Machining result evaluation device, machining result evaluation method, machining condition determination device, and machining condition determination method

Abstract

A machining result evaluation device (1) that evaluates the machining result of machining performed by a machine tool (4) is provided with: a numerical control simulation unit (12) that simulates the operation of a numerical control device (2) that controls a servo control device (3) and outputs a position command to a drive shaft of the machine tool; a servo control simulation unit (13) that simulates the operation of the servo control device on the basis of the position command and outputs a torque command to the drive shaft; a drive shaft simulation unit (14) that simulates the operation of the drive shaft on the basis of the torque command; and a machining result evaluation unit (15) that evaluates a machining result on the basis of information corresponding to the operation of the drive shaft, the drive shaft simulation unit outputs position information indicating the position of the drive shaft to the servo control simulation unit, and the servo control simulation unit simulates feedback control to the drive shaft simulation unit using the position information. The machining result evaluation unit evaluates a machining result when feedback control to the drive shaft simulation unit is simulated.

Description

Technical Field

[0001] The present invention relates to a processing result evaluation device, a processing result evaluation method, a processing condition determination device and a processing condition determination method for evaluating a processing result of a machine tool. Background Art

[0002] In recent years, the development of machining simulation technology that uses a machining simulation device to evaluate the shape of a workpiece after machining before the machine tool actually performs machining has been continuously developed. The machining simulation device moves a tool in a virtual space according to a machining program, removes the tool from the area where the workpiece, which is the object to be machined, passes through, and thereby evaluates the shape of the workpiece after machining. In actual machining performed by a machine tool, machining is often not performed according to the machining program, and in machining simulation based on the machining program, it is difficult to accurately evaluate the shape of the workpiece after machining.

[0003] The machining simulation device described in Patent Document 1 simulates the operation of a machine tool based on a position command outputted from a numerical control device and the transfer characteristics of the machine tool, thereby evaluating the shape of a machined workpiece.

[0004] Patent Document 1: Japanese Patent Application Publication No. 2019-152936 Summary of the invention

[0005] However, the technology of the above-mentioned Patent Document 1 does not consider the response from the servo control device or the machine tool to the numerical control device, which is a device at a later stage than the numerical control device, to simulate the processing. Therefore, the technology of the above-mentioned Patent Document 1 cannot simulate the processing corresponding to the function based on the return value of the response from the servo control device or the machine tool to the numerical control device, and there is a problem that the processing result cannot be accurately evaluated.

[0006] The present invention has been made in view of the above-mentioned circumstances, and an object of the present invention is to obtain a processing result evaluation device capable of accurately evaluating a processing result.

[0007] In order to solve the above-mentioned problems and achieve the purpose, the processing result evaluation device of the present invention evaluates the processing results of the processing performed by a working machine driven by a servo control device, and the processing result evaluation device comprises: a numerical control simulation unit, which simulates the action of the numerical control device that controls the servo control device, and outputs a position instruction to the drive shaft of the working machine; a servo control simulation unit, which simulates the action of the servo control device based on the position instruction, and outputs a torque instruction to the drive shaft; a drive shaft simulation unit, which simulates the action of the drive shaft based on the torque instruction; and a processing result evaluation unit, which evaluates the processing result based on information corresponding to the action of the drive shaft, the drive shaft simulation unit outputs position information indicating the position of the drive shaft to the servo control simulation unit, the servo control simulation unit uses the position information to simulate feedback control to the drive shaft simulation unit, and the processing result evaluation unit evaluates the processing result when simulating feedback control to the drive shaft simulation unit.

[0008] Effects of the Invention

[0009] The processing result evaluation device according to the present invention has the effect of being able to accurately evaluate the processing result. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] Figure 1 This is a block diagram showing the configuration of a processing result evaluation system including the processing result evaluation device according to the first embodiment.

[0011] Figure 2 This is a diagram for explaining an example of a process simulated by the processing result evaluation device according to the first embodiment.

[0012] Figure 3 This is a flowchart showing the processing procedure of the processing executed by the processing result evaluation device according to the first embodiment.

[0013] Figure 4 This is a diagram showing a configuration example of a processing circuit in a case where the processing circuit included in the processing result evaluation device according to the first embodiment is realized by a computing device and a memory.

[0014] Figure 5 This is a diagram showing an example of a processing circuit in a case where the processing circuit included in the processing result evaluation device according to the first embodiment is configured by dedicated hardware.

[0015] Figure 6 This is a block diagram showing the structure of a processing condition determination device according to the second embodiment.

[0016] Figure 7This is a block diagram showing the structure of a processing condition determination unit when the processing condition determination device according to the second embodiment calculates processing conditions corresponding to processing results using an inference model.

[0017] Figure 8 This is a block diagram showing the structure of a machine learning device according to Implementation Example 2.

[0018] Fig. 9 This is a diagram for explaining an example of a neural network used by the machine learning device involved in Implementation Example 2.

[0019] Fig.10 This is a flowchart showing the processing procedure of the processing executed by the processing condition determination device involved in the second embodiment. DETAILED DESCRIPTION

[0020] Hereinafter, a processing result evaluation device, a processing result evaluation method, a processing condition determination device, and a processing condition determination method according to embodiments of the present invention will be described in detail with reference to the accompanying drawings.

[0021] Implementation method 1.

[0022] Figure 1 This is a block diagram showing the configuration of a machining result evaluation system including the machining result evaluation device according to Embodiment 1. The machining result evaluation system 101 includes a machining result evaluation device 1 , a numerical control device 2 , a servo control device 3 , and a machine tool 4 .

[0023] In the machining result evaluation system 101 , the numerical control device 2 outputs a position command, and the servo control device 3 controls a drive axis of the machine tool 4 so as to follow the position command, thereby executing cutting machining.

[0024] During the cutting process, the drive shaft of the machine tool 4 moves, thereby moving the tool mounted on the spindle of the machine tool 4 and the workpiece (workpiece) fixed to the table or turning spindle of the machine tool 4. In addition, during the cutting process, the spindle or turning spindle rotates, thereby rotating the tool or the workpiece, and the tool contacts the workpiece, thereby removing a portion of the workpiece.

[0025] The numerical control device 2 analyzes the command code described in the machining program, and outputs a position command to the servo control device 3 based on the command code.

[0026] The servo control device 3 controls the drive shaft connected to the motor of the working machine 4 based on the position command received from the numerical control device 2. In addition, the servo control device 3 performs feedback control. Specifically, the servo control device 3 performs feedback control to flow current to the motor and control the drive shaft so that the error between the detection position detected by the detector (not shown) from the drive shaft and the position command received from the numerical control device 2 becomes smaller.

[0027] The processing result evaluation device 1 is a computer that evaluates the processing result of processing performed by the machine tool 4. An example of processing performed by the machine tool 4 is cutting processing. The processing result evaluation device 1 includes a numerical control simulation unit 12, a servo control simulation unit 13, a drive axis simulation unit 14, a processing result evaluation unit 15, and a display unit 16.

[0028] The numerical control simulation unit 12 simulates the processing executed by the numerical control device 2. Specifically, the numerical control simulation unit 12 analyzes the command code described in the machining program and outputs a position command to the servo control simulation unit 13.

[0029] The servo control simulation unit 13 simulates the processing executed by the servo control device 3. Specifically, the servo control simulation unit 13 performs feedback control and outputs a torque command to the drive axis simulation unit 14 so that the error between the position command received from the numerical control simulation unit 12 and the detected position received from the drive axis simulation unit 14 becomes small.

[0030] The drive shaft simulation unit 14 simulates the motion of the drive shaft based on a drive shaft model obtained by modeling the motion of the drive shaft of the machine tool 4. Specifically, the drive shaft simulation unit 14 simulates the motion of the drive shaft of the machine tool 4 based on the torque command received from the servo control simulation unit 13 and the response characteristics (for example, transfer function) to the torque command. In addition, the drive shaft simulation unit 14 calculates the position information indicating the detection position of the drive shaft and outputs it to the servo control simulation unit 13. The tool is driven by the drive shaft, so the position of the drive shaft corresponds to the position of the tool.

[0031] As described above, the numerical control simulation unit 12 simulates the action of the numerical control device 2 that controls the servo control device 3, and calculates and outputs the position command of the drive shaft of the working machine 4. In addition, the servo control simulation unit 13 simulates the action of the servo control device 3 based on the position command, and calculates and outputs the torque command of the drive shaft. In addition, the drive shaft simulation unit 14 simulates the action of the drive shaft based on the torque command, and calculates the position information of the drive shaft corresponding to the action of the drive shaft. The drive shaft simulation unit 14 outputs the calculated position information to the servo control simulation unit 13 and the processing result evaluation unit 15.

[0032] When the detector for detecting the position of the drive shaft is a scale, the drive shaft simulation unit 14 directly outputs the position information of the drive shaft to the servo control simulation unit 13 and the processing result evaluation unit 15. In addition, when the detector is an encoder for detecting the rotation angle of the motor, the drive shaft simulation unit 14 outputs the position information after the position of the drive shaft is converted into the rotation angle to the servo control simulation unit 13 and the processing result evaluation unit 15. For example, when the drive shaft is a feed screw mechanism, the drive shaft simulation unit 14 can obtain the rotation angle by dividing the position of the drive shaft by the pitch of the feed screw.

[0033] The servo control simulation unit 13 simulates feedback control for the drive shaft simulation unit 14 using the position information from the drive shaft simulation unit 14. The servo control simulation unit 13 uses the position information received from the drive shaft simulation unit 14 for simulation of feedback control and outputs the position information to the numerical control simulation unit 12 as a feedback position.

[0034] The numerical control simulation unit 12 simulates feedback control for the servo control simulation unit 13 using the position information from the servo control simulation unit 13. That is, the numerical control simulation unit 12 simulates processing that acts based on the feedback position (position information) received from the servo control simulation unit 13.

[0035] Figure 2 This is a diagram for explaining an example of a process simulated by the processing result evaluation device according to Embodiment 1. Here, a case is described in which the tool machine 4 moves the tool along a straight line 62 of a block n (n is a natural number) and then moves the tool along a straight line 63 of a block (n+1) which is the next block. The two straight lines 62 and 63 are orthogonal.

[0036] Working machinery 4 Figure 2 As shown, when the tool passes through the corner portion 60 where two straight lines 62 and 63 intersect perpendicularly, in the corner portion 60, the tool usually starts moving to the next block (n+1) before reaching the intersection of the two straight lines 62 and 63, and rotates inward. Figure 2 In FIG. 6 , the path of the inward rotation of the tool is represented by path 61 .

[0037] In the case of inward rotation of the tool, the CNC device 2 can suppress inward rotation by using a precise stop function that does not start the movement of the next block (n+1) until it is confirmed that the remaining distance in the previous block n when starting the next block (n+1) is within a specific range (in-position check).

[0038] The numerical control device 2 performs the in-position check based on the position information (feedback position) received from the servo control device 3. Therefore, the numerical control simulation unit 12 of this embodiment simulates the precise stop function by receiving the position information from the servo control simulation unit 13.

[0039] The numerical control simulation unit 12 can accurately evaluate the machining result (machining accuracy) of the corner portion 60 by simulating the in-situ inspection. On the other hand, a machining result evaluation device that cannot simulate the in-situ inspection cannot accurately evaluate the machining result of the corner portion 60.

[0040] In addition, since the numerical control simulation unit 12 simulates the in-position check, it is possible to simulate the same path 61 as the actual processing, thereby being able to estimate the same processing time as the actual processing. On the other hand, the processing result evaluation device that cannot simulate the in-position check will simulate that the tool rotates inward compared to the actual processing, and thus may estimate the processing time to be shorter than the actual processing.

[0041] In addition, the function of performing tapping by synchronizing the rotation of the spindle and the feed of the drive shaft is called synchronous tapping, and it is activated when the numerical control device 2 receives the rotation angle of the spindle and the position information of the drive shaft from the servo control device 3. Therefore, the numerical control simulation unit 12 receives the rotation angle of the spindle and the position information of the drive shaft from the servo control simulation unit 13, and simulates synchronous tapping based on the rotation angle of the spindle and the position information of the drive shaft. As a result, the numerical control simulation unit 12 can accurately evaluate whether the tapped hole can be accurately processed. On the other hand, the processing result evaluation device that does not receive the rotation angle of the spindle and the position information of the drive shaft cannot simulate synchronous tapping, and therefore cannot accurately evaluate whether the tapped hole can be accurately processed.

[0042] As described above, the processing of the numerical control simulation unit 12 based on the position information received from the servo control simulation unit 13 may affect the machining results such as machining accuracy and machining time. Therefore, in order to accurately evaluate the machining results, it is necessary to accurately simulate the processing that is effective in actual machining as the numerical control simulation unit 12 does.

[0043] The drive shaft simulation unit 14 simulates the motion of the drive shaft and outputs motion information indicating the motion of the drive shaft to the machining result evaluation unit 15. The motion information corresponds to the motion (movement path) of the tool. That is, the motion information includes the position information of the drive shaft.

[0044] The machining result evaluation unit 15 evaluates the machining result based on the motion information sent from the drive axis simulation unit 14. The motion information sent from the drive axis simulation unit 14 is motion information corresponding to the response of the servo control simulation unit 13 and the response of the drive axis simulation unit 14. That is, the motion information sent from the drive axis simulation unit 14 is information reflecting the position information sent from the servo control simulation unit 13 to the numerical control simulation unit 12 and the position information sent from the drive axis simulation unit 14 to the servo control simulation unit 13. Therefore, the machining result evaluation unit 15 evaluates the machining result corresponding to the response of the servo control simulation unit 13 and the response of the drive axis simulation unit 14.

[0045] As described above, the machining result evaluation unit 15 evaluates the machining result based on the action information when simulating the feedback control for the servo control simulation unit 13 and the feedback control for the drive axis simulation unit 14. In addition, the machining result evaluation unit 15 can evaluate the machining result based on the information sent from the numerical control simulation unit 12 or the servo control simulation unit 13.

[0046] Furthermore, the motion information sent from the drive axis simulation unit 14 may be motion information corresponding to the response of the drive axis simulation unit 14. That is, the motion information sent from the drive axis simulation unit 14 may be information that does not reflect the position information sent from the servo control simulation unit 13 to the numerical control simulation unit 12. In this case, the machining result evaluation unit 15 evaluates the machining result corresponding to the response of the drive axis simulation unit 14.

[0047] Furthermore, the machining result evaluation unit 15 may evaluate the machining result based on at least one of the data output from the numerical control simulation unit 12 to the servo control simulation unit 13 and the data output from the servo control simulation unit 13 to the drive axis simulation unit 14 .

[0048] The machining result evaluated by the machining result evaluation unit 15 includes at least one of machining time, machining accuracy, machined surface quality, and power consumption of machining performed by the machine tool 4. The power consumption is power consumed when the tool is driven.

[0049] When evaluating the machining time, the machining result evaluation unit 15 can estimate the machining time based on at least one data (response result) among the data (position command) output from the numerical control simulation unit 12, the response (detected position) of the servo control simulation unit 13, and the response (detected position) of the drive axis simulation unit 14. The machining result evaluation unit 15 can estimate the machining time by calculating the sum of the cycles (times) between the position command or the detected position data. That is, the machining result evaluation unit 15 can estimate the machining time by accumulating the number of data of the position indicated by the position command or the detected position and the output cycle of the data.

[0050] The machining result evaluation unit 15 moves the tool in the virtual space along at least one of the data (position command) output from the numerical control simulation unit 12, the response (detection position) of the servo control simulation unit 13, and the response (detection position) of the drive axis simulation unit 14, while evaluating the machining accuracy and the machined surface quality. The machining result evaluation unit 15 can estimate the shape of the workpiece after machining by performing a machining simulation in which the tool is removed from the area where the workpiece passes. That is, the machining result evaluation unit 15 calculates the shape of the workpiece after machining by removing the area where the workpiece passes from the area where the workpiece is arranged.

[0051] When evaluating the power consumption, the machining result evaluation unit 15 calculates the speed of the drive shaft based on at least one data (response result) among the data (position command) output from the numerical control simulation unit 12, the response (detected position) of the servo control simulation unit 13, and the response (detected position) of the drive shaft simulation unit 14. The machining result evaluation unit 15 integrates the torque command output from the servo control simulation unit 13 to the drive shaft simulation unit 14 and the speed of the drive shaft, thereby being able to estimate the power consumption of the motor.

[0052] The processing result evaluation unit 15 sends the estimated processing result (at least one of the processing time, processing accuracy, processed surface quality, and power consumption) to the display unit 16. The display unit 16 displays the processing result evaluated by the processing result evaluation unit 15.

[0053] Figure 3 This is a flowchart showing the processing procedure of the processing executed by the machining result evaluation device according to Embodiment 1. The numerical control simulation unit 12 analyzes the command code described in the machining program, calculates the position command corresponding to the command code, and outputs it to the servo control simulation unit 13 (step S1).

[0054] The servo control simulation unit 13 simulates the feedback control, calculates the torque instruction corresponding to the feedback control and outputs it to the drive shaft simulation unit 14, so that the error between the position instruction received from the CNC simulation unit 12 and the detected position received from the drive shaft simulation unit 14 becomes smaller (step S2).

[0055] The drive shaft simulation unit 14 simulates the motion of the drive shaft based on the torque command received from the servo control simulation unit 13 and the response characteristics to the torque command, calculates position information indicating the position of the drive shaft as a detection position corresponding to the motion of the drive shaft, and outputs it to the servo control simulation unit 13 (step S3). In addition, the drive shaft simulation unit 14 outputs motion information corresponding to the position information of the drive shaft to the processing result evaluation unit 15.

[0056] The servo control simulation unit 13 calculates a feedback position (position information) corresponding to the detection position received from the drive shaft simulation unit 14, and outputs the calculated feedback position to the numerical control simulation unit 12 (step S4).

[0057] The numerical control simulation unit 12 simulates the processing performed by the numerical control device 2 based on the feedback position received from the servo control simulation unit 13 (step S5). In other words, the numerical control simulation unit 12 simulates the processing that acts based on the feedback position received from the servo control simulation unit 13.

[0058] As described above, the processing result evaluation device 1 simulates the feedback control based on the feedback position.

[0059] The machining result evaluation device 1 determines whether machining in machining simulation is completed (step S6). If machining is not completed (step S6, No), the machining result evaluation device 1 returns to the process of step S1 and repeats the simulation (processes of steps S1 to S6) until machining is completed.

[0060] When the machining is completed (step S6, Yes), the machining result evaluation unit 15 evaluates the machining result based on the motion information sent from the drive axis simulation unit 14 (step S7). In this case, the machining result evaluation unit 15 evaluates the machining result based on at least one of the data output from the numerical control simulation unit 12 to the servo control simulation unit 13, the data output from the servo control simulation unit 13 to the drive axis simulation unit 14, the data (motion information) output from the drive axis simulation unit 14 to the machining result evaluation unit 15, the response of the servo control simulation unit 13, and the response of the drive axis simulation unit 14.

[0061] In addition, the machining result evaluation device 1 may also simulate machining while evaluating the machining result through the machining result evaluation unit 15. That is, the machining result evaluation unit 15 may evaluate the machining result each time data is output from the numerical control simulation unit 12, the servo control simulation unit 13, or the drive axis simulation unit 14. The machining result evaluation unit 15 sends the evaluated machining result to the display unit 16.

[0062] The display unit 16 displays the processing result evaluated by the processing result evaluation unit 15 (step S8). Thus, the operator can refer to the processing result. The operator changes the settings (processing parameters, etc.) of the numerical control device 2 based on the processing result, and operates the numerical control device 2 according to the changed settings.

[0063] As described above, in the processing result evaluation device 1 according to the first embodiment, by returning a response from the drive axis simulation unit 14 to the servo control simulation unit 13, the servo control simulation unit 13 can accurately simulate the process that works in the actual processing. In addition, in the processing result evaluation device 1, by returning a response from the servo control simulation unit 13 to the numerical control simulation unit 12, the numerical control simulation unit 12 can accurately simulate the process that works in the actual processing. Therefore, the processing result evaluation device 1 according to the first embodiment can accurately evaluate the processing result.

[0064] Next, the hardware structure of the processing result evaluation device 1 is described. In the processing result evaluation device 1, the numerical control simulation unit 12, the servo control simulation unit 13, the drive axis simulation unit 14, the processing result evaluation unit 15, and the display unit 16 are implemented by a processing circuit. The processing circuit can be a processor and a memory that executes a program stored in a memory, or it can be dedicated hardware. The processing circuit is also called a control circuit.

[0065] Figure 4 1 is a diagram showing a configuration example of a processing circuit in which the processing circuit included in the processing result evaluation device according to the first embodiment is realized by a computing device and a memory. Figure 4 , a hardware configuration for realizing the processing result evaluation device 1 according to the first embodiment is shown.

[0066] The processing result evaluation device 1 comprises: a computing device 41, which is a processor for performing computing processing; a memory 42, which is used by the computing device 41 as a working area; a storage device 43, which stores programs and data; a communication device 44, which communicates with the outside; an input device 45, which receives input from an operator; and a display device 46.

[0067] Examples of the computing device 41 include a CPU (Central Processing Unit), a processing device, a microprocessor, or a DSP (Digital Signal Processor). Examples of the memory 42 include a semiconductor memory. Examples of the storage device 43 include a nonvolatile or volatile semiconductor memory such as a RAM (Random Access Memory), a ROM (Read Only Memory), a flash memory, an EPROM (Erasable Programmable Read Only Memory), an EEPROM (registered trademark) (Electrically Erasable Programmable Read Only Memory), a magnetic disk, a floppy disk, an optical disk, a compact disk, a mini disk, or a DVD (Digital Versatile Disk).

[0068] The processing result evaluation program stored in the storage device 43 is a program that causes the computing device 41 to execute the procedures or methods executed by the numerical control simulation unit 12, the servo control simulation unit 13, the drive axis simulation unit 14, and the processing result evaluation unit 15. That is, the functions of the numerical control simulation unit 12, the servo control simulation unit 13, the drive axis simulation unit 14, and the processing result evaluation unit 15 are realized by the computing device 41 executing the processing result evaluation program stored in the storage device 43.

[0069] Part of the functions of the display unit 16 are also realized by the computing device 41 executing the display program stored in the storage device 43. The storage device 43 is also a device for storing the display program for realizing part of the functions of the display unit 16. That is, the storage device 43 also stores the display program that causes the computing device 41 to execute a part of the procedure or method executed by the display unit 16.

[0070] An example of the input device 45 is a keyboard, a pointing device, or part or all of a mouse. The display device 46 is a unit that implements the display unit 16. An example of the display device 46 is a liquid crystal display device. The input device 45 and the display device 46 may be integrated. Specifically, the input device 45 and the display device 46 may be implemented by a touch panel.

[0071] Figure 5 FIG. 1 is a diagram showing an example of a processing circuit in which the processing circuit of the processing result evaluation device according to the first embodiment is constituted by dedicated hardware. Figure 5, a processing circuit 51 is shown in which part or all of the numerical control simulation unit 12, servo control simulation unit 13, drive axis simulation unit 14, processing result evaluation unit 15 and display unit 16 of the processing result evaluation device 1 involved in embodiment 1 are implemented by a processing circuit.

[0072] The processing circuit 51 is dedicated hardware and is, for example, a single circuit, a complex circuit, a programmed processor, a parallel programmed processor, an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or a combination thereof.

[0073] Regarding the multiple functions of the numerical control simulation unit 12, the servo control simulation unit 13, the drive axis simulation unit 14, the processing result evaluation unit 15 and the display unit 16, a part of the multiple functions can be implemented by software or firmware, and the remaining parts of the multiple functions can be implemented by dedicated hardware. As described above, the multiple functions of the numerical control simulation unit 12, the servo control simulation unit 13, the drive axis simulation unit 14, the processing result evaluation unit 15 and the display unit 16 can be implemented by hardware, software, firmware or a combination thereof. In addition, the servo control simulation unit 13, the drive axis simulation unit 14, the processing result evaluation unit 15 and a part of the display unit 16 can also be implemented by different processing circuits.

[0074] The processing result evaluation device 1 may be built in the numerical control device 2, or may be connected to the numerical control device 2 via a communication network. Alternatively, the processing result evaluation device 1 may be installed on a server or a cloud.

[0075] As described above, in the processing result evaluation device 1 of the first embodiment, the drive shaft simulation unit 14 outputs the position information indicating the position of the drive shaft to the servo control simulation unit 13, and the servo control simulation unit 13 uses the position information to simulate the feedback control for the drive shaft simulation unit 14. In addition, the processing result evaluation unit 15 evaluates the processing result based on the action information when the feedback control for the drive shaft simulation unit 14 is simulated. Thus, the processing result evaluation device 1 can accurately simulate the processing that works in the actual processing, and thus can accurately evaluate the processing results such as the processing accuracy and the processing time.

[0076] In addition, in the processing result evaluation device 1, the servo control simulation unit 13 outputs the position information to the numerical control simulation unit 12, and the numerical control simulation unit 12 uses the position information to simulate the feedback control for the servo control simulation unit 13. Moreover, the processing result evaluation unit 15 evaluates the processing result based on the action information when the feedback control for the servo control simulation unit 13 and the feedback control for the drive axis simulation unit 14 are simulated. As a result, the processing result evaluation device 1 can more accurately simulate the processing that plays a role in actual processing, and thus can more accurately evaluate the processing results such as processing accuracy and processing time.

[0077] Implementation method 2.

[0078] Next, use Figures 6 to 9 Embodiment 2 will be described. In Embodiment 2, the correspondence relationship between the processing results and the processing conditions is learned in advance, and the processing conditions corresponding to the processing results are determined.

[0079] Figure 6 FIG. 2 is a block diagram showing the structure of a processing condition determination device according to Embodiment 2. Figure 6 Among the structural elements of Figure 1 The same reference numerals are used to represent the same components of the machining result evaluation device 1 of the first embodiment, and duplicate descriptions are omitted. The machining condition determination system 102 includes a machining condition determination device 5 , a numerical control device 2 , a servo control device 3 , and a machine tool 4 .

[0080] The processing condition determination device 5 according to the second embodiment includes the numerical control simulation unit 12, the servo control simulation unit 13, the drive axis simulation unit 14, and the processing result evaluation unit 15 included in the processing result evaluation device 1 according to the first embodiment. In addition, the processing condition determination device 5 according to the second embodiment does not include the display unit 16 included in the processing result evaluation device 1 according to the first embodiment. The processing condition determination device 5 according to the second embodiment includes the machine learning device 22 and the processing condition determination unit 21 that the processing result evaluation device 1 according to the first embodiment does not include. That is, compared with the processing result evaluation device 1 according to the first embodiment, the processing condition determination device 5 includes the machine learning device 22 and the processing condition determination unit 21 instead of the display unit 16. In addition, the processing condition determination device 5 may also include the display unit 16.

[0081] In the second embodiment, the differences from the first embodiment are mainly described. The machine learning device 22 receives the processing result output from the processing result evaluation unit 15. In addition, the machine learning device 22 receives the processing conditions used in the simulation by the numerical control simulation unit 12. The machine learning device 22 performs machine learning in a manner of calculating the correspondence between the processing conditions and the processing results, thereby generating an inference model (trained model). The machine learning device 22 sends the generated inference model to the processing condition determination unit 21.

[0082] The processing condition determination unit 21 calculates appropriate processing conditions for the processing result input by the operator. The processing condition determination unit 21 calculates processing conditions corresponding to the processing result using the estimation model generated by the machine learning device 22 .

[0083] The machining condition determination unit 21 outputs machining parameters included in the determined machining conditions to the numerical control device 2 . Thus, the numerical control device 2 controls the servo control device 3 using the machining parameters sent from the machining condition determination unit 21 .

[0084] Figure 7 1 is a block diagram showing the structure of a processing condition determination unit in the case where the processing condition determination device according to the second embodiment calculates the processing condition corresponding to the processing result using the inference model. The processing condition determination unit 21 includes an inference unit 200. The inference unit 200 includes an inference model trained by machine learning in a manner that the processing result is input from the processing result evaluation unit 15 and the processing condition is output. Specifically, the inference unit 200 inputs the processing result to the inference model that has been machine-learned in advance so that the processing condition is output, thereby outputting the processing condition corresponding to the processing result.

[0085] The processing conditions corresponding to the processing results are processing conditions that can reduce the difference between the desired processing results and the processing results obtained by simulation. That is, the processing condition determination unit 21 calculates the processing conditions that can obtain the desired processing results based on the processing results after simulation.

[0086] Figure 8 2 is a block diagram showing the structure of a machine learning device according to Embodiment 2. The machine learning device 22 is a device for learning an inference model, and learns the correspondence between processing conditions and processing results. The machine learning device 22 includes a data acquisition unit 201 and a learning unit 202 .

[0087] The data acquisition unit 201 acquires a combination of a machining condition and a machining result. Specifically, the data acquisition unit 201 acquires a combination of a machining condition and at least one of machining time, machining accuracy, machined surface quality, and power consumption.

[0088] The data acquisition unit 201 acquires the machining conditions from, for example, the numerical control simulation unit 12. Alternatively, the data acquisition unit 201 may acquire the machining conditions from the servo control simulation unit 13 or the drive axis simulation unit 14. Furthermore, the data acquisition unit 201 acquires machining results corresponding to the machining conditions from, for example, the machining result evaluation unit 15.

[0089] The data acquisition unit 201 may also acquire machining conditions from the numerical control device 2. The data acquisition unit 201 may also acquire machining results of a workpiece actually machined by the machine tool 4. The data acquisition unit 201 outputs a combination of machining conditions and machining results to the learning unit 202.

[0090] The learning unit 202 learns the correspondence between the processing conditions and the processing results according to the data set created based on the combination of the processing conditions and the processing results. Specifically, the learning unit 202 uses the data set created based on the combination of the processing conditions, processing time, processing accuracy, processing surface quality and power consumption output from the data acquisition unit 201 to learn the correspondence between the processing conditions and the processing results. The data set is data obtained by associating state variables and processing conditions with each other. The state variable is at least one of the processing time, processing accuracy, processing surface quality and power consumption. The learning unit 202 adjusts the inference model so that the processing conditions are output from the inference model when the state variables are input to the inference model. The learning unit 202 generates a trained inference model by learning the correspondence between the processing conditions and the processing results.

[0091] The machine learning device 22 generates a trained inference model used by the processing condition determination device 5. That is, the machine learning device 22 is used to learn the processing conditions corresponding to the processing time, processing accuracy, processing surface quality and power consumption calculated by the processing condition determination device 5. The machine learning device 22 may be a device separate from the processing condition determination device 5, or it may be built into the processing condition determination device 5. In the case where the machine learning device 22 is a device separate from the processing condition determination device 5, the machine learning device 22 is connected to the processing condition determination device 5, for example, via a communication network. In addition, the machine learning device 22 may also exist on a server or a cloud. In addition, the processing condition determination unit 21 may be a device separate from the processing condition determination device 5, or it may be built into the processing condition determination device 5. In the case where the processing condition determination unit 21 is a device separate from the processing condition determination device 5, the processing condition determination unit 21 is connected to the processing condition determination device 5, for example, via a communication network. In addition, the processing condition determination unit 21 may exist on a server or a cloud.

[0092] The learning unit 202 learns the correspondence between the processing conditions and the processing results through so-called supervised learning, for example, according to a neural network model. Supervised learning refers to a model in which a large number of data sets of certain inputs and results (labels) are given to a learning device, thereby learning the features existing in the data set and inferring the results based on the inputs.

[0093] A neural network is composed of an input layer composed of multiple neurons, an intermediate layer (hidden layer) composed of multiple neurons, and an output layer composed of multiple neurons. The intermediate layer can be one layer or more than two layers.

[0094] Fig. 9 is a diagram for explaining an example of a neural network used by the machine learning device according to Embodiment 2. Fig. 9 In the three-layer neural network shown, when multiple inputs are input to the input layer (X1-X3), the value obtained by multiplying the input value by the weight W1 (w11-w16) is input to the intermediate layer (Y1-Y2). The value obtained by multiplying the value input to the intermediate layer (Y1-Y2) by the weight W2 (w21-w26) is output from the output layer (Z1-Z3). The output result changes according to the values ​​of the weight W1 and the weight W2.

[0095] For example, the neural network learns the correspondence between the machining conditions and the machining results by so-called supervised learning according to the data set created based on the combination of the machining conditions, machining time, machining accuracy, machined surface quality, and power consumption acquired by the data acquisition unit 201. That is, the neural network learns by adjusting the weights W1 and W2 so that the machining time, machining accuracy, machined surface quality, and power consumption are input to the input layer and the result output from the output layer is close to the machining conditions.

[0096] The neural network can learn the correspondence between processing conditions and processing results through so-called unsupervised learning. Unsupervised learning is a method of learning the following device, which learns what kind of distribution the input data has by only giving a large amount of input data to the machine learning device 22, and even if the corresponding teacher output data is not given, it compresses, classifies and shapes part or all of the input data. For example, the neural network can cluster those with similar features in the data set. The neural network uses the obtained results, sets a certain benchmark and distributes the output that optimizes the result, thereby enabling the prediction of the output.

[0097] As a problem setting intermediate between unsupervised learning and supervised learning, there is also learning called semi-supervised learning. Semi-supervised learning is learning in which there is a data set with only a portion of input and output, and the rest is input data only.

[0098] The learning unit 202 can learn the correspondence between the processing conditions and the processing results according to the data sets created for the plurality of processing condition determination devices 5. The learning unit 202 can acquire data sets from the plurality of processing condition determination devices 5 used at the same site, or can learn the correspondence between the processing conditions and the processing results using data sets collected from the plurality of processing condition determination devices 5 independently operated at different sites.

[0099] The processing condition determination device 5 that collects the data set can be added to the object in the middle, and the processing condition determination device 5 can also be removed from the object. The machine learning device 22 that learns the correspondence between the processing conditions and the processing results is installed in the processing condition determination device 5 that is separate from the machine learning device 22. The processing condition determination device 5 that is separate can re-learn and update the correspondence between the processing conditions and the processing results.

[0100] Deep learning that learns to extract feature quantities themselves can be used as a learning algorithm used by the learning unit 202. The learning unit 202 can perform machine learning according to other well-known methods, such as genetic programming, functional logic programming, or support vector machines.

[0101] Fig.10 1 is a flowchart showing the processing sequence of the processing executed by the processing condition determination device according to the second embodiment. Figure 3 The same processing as steps S1 to S7 executed by the processing result evaluation device 1 described in .

[0102] In the processing condition determination device 5, the processing result evaluation unit 15 outputs the evaluated processing result to the machine learning device 22. The machine learning device 22 generates an inference model (inference unit 200) for calculating the correspondence between the processing conditions and the processing results (step S9). The processing condition determination unit 21 calculates the processing conditions corresponding to the processing results using the inference model (step S10).

[0103] The machining condition determination unit 21 outputs machining parameters included in the determined machining conditions to the numerical control device 2 . Thus, the numerical control device 2 controls the servo control device 3 using the machining parameters sent from the machining condition determination unit 21 .

[0104] As described above, the processing condition determination device 5 according to the second embodiment can accurately simulate the processing that works in actual processing by returning a response from the servo control simulation unit 13 to the numerical control simulation unit 12. Therefore, the processing condition determination device 5 according to the second embodiment can accurately evaluate the processing result.

[0105] In addition, the processing condition determination device 5 involved in the second embodiment uses the inference model that has learned the correspondence between the processing conditions and the accurately evaluated processing results to calculate the processing conditions corresponding to the processing results. The processing condition determination device 5 calculates the processing conditions corresponding to the processing results specified by the operator.

[0106] The processing condition determination device 5 can determine the processing conditions that satisfy the processing results desired by the operator when calculating the processing conditions corresponding to the processing results specified by the operator. Therefore, the processing condition determination device 5 involved in the second embodiment can determine the processing conditions that satisfy the processing results desired by the operator only by allowing the operator to input information indicating the desired processing results.

[0107] At least a part of the functions of the processing condition determination unit 21 in the second embodiment can be realized by a computing device that executes a program stored in a storage device. The storage device is a storage device for storing a program that finally executes at least a part of the steps executed by the processing condition determination unit 21, and is the same storage device as the storage device 43. The computing device in this case is the same computing device as the computing device 41. In addition, at least a part of the functions of the processing condition determination unit 21 can be realized by a processing circuit. The processing circuit is the same as in Figure 4 The processing circuit described in Figure 5 The processing circuit 51 described in is the same processing circuit.

[0108] At least a part of the functions of the inference unit 200 of the processing condition determination unit 21 in the second embodiment can be realized by a computing device that executes a program stored in a storage device. The storage device is a storage device for storing a program that finally executes at least a part of the steps executed by the inference unit 200, and is the same storage device as the storage device 43. The computing device in this case is the same computing device as the computing device 41. At least a part of the functions of the inference unit 200 can be realized by a processing circuit. The processing circuit is the same as in Figure 4 The processing circuit described in Figure 5 The processing circuit 51 described in is the same processing circuit.

[0109] At least a part of the functions of the data acquisition unit 201 and the learning unit 202 of the machine learning device 22 involved in Implementation Example 2 can be realized by a computing device that executes a program stored in a storage device. The storage device is a storage device for storing a program that finally executes at least a part of the steps executed by the data acquisition unit 201 and the learning unit 202, and is the same storage device as the storage device 43. The computing device in this case is the same computing device as the computing device 41. At least a part of the functions of the data acquisition unit 201 and the learning unit 202 can be realized by a processing circuit. The processing circuit is the same as in Figure 4 The processing circuit described in Figure 5 The processing circuit 51 described in is the same processing circuit.

[0110] In addition, at least part of the function of the processing condition determination device 5 can be achieved by Figure 4 The processing circuit described in Figure 5 The processing circuit 51 described in the above is implemented by the same processing circuit.

[0111] As described above, in the processing condition determination device 5 of the second embodiment, the drive shaft simulation unit 14 outputs the position information indicating the position of the drive shaft to the servo control simulation unit 13, and the servo control simulation unit 13 uses the position information to simulate the feedback control for the drive shaft simulation unit 14. Moreover, the processing result evaluation unit 15 evaluates the processing result based on the action information when the feedback control for the drive shaft simulation unit 14 is simulated. In addition, the machine learning device 22 generates an inference model for inferring the processing conditions based on the processing results, and the processing condition determination unit 21 determines the processing conditions corresponding to the processing results using the inference model. Thus, the processing condition determination device 5 can determine the processing conditions corresponding to the processing results obtained by accurately simulating the processing that works in the actual processing.

[0112] In addition, in the processing condition determination device 5, the servo control simulation unit 13 outputs the position information to the numerical control simulation unit 12, and the numerical control simulation unit 12 uses the position information to simulate the feedback control for the servo control simulation unit 13. Moreover, the processing result evaluation unit 15 evaluates the processing result based on the action information when the feedback control for the servo control simulation unit 13 and the feedback control for the drive axis simulation unit 14 are simulated. As a result, the processing condition determination device 5 can more accurately simulate the processing that works in the actual processing, and thus can determine the processing conditions corresponding to the processing result simulated more accurately.

[0113] The configuration described in the above embodiment is merely an example, and may be combined with other known technologies, the embodiments may be combined with each other, and part of the configuration may be omitted or changed without departing from the gist.

[0114] Description of the label

[0115] 1 machining result evaluation device, 2 numerical control device, 3 servo control device, 4 machine tool, 5 machining condition determination device, 12 numerical control simulation unit, 13 servo control simulation unit, 14 drive axis simulation unit, 15 machining result evaluation unit, 16 display unit, 21 machining condition determination unit, 22 machine learning device, 41 computing unit, 42 memory, 43 storage device, 44 communication device, 45 input device, 46 display device, 51 processing circuit, 60 angular portion, 61 path, 62, 63 straight line, 101 machining result evaluation system, 102 machining condition determination system, 200 inference unit, 201 data acquisition unit, 202 learning unit.

Claims

1. A processing result evaluation device for evaluating a processing result of a processing performed by a working machine driven by a servo control device, The processing result evaluation device is characterized by having: a numerical control simulation unit that simulates the operation of a numerical control device that controls the servo control device and outputs a position command to a drive shaft of the machine tool; a servo control simulation unit that simulates the operation of the servo control device based on the position command and outputs a torque command to the drive shaft; a drive shaft simulation unit that simulates the operation of the drive shaft based on the torque command; and a processing result evaluation unit that evaluates the processing result based on information corresponding to the operation of the drive shaft, The drive shaft simulation unit outputs position information indicating the position of the drive shaft to the servo control simulation unit, The servo control simulation unit simulates feedback control to the drive shaft simulation unit using the position information. The machining result evaluation unit evaluates the machining result when feedback control to the drive axis simulation unit is simulated.

2. The processing result evaluation device according to claim 1, characterized in that: The information corresponding to the movement of the drive shaft is the position information, The processing result evaluation unit evaluates the processing result based on the position information.

3. The processing result evaluation device according to claim 1, characterized in that: The servo control simulation unit outputs the position information to the numerical control simulation unit, The numerical control simulation unit simulates feedback control to the servo control simulation unit using the position information. The machining result evaluation unit evaluates the machining result when feedback control to the servo control simulation unit and feedback control to the drive axis simulation unit are simulated.

4. The processing result evaluation device according to claim 3, characterized in that: The information corresponding to the movement of the drive shaft is the position information outputted from the servo control simulation unit to the numerical control simulation unit. The processing result evaluation unit evaluates the processing result based on the position information output from the servo control simulation unit to the numerical control simulation unit.

5. The processing result evaluation device according to claim 3, characterized in that: The information corresponding to the movement of the drive shaft is the position instruction output by the numerical control simulation unit. The machining result evaluation unit evaluates the machining result based on the position command output by the numerical control simulation unit.

6. The processing result evaluation device according to any one of claims 1 to 5, characterized in that: The machining result evaluation unit evaluates at least one of machining time, machining accuracy, machined surface quality, and power consumption of machining performed by the machine tool.

7. A processing result evaluation method for evaluating a processing result of processing performed by a machine tool driven by a servo control device, The processing result evaluation method is characterized by comprising: A numerical control simulation step, in which a numerical control simulation unit of the processing result evaluation device simulates the action of a numerical control device that controls the servo control device, and outputs a position instruction to a drive shaft of the machine tool; a servo control simulation step, wherein the servo control simulation unit of the processing result evaluation device simulates the operation of the servo control device based on the position command and outputs a torque command to the drive shaft; a drive shaft simulation step, wherein a drive shaft simulation unit of the machining result evaluation device simulates the movement of the drive shaft based on the torque command; and a processing result evaluation step, wherein a processing result evaluation unit of the processing result evaluation device evaluates the processing result based on information corresponding to the movement of the drive shaft, In the drive shaft simulation step, the drive shaft simulation unit outputs position information indicating the position of the drive shaft to the servo control simulation unit. In the servo control simulation step, the servo control simulation unit simulates feedback control to the drive shaft simulation unit using the position information. In the machining result evaluation step, the machining result evaluation unit evaluates the machining result when feedback control to the drive axis simulation unit is simulated.

8. The processing result evaluation method according to claim 7, characterized in that: In the servo control simulation step, the servo control simulation unit outputs the position information to the numerical control simulation unit. In the numerical control simulation step, the numerical control simulation unit simulates feedback control to the servo control simulation unit using the position information. In the machining result evaluation step, the machining result evaluation unit evaluates the machining result when feedback control to the servo control simulation unit and feedback control to the drive axis simulation unit are simulated.

9. A processing condition determination device for determining processing conditions when a working machine driven by a servo control device performs processing, The processing condition determination device is characterized by having: a numerical control simulation unit that simulates the operation of a numerical control device that controls the servo control device and outputs a position command to a drive shaft of the machine tool; a servo control simulation unit that simulates the operation of the servo control device based on the position command and outputs a torque command to the drive shaft; a drive shaft simulation unit that simulates the motion of the drive shaft based on the torque command and outputs motion information indicating the motion of the drive shaft; a processing result evaluation unit that evaluates a processing result of processing performed by the machine tool based on information corresponding to the operation of the drive shaft; a machine learning device that generates an inference model for inferring the processing conditions based on the processing results; and a processing condition determination unit that uses the inference model to determine processing conditions corresponding to the processing result input by the operator, The drive shaft simulation unit outputs position information indicating the position of the drive shaft to the servo control simulation unit, The servo control simulation unit simulates feedback control to the drive shaft simulation unit using the position information. The machining result evaluation unit evaluates the machining result when feedback control to the drive axis simulation unit is simulated.

10. The processing condition determination device according to claim 9, characterized in that: The servo control simulation unit outputs the position information to the numerical control simulation unit, The numerical control simulation unit simulates feedback control to the servo control simulation unit using the position information. The machining result evaluation unit evaluates the machining result when feedback control to the servo control simulation unit and feedback control to the drive axis simulation unit are simulated.

11. A method for determining machining conditions, the method comprising determining machining conditions when a machine tool driven by a servo control device performs machining, The processing condition determination method is characterized by comprising: A numerical control simulation step, in which a numerical control simulation unit of a processing condition determination device simulates the action of a numerical control device that controls the servo control device, and outputs a position instruction to a drive shaft of the machine tool; a servo control simulation step, wherein the servo control simulation unit of the processing condition determination device simulates the operation of the servo control device based on the position command and outputs a torque command to the drive shaft; a drive shaft simulation step, wherein a drive shaft simulation unit of the machining condition determination device simulates the motion of the drive shaft based on the torque command and outputs motion information indicating the motion of the drive shaft; a machining result evaluation step in which a machining result evaluation unit of the machining condition determination device evaluates a machining result of machining performed by the machine tool based on information corresponding to the operation of the drive shaft; a machine learning step, wherein a machine learning device generates an inference model for inferring the processing conditions based on the processing results; and a processing condition determination step, wherein a processing condition determination unit determines a processing condition corresponding to a processing result input by an operator using the inference model, In the drive shaft simulation step, the drive shaft simulation unit outputs position information indicating the position of the drive shaft to the servo control simulation unit. In the servo control simulation step, the servo control simulation unit simulates feedback control of the drive axis simulation unit using the position information. In the machining result evaluation step, the machining condition determination unit evaluates the machining result when feedback control to the drive axis simulation unit is simulated.

12. The method for determining processing conditions according to claim 11, characterized in that: The servo control simulation unit outputs the position information to the numerical control simulation unit, The numerical control simulation unit simulates feedback control to the servo control simulation unit using the position information. The machining result evaluation unit evaluates the machining result when feedback control to the servo control simulation unit and feedback control to the drive axis simulation unit are simulated.

Images