., and is configured to control each component in accordance with information processing. The communication I / F 230 is configured to communicate with the server 100 through the network N1. The communication I / F 230 is configured, for example, as a wired LAN module or a wireless LAN module. The operation unit 240 is configured to receive input from a user. The operation unit 240 is configured, for example, as a part or all of a touch panel, a keyboard, a mouse, and a microphone. The display 250 is configured to display images. The display 250 is configured, for example, as a monitor such as a liquid crystal monitor or an organic EL (Electro Luminescence) monitor.

[0037] The storage unit 220 is, for example, an auxiliary storage device such as a hard disk drive or a solid state drive. The storage unit 220 stores, for example, a control program 222. When the control program 222 is executed by the CPU of the control unit 210, various functions of the notebook PC 200 are realized.

[0038] [2. The need to determine whether there are any abnormalities in the cutter] If the groove cutting process for the lapping plate 70 continues while an abnormality has occurred in the cutter 54 attached to the groove cutting machine 50, defects such as bending of the grooves formed in the lapping plate 70 may occur. As a result, the manufactured lapping plate 70 will be defective. On the other hand, if the cutter 54 is replaced even though there is no abnormality in the cutter 54, the processing cost will be higher than necessary. Therefore, it is important to accurately determine whether or not there is an abnormality in the cutter 54.

[0039] The inventor(s) replaced each of the multiple cutters 54 attached to the groove cutting machine 50 with a new one, and then manufactured 10 lapping plates 70. The multiple cutters 54 were not replaced until groove cutting on all 10 lapping plates 70 was completed. Hereinafter, the period from start to finish of groove cutting on one lapping plate 70 will be referred to as "one operation." In one operation, groove cutting was performed in each pass before the lapping plate 70 rotated 90 degrees around the Z axis (hereinafter also referred to as the "first half of the operation"), and then groove cutting was performed in each pass after the lapping plate 70 rotated 90 degrees around the Z axis (hereinafter also referred to as the "second half of the operation"). Ten operations were performed to manufacture 10 lapping plates 70.

[0040] In each operation, groove cutting was performed in five passes in the first half of the operation, and then in five passes in the second half of the operation. The five passes in the first half of the operation were assigned pass numbers 1-5, and the five passes in the second half of the operation were assigned pass numbers 6-10. Note that the number of passes is not necessarily limited to this. The output of the sensor 60 was collected in each of the 10 operations.

[0041] FIG. 7 is a diagram comparing the transition of vibration acceleration in the first operation with the transition of vibration acceleration in the tenth operation. Referring to the upper and lower diagrams in FIG. 7, the horizontal axis represents the machining distance, and the vertical axis represents the vibration acceleration. As shown in FIG. 7, it can be seen that the vibration acceleration in the tenth operation tends to be higher than in the first operation. In this way, from data showing the vibration acceleration obtained through 10 operations (hereinafter also referred to as "vibration acceleration data"), the inventor(s) discovered that the vibration acceleration of the groove cutting machine 50 changes depending on the state (e.g., wear state) of the multiple cutters 54 attached to the groove cutting machine 50.

[0042] Fig. 8 is a diagram showing vibration acceleration during groove cutting in each pass in the first operation. Referring to Fig. 8, the horizontal axis represents the pass number, and the vertical axis represents vibration acceleration. Referring to Fig. 8, it can be seen that the vibration acceleration varies greatly for each pass. In this way, the inventor(s) have discovered that physical quantities related to vibration, such as vibration acceleration, vary depending on the pass during groove cutting.

[0043] Although details will be described later, the abnormality determination system 10 determines whether or not there is an abnormality in the cutter 54 based on information indicating which of the multiple passes included in the lapping plate 70 is performing groove cutting (hereinafter also referred to as "pass information") and the vibration acceleration. Therefore, according to the abnormality determination system 10, the presence or absence of the abnormality is determined based on the vibration acceleration while taking into account which of the multiple passes included in the lapping plate 70 is performing groove cutting, so that the presence or absence of the abnormality can be determined with higher accuracy.

[0044] [3. Trained model for path determination] In this way, in the abnormality determination system 10, in determining whether or not there is an abnormality in the cutter 54, it is taken into consideration which of the multiple passes included in the lapping plate 70 is performing groove cutting. In the abnormality determination system 10, during groove cutting on the lapping plate 70, path information is generated by using the trained model 124 stored in the memory unit 120 of the server 100.

[0045] FIG. 9 is a diagram showing a spectrogram generated based on vibration acceleration data collected during the fourth operation. Referring to FIG. 9, the horizontal axis represents time, and the vertical axis represents frequency. In this spectrogram, each part is assigned a color according to its amplitude. Specifically, the larger the amplitude, the closer to red the color is assigned, and the smaller the amplitude, the closer to blue the color is assigned. As shown in FIG. 9, the frequency characteristics and amplitude differ for each pass. The trained model 124 is configured to output pass information in response to input of a spectrogram generated based on vibration acceleration data collected over, for example, one minute. Note that the vibration acceleration data used to generate the spectrogram does not necessarily have to be for one minute. Types of pass information that can be output include pass numbers 1-10 and information indicating no cutting. Information indicating no cutting is output when no groove cutting is performed on the lapping plate 70.

[0046] The trained model 124 is generated through machine learning. For example, a large number of one-minute vibration acceleration data (hereinafter also referred to as "one-minute data") are extracted from vibration acceleration data output by the sensor 60 over a long period of time during groove cutting. A spectrogram is generated based on each of the large number of one-minute data. Each spectrogram is associated with a label indicating the pass number of the pass on which groove cutting was performed when the one-minute data used to generate the spectrogram was collected. In machine learning, each spectrogram associated with a label indicating the pass number is used as training data (training data). Various well-known methods can be applied for machine learning, such as neural networks (e.g., convolutional neural networks (CNNs)), deep learning, decision tree learning, association rule learning, and Bayesian networks. The trained model 124 is generated through machine learning using such training data.

[0047] [4. Operation] 10 is a flowchart showing the procedure for collecting vibration acceleration data. The process shown in this flowchart is repeatedly executed by the control unit 210 of the notebook PC 200 at a predetermined interval when the grooving machine 50 is processing the lapping plate 70.

[0048] 10, control unit 210 detects vibration acceleration by receiving vibration acceleration data output by sensor 60, and executes a process for storing the received vibration acceleration data in storage unit 220 (step S100). Control unit 210 determines whether the vibration acceleration data newly accumulated in storage unit 220 has reached a predetermined time since the previous transmission of vibration acceleration data to server 100 (step S110). The predetermined time is, for example, one minute.

[0049] When it is determined that the vibration acceleration data newly accumulated in storage unit 220 has not reached the predetermined time since the timing at which the vibration acceleration data was last transmitted to server 100 (NO in step S110), control unit 210 executes the process of step S100 again. On the other hand, when it is determined that the vibration acceleration data newly accumulated in storage unit 220 has reached the predetermined time since the timing at which the vibration acceleration data was last transmitted to server 100 (YES in step S110), control unit 210 controls communication I / F 230 to transmit the vibration acceleration data for the predetermined time newly accumulated in storage unit 220 to server 100 (step S120). By repeatedly executing the process shown in this flowchart, the vibration acceleration data for the predetermined time is sequentially transmitted to server 100.

[0050] 11 is a flowchart showing the procedure for determining an abnormality. The process shown in this flowchart is repeatedly executed by the control unit 110 of the server 100 when the groove cutting machine 50 is cutting the lapping plate 70.

[0051] 11, control unit 110 determines whether or not vibration acceleration data for a predetermined time period has been received from notebook PC 200 (step S200). If it is determined that vibration acceleration data for the predetermined time period has not been received (NO in step S200), control unit 110 executes the process of step S200 again.

[0052] On the other hand, if it is determined that vibration acceleration data for the predetermined time period has been received (YES in step S200), control unit 110 generates a spectrogram based on the received vibration acceleration data for the predetermined time period (step S210). Various known algorithms can be applied to generate the spectrogram.

[0053] The control unit 110 inputs the generated spectrogram to the trained model 124 and acquires path information output by the trained model 124 in response to the input of the spectrogram (step S220). The control unit 110 calculates the effective value of the vibration acceleration data for the predetermined time period received in step S200 (step S230). The control unit 110 reads out the reference value data corresponding to the path number indicated by the path information acquired in step S220 by referring to the reference value table 126 stored in the storage unit 120 (step S240).

[0054] Fig. 12 is a diagram schematically showing the reference value table 126. As shown in Fig. 12, in the reference value table 126, a reference value is associated with each pass number. In this example, a first reference value (0.41) is associated with the pass with pass number 1, and a second reference value (0.43) is associated with the pass with pass number 2. Each reference value is, for example, the effective value of the vibration acceleration data collected during groove cutting in the corresponding pass in the first operation.

[0055] 11, when the reference value data is read in step S240, the control unit 110 calculates the rate of change of the vibration acceleration by dividing the effective value calculated in step S230 by the reference value read in step S240 (step S250). The control unit 110 determines whether the rate of change is less than a threshold value (step S260). Here, the threshold value is determined in advance, for example, by investigating in advance through multiple operations the tendency of the rate of change at the timing when cutter 54 needs to be replaced. The threshold value is, for example, 1.2.

[0056] If it is determined that the rate of change is less than the threshold value (YES in step S260), control unit 110 controls communication I / F 130 to transmit data to notebook PC 200 for displaying information corresponding to the rate of change on display 300 (see FIG. 1) (step S270). As a result, for example, data indicating the rate of change is transmitted to notebook PC 200, and the rate of change is displayed on display 300.

[0057] On the other hand, if it is determined that the rate of change is equal to or greater than the threshold value (NO in step S260), the control unit 110 executes processing to stop the groove cutting machine 50 (step S280). For example, the control unit 110 transmits a signal to instruct the groove cutting machine 50 to stop the groove cutting machine 50 to a control device (not shown) of the groove cutting machine 50. As a result, for example, the groove cutting by the groove cutting machine 50 is stopped.

[0058] [5. Features] As described above, in the abnormality determination system 10, the presence or absence of an abnormality in the cutter 54 is determined based on the vibration acceleration data and the pass information indicating which of the multiple passes included in the lapping plate 70 is performing the groove cutting. Therefore, according to the abnormality determination system 10, the presence or absence of the abnormality is determined based on the vibration acceleration data while taking into account which of the multiple passes included in the lapping plate 70 is performing the groove cutting, so that the presence or absence of the abnormality can be determined with higher accuracy.

[0059] Furthermore, in the abnormality determination system 10, when the pass information indicates a pass with pass number 1, the presence or absence of the abnormality is determined based on the reference value and vibration acceleration data associated with the pass with pass number 1, while when the pass information indicates a pass with pass number 2, the presence or absence of the abnormality is determined based on the reference value and vibration acceleration data associated with the pass with pass number 2. Therefore, according to the abnormality determination system 10, a reference value appropriate for each pass on which grooving is performed is set, and therefore the presence or absence of the abnormality can be determined with higher accuracy.

[0060] Furthermore, in the abnormality determination system 10, path information is acquired by inputting a spectrogram generated based on vibration acceleration data for a predetermined time into a trained model. Therefore, according to the abnormality determination system 10, even if the groove cutting machine 50 does not have a function for identifying the coordinate position of the cutter axis 53, for example, it is possible to identify in which of the multiple passes included in the lapping plate 70 groove cutting is being performed.

[0061] Furthermore, in the abnormality determination system 10, if it is determined that there is an abnormality in the cutter 54, a process is executed to stop the groove cutting machine 50. Therefore, according to the abnormality determination system 10, if it is determined that there is an abnormality in the cutter 54, the groove cutting machine 50 is stopped, and therefore, it is possible to prevent the occurrence of damage to the lapping plate 70 due to an abnormality in the cutter 54.

[0062] The groove cutting machine 50 is an example of a "machining device" in the present invention. The cutter 54 is an example of a "cutting tool" in the present invention. The abnormality determination system 10 is an example of an "abnormality determination system" in the present invention. The lapping plate 70 is an example of a "machined object" in the present invention. The multiple paths are an example of a "multiple regions" in the present invention. The vibration acceleration is an example of a "physical quantity related to vibration" in the present invention. The sensor 60 is an example of a "sensor" in the present invention. The path information is an example of "region information" in the present invention. The control unit 110 is an example of a "control unit" in the present invention. The memory unit 120 is an example of a "memory unit" in the present invention. The trained model 124 is an example of a "trained model" in the present invention.

[0063] 6. Other Embodiments The concept of the above embodiment is not limited to the embodiment described above. Hereinafter, examples of other embodiments to which the concept of the above embodiment can be applied will be described.

[0064] <6-1> In the above embodiment, the path information was generated by the trained model 124. However, the method of generating the path information is not limited to this. For example, if the groove cutting machine 50 has a function of recognizing coordinate information of the cutter shaft 53, the control device of the groove cutting machine 50 may generate the path information based on the coordinate information. Alternatively, for example, the coordinate information recognized by the control device of the groove cutting machine 50 may be transmitted to the server 100, and the control unit 110 of the server 100 may generate the path information based on the coordinate information. Alternatively, for example, the elapsed time from the start of groove cutting may be measured, and the control unit 110 of the server 100 may generate the path information based on the measured elapsed time.

[0065] <6-2> In the above embodiment, the presence or absence of an abnormality is determined in the cutter 54 of the groove cutting machine 50. However, the object for which the presence or absence of an abnormality is determined is not limited to this. For example, the presence or absence of an abnormality may be determined in a drill tool of an NC drilling machine that performs hole drilling, or the presence or absence of an abnormality may be determined in tools used in various other machine tools.

[0066] <6-3> Furthermore, in the above embodiment, vibration acceleration data is used to determine whether or not there is an abnormality in the cutter 54. However, the data used to determine whether or not there is an abnormality in the cutter 54 is not limited to this. Any physical quantity related to the vibration of the groove cutting machine 50 may be used, and for example, data indicating the vibration velocity or displacement of the groove cutting machine 50 may be used, or data indicating the sound pressure or AE (Acoustic Emission) waves generated by the groove cutting machine 50 may be used.

[0067] <6-4> Furthermore, in the above embodiment, during groove cutting, the lapping plate 70 moves along the X-axis, and the cutter 54 moves along the Y-axis. However, the movement directions of the lapping plate 70 and the cutter 54 are not limited to this. For example, the lapping plate 70 may move along the Y-axis, and the cutter 54 may move along the X-axis. Alternatively, for example, the lapping plate 70 may not move, and the cutter 54 may move along both the Y-axis and the X-axis. Alternatively, for example, the cutter 54 may not move, and the lapping plate 70 may move along both the Y-axis and the X-axis.

[0068] <6-5> Furthermore, in the above embodiment, whether or not to stop the groove cutting machine 50 is determined depending on whether the rate of change of the vibration acceleration is less than a threshold value. However, whether or not to stop the groove cutting machine 50 does not necessarily have to be determined based on the rate of change of the vibration acceleration. For example, a reference value (threshold value) may be set for each pass, and whether or not to stop the groove cutting machine 50 may be determined based on whether the vibration acceleration exceeds the reference value associated with the pass being grooved.

[0069] <6-6> In the above embodiment, a reference value is assigned to each pass. However, the assignment of a reference value does not necessarily have to be for each pass. For example, a plurality of regions may be defined along the X axis, and a reference value may be assigned to each of these regions. Furthermore, for example, when determining whether or not there is an abnormality in a drill tool of an NC drilling machine that performs hole drilling, a plurality of regions may be defined in the thickness direction (Z axis direction) of the workpiece, and a reference value may be assigned to each of these regions.

[0070] 13 is a diagram for explaining a plurality of regions defined in the thickness direction. Referring to FIG. 13, in this example, a workpiece W1 is drilled with a drill D1. In this case, a plurality of regions (a first region, a second region, and a third region) may be defined in the thickness direction of the workpiece W1.

[0071] The above describes exemplary embodiments of the present invention. That is, the detailed description and the accompanying drawings are disclosed for the purpose of illustrative explanation. Therefore, some of the components described in the detailed description and the accompanying drawings may be non-essential components for solving the problems. Therefore, just because these non-essential components are described in the detailed description and the accompanying drawings, it should not be immediately recognized that these non-essential components are essential.

[0072] Furthermore, the above-described embodiments are merely illustrative of the present invention in all respects. Various improvements and modifications to the above-described embodiments are possible within the scope of the present invention. For example, at least a portion of the configuration of any of the embodiments may be combined with at least a portion of the configuration of any of the other embodiments. In other words, when implementing the present invention, specific configurations can be appropriately adopted depending on the embodiment. [Explanation of symbols]

[0073] 10 Abnormality judgment system, 50 Grooving machine, 51 Column, 52 Cross rail, 53 Cutter shaft, 54 Cutter, 55 Bed, 56 Surface plate, 60 Sensor, 70 Lapping plate, 100 Server, 110, 210 Control unit, 112 CPU, 114 RAM, 116 ROM, 120, 220 Memory unit, 122, 222 Control program, 124 Trained model, 126 Reference value table, 130, 230 Communication I / F, 200 Notebook PC, 240 Operation unit, 250, 300 Display, C1 Groove, D1 Drill, F1 Factory, H1 Hole, N1 Network, W1 Workpiece.

Claims

1. An abnormality determination system that determines whether or not there is an abnormality in a cutting tool attached to a processing device, The cutting tool performs cutting on a plurality of regions included in the workpiece, a sensor for detecting a physical quantity related to vibration of the processing device; and a control unit that determines whether or not the abnormality exists based on region information indicating which of the plurality of regions the cutting process has been performed in and the physical quantity.

2. the plurality of regions include a first region and a second region, the abnormality determination system further includes a storage unit that stores a first reference value associated with the first region and a second reference value associated with the second region; 2. The abnormality determination system according to claim 1, wherein the control unit determines the presence or absence of the abnormality based on the first reference value and the physical quantity when the region information indicates the first region, and determines the presence or absence of the abnormality based on the second reference value and the physical quantity when the region information indicates the second region.

3. the control unit acquires the region information by inputting a spectrogram generated based on the physical quantity into a trained model; 3. The anomaly determination system according to claim 1, wherein the trained model is generated through machine learning using, as training data, a plurality of spectrograms generated based on the physical quantities detected by the sensor during cutting processing of the plurality of regions, and the system outputs the region information in response to input of the spectrograms.

4. the cutting process is performed by fixing a relative positional relationship between the cutting tool and the workpiece along a first axis and changing the relative positional relationship along a second axis perpendicular to the first axis; The abnormality determination system according to claim 1 or 2, wherein the plurality of regions are aligned along the first axis.

5. 3. The abnormality determination system according to claim 1, wherein the control unit executes a process for stopping the processing device when it is determined that the abnormality exists.

6. the processing device is a groove cutting machine, the cutting tool is a cutter, 3. The abnormality determination system according to claim 1, wherein the workpiece is a lapping plate before groove cutting.

7. An abnormality determination method for determining whether or not there is an abnormality in a cutting tool attached to a processing device, comprising: The cutting tool performs cutting on a plurality of regions included in the workpiece, Detecting a physical quantity related to vibration of the processing device; determining whether or not the abnormality exists based on region information indicating which of the plurality of regions has been subjected to the cutting process and the physical quantity.

8. A control program that causes a computer to execute a process for determining whether or not there is an abnormality in a cutting tool attached to a processing device, The cutting tool performs cutting on a plurality of regions included in the workpiece, A process of detecting a physical quantity related to vibration of the processing device; and determining whether or not there is an abnormality based on area information indicating which of the plurality of areas has been subjected to the cutting process and the physical quantity.

Images