Servo adjusting system

Through the virtualization of the servo motor and control object model, the control parameters are automatically adjusted using virtual feedback information, which solves the problems of high equipment costs and complex operation in the existing technology, and achieves high-precision and rapid servo adjustment.

CN119032506APending Publication Date: 2024-11-26FANUC LTD
View PDF 3 Cites 0 Cited by

Patent Information

Application Number
CN202280095032.7
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2022-04-25
Publication Date
2024-11-26

AI Technical Summary

Technical Problem

The existing servo adjustment technology requires additional equipment to increase costs, and users need to decide parameter values, resulting in a large operating burden and prone to errors.

Method used

Using a virtualized servo motor model and control object model, the virtual control device executes the evaluation program, generates virtual feedback information to automatically adjust the control parameters, and realizes high-precision servo adjustment.

Benefits of technology

Servo adjustment can be automatically performed with high precision in a short period of time without adding equipment, reducing user operation burden, preventing operational errors, and improving the efficiency of servo adjustment.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119032506A_ABST
    Figure CN119032506A_ABST
Patent Text Reader

Abstract

Provided is a servo adjustment device capable of automatically performing servo adjustment with high precision and in a short time without requiring additional equipment. A servo adjustment system (1) adjusts control parameter setting information of a servo motor controlled by a control device of an industrial machine, and is provided with: a servo motor model (30) obtained by virtualizing the operation of the servo motor; a virtual control device (20) that virtually controls the servomotor model (30) by executing an evaluation program on the basis of the control parameter setting information; and a servo adjustment device (10) that determines control parameter setting information on the basis of virtual feedback information obtained by executing the evaluation program multiple times on the basis of different control parameter setting information in the virtual control device (20).
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present disclosure relates to a servo adjustment system. Background Art

[0002] Conventionally, there are known techniques for adjusting control parameters of servo motors (hereinafter referred to as servo adjustment) such as gain / filter adjustment, feedforward adjustment, and acceleration / deceleration adjustment. These servo adjustment techniques are required to improve adjustment accuracy and shorten adjustment time.

[0003] However, in order to perform servo adjustment, feedback information is required when the servo motor or machine tool that is the object of control actually moves. Therefore, during the process of performing servo adjustment, the object of control cannot be used for other purposes. In addition, the time required to actually move the object of control and obtain feedback information cannot be shortened.

[0004] In contrast, a technique for performing servo adjustment so that the movement of the tool tip matches the command has been proposed (see, for example, Patent Document 1). Another technique for assisting servo adjustment using a virtual model has been proposed (see, for example, Patent Document 2).

[0005] Prior art literature

[0006] Patent Literature

[0007] Patent Document 1: Japanese Patent Application Publication No. 2006-172149

[0008] Patent Document 2: Japanese Patent Application Publication No. 2017-167607 Summary of the invention

[0009] Problems to be solved by the invention

[0010] However, the technique of Patent Document 1 requires additional equipment such as an acceleration sensor, which increases the cost. In addition, the technique of Patent Document 2 requires the user to determine parameter values, which places a heavy workload on the user and causes operational errors.

[0011] The present disclosure has been made in view of the above circumstances, and an object of the present disclosure is to provide a servo adjustment device that can automatically perform servo adjustment with high accuracy and in a short time without adding equipment.

[0012] Means for solving problems

[0013] One method disclosed herein is a servo adjustment system for adjusting control parameter setting information of a servo motor controlled by a control device of an industrial machine, the servo adjustment system comprising: a servo motor model obtained by virtualizing the action of the servo motor; a virtual control device, which executes an evaluation program according to the control parameter setting information, thereby virtually controlling the servo motor model; and a servo adjustment device, which determines the control parameter setting information according to virtual feedback information, wherein the virtual feedback information is information obtained by executing the evaluation program multiple times in the virtual control device according to different control parameter setting information.

[0014] Effects of the Invention

[0015] According to the present disclosure, it is possible to provide a servo adjustment device that can automatically perform servo adjustment with high accuracy and in a short time without adding equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] FIG. 1 is a block diagram showing a configuration of a servo adjustment system according to a first embodiment.

[0017] FIG. 2 is a flowchart showing the procedure of the servo adjustment process executed by the servo adjustment system according to the first embodiment.

[0018] FIG. 3 is a flowchart showing the procedure of feedback information generation processing.

[0019] Figure 4 It is a diagram showing servo parameter information.

[0020] Figure 5 This is a diagram showing servo motor model information.

[0021] Figure 6 It is a diagram showing the control object model information.

[0022] Figure 7 It is a diagram showing instruction information.

[0023] Figure 8 This is a diagram showing the servo motor model operation information taking into account the motor friction coefficient.

[0024] Fig. 9 This is a diagram showing the servo motor model operation information taking into account the motor friction coefficient and the feed axis friction coefficient.

[0025] Fig.10 This is a flowchart showing the procedure of parameter setting determination processing.

[0026] Fig.11 This is a diagram showing an example of parameter adjustment.

[0027] Fig.12It is a block diagram showing the configuration of a servo adjustment system according to a second embodiment.

[0028] Fig.13 This is a block diagram showing the configuration of a servo adjustment system according to a modified example of the second embodiment.

[0029] Fig.14 This is a flowchart showing the procedure of the servo adjustment process executed by the servo adjustment system according to the second embodiment.

[0030] Fig.15 This is a flowchart showing the procedure of the provisional determination processing of parameter settings.

[0031] Fig.16 This is a diagram showing an example of a parameter setting mode.

[0032] Fig.17 This is a diagram showing an example of parameter settings applied to a plurality of virtual environments.

[0033] Fig.18 This is a flowchart showing the procedure of parameter setting determination processing.

[0034] Fig.19 This is a diagram showing an example of a learning result. DETAILED DESCRIPTION

[0035] Hereinafter, embodiments of the present disclosure will be described in detail with reference to the drawings. In the description of the second and third embodiments, the same reference numerals are given to the same configurations as those of the first embodiment, and the description thereof is appropriately omitted.

[0036] [First embodiment]

[0037] The servo adjustment system 1 of the first embodiment is a system for adjusting control parameter setting information (hereinafter referred to as parameter setting information) of a servo motor controlled by a control device of an industrial machine such as a machine tool, for example. FIG. 1 is a block diagram showing the structure of the servo adjustment system 1 of the first embodiment. As shown in FIG. 1 , the servo adjustment system 1 of the first embodiment includes: a servo adjustment device 10, a virtual control device 20, a servo motor model 30, and a control object model 40. The virtual control device 20, the servo motor model 30, and the control object model 40 constitute a virtual environment 50.

[0038] The servo adjustment device 10 and the virtual control device 20 are computers respectively composed of hardware such as a CPU (Central Processing Unit) and other processing units, HDD (Hard Disk Drive) or SSD (Solid State Drive) and other auxiliary storage units for storing various computer programs, RAM (Random Access Memory) and other main storage units for storing data temporarily required when the processing unit executes the computer program, keyboards and other operating units for operators to perform various operations, and displays and other display units for displaying various information to the operator. These servo adjustment devices 10 and virtual control devices 20 and other devices can send and receive various signals to each other, and their communication methods are not particularly limited.

[0039] The servo adjustment device 10 and / or the virtual control device 20 are connected to a numerical control device (CNC: Computerized Numerical Control) not shown in the figure, which corresponds to a control device of an industrial machine such as a machine tool, so as to be communicable. The servo parameter information and the like required for the servo adjustment of the present embodiment described later are part of the CNC parameters stored in the numerical control device and are obtained from the numerical control device. In addition, the parameter setting information after the servo adjustment of the present embodiment is sent to the numerical control device for controlling the actual machine.

[0040] The servo adjustment device 10 performs control parameter adjustment (hereinafter referred to as servo adjustment) of the servo motor, such as gain / filter adjustment, feedforward adjustment, acceleration / deceleration adjustment, etc. Specifically, the servo adjustment device 10 obtains virtual feedback information (hereinafter referred to as virtual FB information) obtained by executing the evaluation program multiple times according to different parameter setting information in the virtual control device 20 described later, and determines the parameter setting information based on the virtual feedback information, thereby performing servo adjustment. The adjusted parameter setting information is sent to the virtual control device 20 and the numerical control device.

[0041] Therefore, the servo adjustment device 10 has: a virtual feedback information acquisition unit not shown in the figure, which acquires virtual FB information sent from the virtual control device 20; a parameter setting determination unit not shown in the figure, which determines parameter setting information based on multiple virtual FB information obtained by executing different parameter setting information; and a parameter setting sending unit not shown in the figure, which sends the determined parameter setting information to the virtual control device 20 and the numerical control device.

[0042] The virtual control device 20 executes the evaluation program multiple times according to different parameter setting information, generates command information to be transmitted to the servo motor model 30 described later, and thereby virtually controls the servo motor model 30. In addition, thereby, the virtual control device 20 virtually drives the control target model 40 such as a machine tool described later. The virtual control device 20 sends feedback information (hereinafter also referred to as FB information) obtained by virtually controlling these servo motor model 30 and the control target model 40 to the servo adjustment device 10. In addition, the current parameter setting information sent from the servo adjustment device 10 is applied to the virtual control device 20.

[0043] Here, the evaluation program is generally different from the actual processing program that takes a long time to process, and is a program created in a way that can efficiently perform servo adjustment in a short time. Specifically, the evaluation program is, for example, a program that specifies the axial movement distance and feed speed corresponding to various processing shapes such as a circle, a four-sided, and a four-sided with an angle. However, it is also possible to use the actual processing program used by the user in processing as the evaluation program instead of the evaluation program.

[0044] The servo motor model 30 is a model that virtualizes the actions and characteristics of the servo motor. That is, the virtual environment 50 of the present embodiment has a servo motor model 30 that virtualizes the actions of a servo motor such as a machine tool. Specifically, the servo motor model 30 is a model that virtualizes at least one of the non-attenuated natural angular vibration frequency, the attenuation coefficient, the advance instruction time, the motor inertia, and the motor friction coefficient. As a result, it is possible to perform action simulation close to the actual machine in the virtual environment 50, and obtain virtual feedback information (hereinafter also referred to as virtual FB information) that is close to the situation of causing the actual machine to act.

[0045] The control object model 40 is, for example, a model that virtualizes the actions and characteristics of industrial machinery such as machine tools. That is, the virtual environment 50 of the present embodiment has a control object model 40 that virtualizes industrial machinery such as machine tools. Specifically, the control object model 40 is a model that virtualizes at least one of a spring constant, a feed axis inertia, a feed axis friction coefficient, and a disturbance torque. As a result, an action simulation that is closer to the actual machine can be performed in the virtual environment 50, and virtual FB information that is closer to the situation of causing the actual machine to operate can be obtained.

[0046] As described above, in this embodiment, since the generation of command information to the servo motor model 30 in the virtual control device 20 and the generation of virtual FB information in the servo motor model 30 and the controlled object model 40 do not require real time, servo adjustment can be performed at high speed.

[0047] Next, the servo adjustment process performed by the servo adjustment system 1 of the present embodiment will be described in detail with reference to Fig. 2. Fig. 2 is a flowchart showing the servo adjustment process performed by the servo adjustment system 1 of the first embodiment. The servo adjustment process is started, for example, in response to an input operation of the servo adjustment device 10 by a user.

[0048] In step S11, the virtual control device 20 analyzes and executes the evaluation program. More specifically, the virtual control device 20 executes the evaluation program based on the parameter setting information (hereinafter, also referred to as parameter setting) of the servo motor currently applied to the virtual control device 20. Then, the process proceeds to step S12. In addition, the parameter setting is adjusted and changed by the servo adjustment process of this process.

[0049] In step S12, the virtual control device 20 generates command information for the servo motor. Specifically, in the above-mentioned step S11, the virtual control device 20 analyzes and executes the evaluation program, thereby generating command information for the servo motor. Then, the process proceeds to step S13.

[0050] In step S13, the virtual control device 20 generates virtual FB information. Specifically, based on the instruction information to the servo motor generated in step S12, the virtual control device 20 virtually controls the servo motor model 30 and the control object model 40 to operate, thereby generating virtual FB information. Then, the process proceeds to step S14. In addition, the virtual FB information generation process will be described in detail later.

[0051] In step S14, the virtual control device 20 transmits the virtual FB information generated in step S13 to the servo adjustment device 10. Thereafter, the process proceeds to step S15.

[0052] In step S15, the servo adjustment device 10 acquires the virtual FB information transmitted from the virtual control device 20. Thereafter, the process proceeds to step S16.

[0053] In step S16, the servo adjustment device 10 determines parameter settings based on the acquired virtual FB information. Then, the process proceeds to step S17. The parameter setting determination process will be described in detail later.

[0054] In step S17, the servo adjustment device 10 transmits the parameter setting determined in step S16 to the virtual control device 20. Thereafter, the process proceeds to step S18.

[0055] In step S18, the virtual control device 20 obtains the parameter setting sent from the servo adjustment device 10. The parameter setting newly obtained this time is stored in the virtual control device 20 and applied to the next servo adjustment process. Thereafter, the process proceeds to step S19.

[0056] In step S19, the servo adjustment device 10 determines whether the servo adjustment is completed. Specifically, for example, the servo adjustment device 10 maintains a list of adjustment parameters, and determines whether the servo adjustment is completed based on whether the adjustment of all parameters in the list is completed. In addition, in the adjustment of each parameter, it is determined that the adjustment is not completed before the decision of the parameter setting based on different virtual FB information is performed at least twice, that is, multiple times, as described later, for example, when the adjustment amount of the parameter is less than 1%, it is determined that the adjustment is completed. However, it is also possible to determine whether the servo adjustment is completed based on the judgment of the user. If the judgment is "no", it returns to step S11, and if it is yes, the present process ends.

[0057] According to the servo adjustment process described above, the parameter setting information is determined and adjusted based on the virtual FB information obtained by analyzing and executing the evaluation program a plurality of times according to different parameter setting information in the virtual control device 20 .

[0058] Next, refer to Figure 3~ Figure 6 The virtual FB information generation process in step S13 of Fig. 2 described above will be described in detail. Fig. 3 is a flowchart showing the procedure of the virtual FB information generation process.

[0059] In step S21, the virtual control device 20 adds the servo parameter information to the virtual FB information generation element. That is, the servo parameter information is added to the virtual FB information generation element regardless of the presence or absence of the servo motor model 30 and the controlled object model 40. Then, the process proceeds to step S22.

[0060] Here, the virtual FB information generation element refers to information required to generate virtual FB information in the virtual environment 50. The servo parameter information added as the virtual FB information generation element becomes the basis of the virtual FB information generation element. The servo parameter information is included in the CNC parameters stored in the numerical control device (CNC) not shown in the figure and connected to the servo adjustment system 1 of the present embodiment so as to be communicable, and is sent from the numerical control device and stored in the virtual control device 20.

[0061] Figure 4 is a diagram showing servo parameter information. Figure 4As shown, as servo parameter information, for example, servo loop gain, speed integral gain, speed proportional gain, phase compensation gain, speed loop gain multiplier during cutting, gain multiplier in high-speed HRV (High Response Vector) current control, offset of speed integral gain, offset of speed proportional gain, load inertia ratio, maximum torque of amplifier, feedforward coefficient, feedforward coefficient when using EGB (electronic gearbox), speed feedforward coefficient, feedforward coefficient during cutting, speed feedforward coefficient during cutting, etc. are exemplified.

[0062] Returning to FIG. 3 , in step S22, the virtual control device 20 determines whether the servo motor model 30 is present in the virtual environment 50. In the servo adjustment system 1 of the present embodiment, the servo motor model 30 is present in the virtual environment 50, so the determination is "yes", and the process proceeds to step S23. On the other hand, in the case where the servo motor model 30 is not present, the determination is "no", and the process proceeds to step S26, where the virtual control device 20 generates virtual FB information based on the virtual FB information generation element including the servo parameter information, and the present process ends.

[0063] In step S23, the virtual control device 20 adds the servo motor model information to the virtual FB information generation element. Thus, the servo parameter information and the servo motor model information are included in the virtual FB information generation element. Then, the process proceeds to step S24.

[0064] Here, the servo motor model information is different from the above-mentioned servo parameter information, is not included in the CNC parameters, and is information that is separately registered and stored in the virtual control device 20 through input such as file input or screen operation by the user. Figure 5 is a diagram showing the servo motor model information. Figure 5 As shown, as the servo motor model information, for example, non-damped natural angular vibration frequency, damping coefficient, advance command time, motor inertia, motor friction coefficient, etc. are exemplified.

[0065] Returning to FIG. 3 , in step S24, the virtual control device 20 determines whether or not the control object model 40 is present in the virtual environment 50. In the servo adjustment system 1 of the present embodiment, the control object model 40 is present in the virtual environment 50, so the determination is "yes", and the process proceeds to step S25. On the other hand, in the case where the control object model 40 is not present, the determination is "no", and the process proceeds to step S26, and the virtual control device 20 generates virtual FB information based on virtual FB information generation elements including servo parameter information and servo motor model information, and the process ends. In this case, the virtual FB information is generated based on the virtual FB information generation elements including the servo motor model information, so that virtual FB information that is closer to the situation of operating the real machine can be generated.

[0066] In step S25, the virtual control device 20 adds the controlled object model information to the virtual FB information generation element. Thus, the virtual FB information generation element includes the servo parameter information, the servo motor model information, and the controlled object model information.

[0067] Here, the controlled object model information is not included in the CNC parameters, as is the case with the servo motor model information described above, but is separately registered and stored in the virtual controller 20 through file input, screen operation by the user, and the like. Figure 6 is a diagram showing the control object model information. Figure 6 As shown in FIG. 1 , as the controlled object model information, for example, a spring constant, a feed axis inertia, a feed axis friction coefficient, a disturbance torque, etc. are exemplified.

[0068] Returning to Fig. 3, after the processing of step S25 is executed, the process proceeds to step S26, and the virtual control device 20 generates virtual FB information based on the virtual FB information generation element including the servo parameter information, the servo motor model information, and the controlled object model information, and ends this processing. In this case, the virtual FB information is generated based on the virtual FB information generation element including the servo motor model information and the controlled object model information, so that the virtual FB information that is closer to the actual machine operation can be generated.

[0069] Regarding the virtual FB information generation process of the present embodiment described above, for example, Figure 7~Figure 9 An example of generating virtual FB information by calculating the difference (pulse number difference or time difference) between the servo motor model operation information and the command information, that is, the error amount, by the virtual control device 20 is described in detail. Figure 7 It is a diagram showing instruction information. Figure 8 This is a diagram showing the servo motor model operation information taking into account the motor friction coefficient. Fig. 9 is a diagram showing the servo motor model motion information taking into account the motor friction coefficient and the feed axis friction coefficient. Figure 8 and Fig. 9 In, with Figure 7 In the regions with different shades of pulses of the instruction information, the light-shaded region indicates a region where the number of pulses is smaller than the number of pulses of the instruction information, and the dark-shaded region indicates a region where the number of pulses is larger than the number of pulses of the instruction information.

[0070] like Figure 8 As shown in FIG. 1 , it can be seen that the pulse ratio of the servo motor model motion information considering the motor friction coefficient included in the servo motor model information is Figure 7 The pulse of the command information shown is delayed by a time Δt aThis is because, if the motor friction coefficient of the servo motor model 30 is taken into consideration, a delay time deviation Δt is generated before the servo motor model 30 actually rotates / stops with respect to the command information. a .

[0071] In addition, if Fig. 9 As shown in FIG. 1 , it can be seen that the pulse and value of the servo motor model motion information which takes into account the feed axis friction coefficient included in the control object model information in addition to the motor friction coefficient included in the servo motor model information. Figure 7 Compared with the pulse of the command information shown, it is further delayed by time Δt a Large time Δt b This is because, if the motor friction coefficient of the servo motor model 30 and the feed axis friction coefficient of the controlled object model 40 are taken into consideration, a delay time deviation Δt is generated before the servo motor model 30 actually rotates / stops relative to the command information. b .

[0072] Thus, for example, when looking at time t 4 , the number of pulses of the command information is 4, whereas the number of pulses of the servo motor model action information taking into account the motor friction coefficient of the servo motor model 30 is 3, and an error amount 1 as the difference between the two can be calculated. Similarly, the number of pulses of the servo motor model action information taking into account the motor friction coefficient of the servo motor model 30 and the feed axis friction coefficient of the controlled object model 40 is 2, and an error amount 2 as the difference from the command information can be calculated. In this way, the error amount as the difference from the command information can be calculated, and virtual FB information can be generated based on the calculated error amount.

[0073] Next, refer to Fig.10 and Fig.11 The parameter setting determination process in step S16 of FIG. 2 described above will be described in detail. Fig.10 This is a flowchart showing the procedure of parameter setting determination processing.

[0074] In step S31, the servo adjustment device 10 selects a parameter (hereinafter referred to as an adjustment parameter) as a target of servo adjustment. The servo adjustment device 10 stores a list of adjustment parameters in advance and automatically selects the adjustment parameter from the stored list. Alternatively, the adjustment parameter may be selected based on input information from the user. Then, the process proceeds to step S32.

[0075] Here, the adjustment parameter refers to the parameter of the object whose setting value is changed according to the parameter setting determined by obtaining the virtual FB information during the last servo adjustment process. In this embodiment, only one parameter is adjusted at the same time. However, this is not limited to this, and multiple parameters can also be adjusted at the same time.

[0076] In addition, when an adjustment parameter is selected once, it is usually kept selected according to a predetermined rule, such as a rule that the adjustment is continued until the adjustment amount of the adjustment parameter becomes less than 1%, until the servo adjustment device 10 determines that the adjustment is completed. That is, the parameter setting determination process is repeatedly executed, for example, until the adjustment amount of the adjustment parameter becomes less than 1%. However, the adjustment can be forcibly interrupted according to input information from the user, and the next adjustment parameter can be selected.

[0077] In step S32, the servo adjustment device 10 determines whether the change of the adjustment parameter selected this time is the first time. Specifically, the servo adjustment device 10 stores the number of times the parameter setting decision process is performed for each adjustment parameter, and based on the stored information, determines whether the parameter setting decision process is the first time for the adjustment parameter selected in step S31. If the determination is "yes", the process proceeds to step S33, and if not, the process proceeds to step S34.

[0078] In step S33 , since the adjustment parameter selected this time is changed for the first time, the parameter setting is determined according to a predetermined rule 1, for example, rule 1 of changing the adjustment parameter to +10% relative to the initial value. Thereafter, the present process ends.

[0079] In step S34, the change of the adjustment parameter selected this time is not the first time, so the servo adjustment device 10 determines whether the virtual FB information generated and obtained by the virtual control device 20 is a better result than the last parameter setting. For example, in this embodiment, when the difference between the virtual FB information and the command information, that is, the error amount, is smaller than the last parameter setting, it is determined to be a good result. On the contrary, when it is larger, it is determined to be a bad result. If the determination is "yes", it proceeds to step S35, and if it is "no", it proceeds to step S36.

[0080] In step S35, the virtual FB information of this time is a better result than the last parameter setting, so the parameter setting is determined according to the predetermined rule 2, for example, the value of 80% of the last adjustment amount is added to the last value in the same direction as the last parameter setting (if it is the second time, 80% of the amount of +10% relative to the initial value is added, so it is set as +8% addition). After that, this process ends.

[0081] In step S36, the virtual FB information of this time is the result of the time difference from the last parameter setting, so the parameter setting is determined according to the predetermined rule 3, for example, the value of 80% of the last adjustment amount is subtracted from the last value in the opposite direction to the last parameter setting (if it is the second time, 80% of the amount of +10% relative to the initial value is subtracted, so it is set to -8% subtraction). After that, this process ends.

[0082] Fig.11 is a diagram showing an example of the above-mentioned parameter adjustment. Fig.11 As shown, the initial value of the selected adjustment parameter is set to 300, for example. If the adjustment parameter is changed for the first time, for example, if the adjustment is adjusted to +10% relative to the initial value according to Rule 1, the adjusted value becomes 330. Next, if the adjustment parameter is changed for the second time, for example, and the virtual FB information of this time is a better result than the last parameter setting, if the adjustment is performed by adding 80% of the last adjustment amount to the last value in the same direction as the last parameter setting according to Rule 2, the adjusted value becomes 354. In addition, if the adjustment parameter is changed for the second time, for example, and the virtual FB information of this time is a worse result than the last parameter setting, if the adjustment is performed by subtracting 80% of the last adjustment amount from the last value in the opposite direction to the last parameter setting according to Rule 3, the adjusted value becomes 306. In this way, for example, the parameter setting determination process is repeatedly performed until the adjustment amount of the adjustment parameter becomes less than 1%.

[0083] According to the servo adjustment system 1 of the present embodiment, the following effects are achieved.

[0084] In the servo adjustment system 1 of the present embodiment, the structure includes: a servo motor model 30 obtained by virtualizing the action of the servo motor; a virtual control device 20, which executes an evaluation program according to control parameter setting information, thereby virtually controlling the servo motor model 30; and a servo adjustment device 10, which determines the control parameter setting information according to virtual FB information, and the virtual FB information is information obtained by executing the evaluation program multiple times in the virtual control device 20 according to different control parameter setting information.

[0085] In addition, in the servo adjustment system 1 of this embodiment, it is preferable that the servo adjustment device 10 further includes a control target model obtained by virtualizing the industrial machine, and the servo motor model 30 virtually controlled by the virtual control device 20 drives the control target model 40, thereby obtaining virtual FB information.

[0086] Thus, according to the present embodiment, servo adjustment can be automatically performed based on virtual FB information from the virtual environment 50, and parameter settings can be determined automatically and with high accuracy, wherein the virtual environment 50 uses the servo motor model 30 including the motion and characteristics of the servo motor and the control object model 40 including the motion and characteristics of the industrial machine. Therefore, virtual FB information that is closer to the actual machine motion can be generated, and servo adjustment that is closer to the actual machine motion can be performed. In addition, compared with the case where the user determines the parameter settings, the burden on the user can be reduced, and operational errors can be prevented.

[0087] Furthermore, according to the present embodiment, servo adjustment can be performed using the virtual environment 50, so servo adjustment can be automatically performed in a short time by high-speed execution in the virtual environment 50. Therefore, the downtime of the equipment can be reduced by eliminating the need for a real machine, and servo adjustment work can be performed in the design stage.

[0088] In addition, according to this embodiment, by constructing a virtual environment 50 that accurately reflects the size, friction, mechanical rigidity, etc. of the industrial machinery, the movement of the tool tip can be simulated based on the virtual FB information, i.e., the action of the servo motor model, without the need for additional equipment such as acceleration sensors.

[0089] In addition, according to the present embodiment, in order to generate virtual FB information, the virtual control device 20 executes the evaluation program, so by changing the evaluation program, virtual FB information for different command information can be easily obtained. In addition, the actual machining program (or part thereof) used by the user in machining can also be used as the evaluation program, and there is no need to prepare the axis motion for evaluation separately, and the actual motion to be adjusted can be easily obtained.

[0090] [Second embodiment]

[0091] Fig.12 1A is a block diagram showing the structure of a servo adjustment system 1A according to the second embodiment. Fig.12 As shown, the servo adjustment system 1A of the second embodiment is different from the servo adjustment system 1 of the first embodiment in that it includes a machine learning device 60 and a learning data storage device 70 , and the other structures are the same as those of the first embodiment.

[0092] The machine learning device 60 is a computer composed of hardware such as a CPU or other processing unit, a HDD, SSD or other auxiliary storage unit storing various computer programs, a RAM or other main storage unit storing data temporarily required when the processing unit executes the computer program, a keyboard or other operating unit for the operator to perform various operations, and a display unit such as a display that displays various information to the operator, as is the case with the servo adjustment device 10A and the virtual control device 20. The machine learning device 60 and the learning data storage device 70 can mutually transmit and receive various signals with the servo adjustment device 10A and the virtual control device 20, and the communication method is not particularly limited.

[0093] The machine learning device 60 obtains virtual FB information from the virtual environment 50 via the servo adjustment device 10A, and performs servo adjustment by machine learning based on the obtained virtual FB information. That is, in the first embodiment, the servo adjustment device 10 determines the control parameter setting information according to a predetermined rule based on the virtual FB information obtained according to a plurality of different parameter settings. In contrast to this structure, in the present embodiment, the control parameter setting information is determined by machine learning using the machine learning device 60.

[0094] The learning data storage device 70 acquires and registers the machine learning data including the learning results performed by the machine learning device 60. The learning results include, for example, the pass / fail judgment result corresponding to the difference between the virtual FB information and the command information to the servo motor model, that is, the error amount. The learning results will be described in detail later.

[0095] In addition, the machine learning data registered in the learning data storage device 70 is shared between the virtual environment 50 and the actual environment composed of the servo motor, machine tool, numerical control device, etc., which are not shown in the figure. As a result, more efficient servo adjustment based on machine learning can be performed, and servo adjustment with higher accuracy and in a shorter time can be achieved.

[0096] Here, the machine learning performed by the machine learning device 60 is not particularly limited, and examples thereof include supervised learning, unsupervised learning, reinforcement learning, etc. Among them, for example, reinforcement learning similar to the reinforcement learning described in Japanese Patent Application Laid-Open No. 2018-180764 can be preferably applied to the machine learning device 60 of this embodiment.

[0097] Specifically, the machine learning device 60 is configured to, for example, set a parameter (for example, parameter a) of the control parameter setting information to be adjusted by the servo. i 、b j More specifically, the machine learning device 60 is configured to perform Q-learning, which uses the parameter a i、b j The value of the virtual FB information obtained by executing the evaluation program by the virtual control device 20, and the instruction information to the servo motor model 30 are taken as the state s, and the parameter a related to the state s is i 、b j As the behavior a. It is well known to those skilled in the art that in Q learning, at a certain state s, the behavior a with the highest value Q(s, a) is selected from the possible behaviors a as the best behavior. In this way, the best control parameter setting information can be selected. For more details, it is recorded in Japanese Patent Publication No. 2018-180764, so its detailed description is omitted here.

[0098] in addition, Fig.13 1 is a block diagram showing the structure of a servo adjustment system 1B according to a modified example of the second embodiment. Fig.13 As shown, the servo adjustment system 1B of the modified example of the second embodiment is different from the servo adjustment system 1A of the second embodiment in that it has multiple virtual environments 51, 52, ... 50n and the servo adjustment device 10B has a multi-environment management unit 11, and the other structures are the same as the second embodiment.

[0099] The multiple virtual environments 51, 52, ... 50n are respectively the same structure as the virtual environment 50 of the first embodiment and the second embodiment. That is, the multiple virtual environments 51, 52, ... 50n have the same structure. Therefore, in addition to the virtual control devices 21, 22, ... 20n having the same structure, the servo motor models 31, 32, ... 30n have the same structure, and the control object models 41, 42, ... 40n also have the same structure. Therefore, by virtually operating the same machine tool model and servo motor model in multiple virtual environments, virtual FB information can be obtained in parallel, and machine learning can be performed in parallel, so high-speed learning can be performed.

[0100] The multi-environment management unit 11 of the servo adjustment device 10B manages control parameter setting information applied to multiple virtual environments 51, 52, ... 50n. More specifically, the multi-environment management unit 11 manages parameter settings sent to multiple virtual environments 51, 52, ... 50n. That is, the multi-environment management unit 11 manages which parameter is executed in which virtual environment or which parameter setting mode is executed as described later.

[0101] Thus, the evaluation program can be executed with different parameter settings in each virtual environment 51, 52, ... 50n to obtain virtual FB information. In addition, thereby, virtual FB information is collected from multiple virtual environments 51, 52, ... 50n as learning data to simultaneously perform machine learning, and the obtained learning results are registered in the learning data storage 70, and the learning results are shared among the multiple virtual environments 51, 52, ... 50n, thereby enabling faster machine learning.

[0102] Next, refer to Fig.14 The servo adjustment process performed by the servo adjustment system 1A according to the second embodiment will be described in detail. Fig.14 1 is a flowchart showing the procedure of the servo adjustment process performed by the servo adjustment system 1A of the second embodiment. The servo adjustment process is started, for example, based on the input operation of the user to the servo adjustment device 10A. The servo adjustment process performed by the servo adjustment system 1B of the modified example of the second embodiment is also similar to the servo adjustment process of the second embodiment. Fig.14 The process is the same as shown.

[0103] In step S51, the servo adjustment device 10A temporarily determines parameter settings, and then proceeds to step S52. The temporary determination process of the parameter settings will be described in detail later.

[0104] In step S52, the servo adjustment device 10A transmits the parameter setting temporarily determined in step S51 to the virtual control device 20 of the virtual environment 50. Thereafter, the process proceeds to step S53.

[0105] In step S53 , the virtual control device 20 acquires the parameter setting temporarily determined and transmitted by the servo adjustment device 10A, and then proceeds to step S54 .

[0106] Steps S54 to S58 correspond to steps S11 to S15 of the servo adjustment process of the first embodiment, and the same processes are performed. That is, in this embodiment, the virtual control device 20 analyzes and executes the evaluation program according to the parameter setting temporarily determined by the servo adjustment device 10A, thereby generating virtual FB information. Then, the process proceeds to step S59.

[0107] In step S59 , the machine learning device 60 performs machine learning based on the virtual FB information based on the plurality of different control parameter setting information transmitted and acquired from the servo adjustment device 10A, and generates a learning result. Thereafter, the process proceeds to step S60 .

[0108] In step S60, the learning data storage 70 acquires the learning result obtained by the machine learning device 60, and registers the acquired learning result in the data storage. Thereafter, the process proceeds to step S61.

[0109] In step S61, the servo adjustment device 10A determines whether the machine learning of the machine learning device 60 is completed. If the determination is "yes", the process proceeds to step S62, and if not, the process returns to step S51.

[0110] In step S62, the servo adjustment device 10A determines the parameter setting. Thereafter, the process proceeds to step S63. The parameter setting determination process will be described in detail later.

[0111] Step S63 and step S64 correspond to step S17 and step S18 of the servo adjustment process of the first embodiment, respectively, and similar processes are performed. After step S64 is performed, this process ends.

[0112] Next, refer to Fig.15 The temporary determination process of the parameter setting in the above step S51 is described in detail. Fig.15 This is a flowchart showing the procedure of the provisional determination processing of parameter settings.

[0113] In step S71, the servo adjustment device 10A generates only the setting pattern of the target parameter for the first time. More specifically, it determines one or more parameters as the object of finding the optimal value by machine learning of the machine learning device 60, that is, the parameters (adjustment parameters) as the object of servo adjustment, and generates the setting pattern of the parameters for executing the evaluation program. Then, it proceeds to step S72.

[0114] Here, Fig.16 is a diagram showing an example of a parameter setting mode. Fig.16 As shown, for example, a minimum value, a maximum value, and a step value are respectively specified for two parameters X and Y, thereby generating a two-dimensional setting pattern. Fig.16 The parameter setting pattern shown is an example, and is not limited to a two-dimensional setting pattern, and may be a three-dimensional setting pattern. In addition, the setting pattern is automatically determined by the servo adjustment device 10A. However, the user can determine the parameter setting pattern.

[0115] Return to Fig.15In step S72, the servo adjustment device 10A determines whether there are multiple virtual environments. In the servo adjustment system 1A of the second embodiment, the virtual environment is one of the virtual environments 50, and the determination is "No", so the process proceeds to step S73. On the other hand, in the servo adjustment system 1B of the modified example of the second embodiment, there are multiple virtual environments such as virtual environments 51, 52, ... 50n, and the determination is "Yes", so the process proceeds to step S74.

[0116] In step S73, as in the second embodiment, there is only one virtual environment, so the servo adjustment device 10A performs the following operations, for example, according to Fig.16 The parameter setting mode shown temporarily determines the parameter setting to be applied to the virtual environment 50 and ends the present processing.

[0117] In step S74, as in the case of a modification of the second embodiment, there are multiple virtual environments. Therefore, the multiple environment management unit 11 of the servo adjustment device 10B is configured according to, for example, Fig.16 The parameter setting mode shown temporarily determines the parameter settings to be applied to the plurality of virtual environments 51, 52, ... 50n, respectively, and ends the present processing.

[0118] Here, Fig.17 This is a diagram showing an example of parameter settings applied to a plurality of virtual environments. Fig.17 The parameter settings shown are those that will be Fig.16 The two-dimensional parameter setting pattern composed of the parameters X and Y shown in FIG. 1 is divided into four parts, and applied to the parameter setting of virtual environments 1 to 4 respectively. In the servo adjustment system 1B of the modified example of the second embodiment, there are n virtual environments. Fig.16 The two-dimensional parameter setting pattern composed of the parameters X and Y shown is divided into n parts and applied to each virtual environment 51, 52, ... 50n. Alternatively, it can be configured so that, when there are many parameters to be targeted, completely different patterns are allocated to each virtual environment in such a manner that the virtual environment 51 has parameters X and Y, and the virtual environment 52 has parameters N and M to obtain virtual FB information and perform machine learning.

[0119] Next, refer to Fig.18 The parameter setting determination process in step S62 is described in detail. Fig.18 This is a flowchart showing the procedure of parameter setting determination processing.

[0120] In step S81, the servo adjustment device 10A determines the parameter setting that obtains the best judgment result based on the learning result registered in the learning data memory 70. As a criterion for judgment, for example, the pass / fail judgment result corresponding to the difference between the virtual FB information and the command information to the servo motor model, that is, the error amount, can be cited. After that, this process ends.

[0121] Here, Fig.19 is a diagram showing an example of learning results. Fig.19 As shown, as specific pass / fail judgment results, for example, for each parameter setting, judgment results such as "best", "very good", "good", "acceptable", and "unacceptable" are listed in order from the smallest error amount. Fig.19 In the example shown, the parameter setting of 160 for parameter X and 35 for parameter Y is the best result of determination, and therefore the servo adjustment device 10A determines to use this parameter setting.

[0122] Furthermore, in actual use, the optimal value determined in the virtual environment may not be completely consistent with the actual environment. Therefore, for example, it is preferable to limit the above-mentioned range of "best" and "very good" to perform machine learning again in the actual environment.

[0123] According to the servo adjustment systems 1A and 1B of the present embodiment, the following effects are achieved.

[0124] The servo adjustment system 1A of the present embodiment is further configured to include a machine learning device 60 that performs machine learning on control parameter setting information using virtual FB information, and the servo adjustment device 10A determines the control parameter setting information based on the learning result of the machine learning device 60 .

[0125] Thus, servo adjustment using machine learning of the machine learning device 60 can be performed based on virtual FB information obtained by virtual control of the servo motor model 30 in the virtual environment 50. Therefore, according to this embodiment, servo adjustment can be automatically performed with higher accuracy and in a shorter time.

[0126] In addition, the servo adjustment system 1B of the present embodiment is configured to have a plurality of virtual environments 51, 52, ... 50n, each of which has a virtual control device 21, 22, ... 20n, a servo motor model 31, 32, ... 30n, and a control object model 41, 42, ... 40n. In addition, the servo adjustment device 10B has a multi-environment management unit 11 that manages control parameter setting information applied to the plurality of virtual environments 51, 52, ... 50n, and the machine learning device 60 performs machine learning on the control parameter setting information using virtual FB information obtained from the plurality of virtual environments 51, 52, ... 50n.

[0127] Thus, in a plurality of virtual environments 51, 52, ... 50n, by making the control object models 41, 42, ... 40n and the servo motor models 31, 32, ... 30n perform virtual actions simultaneously and in parallel, virtual FB information can be obtained simultaneously and in parallel. Therefore, according to this embodiment, machine learning based on virtual FB information can be performed at a higher speed, and changes can be automatically performed to perform servo adjustments with high precision and in a short time.

[0128] In addition, the present disclosure is not limited to the above-mentioned embodiment, and modifications and improvements within the scope that can achieve the purpose of the present disclosure are included in the present disclosure.

[0129] For example, in the above-mentioned embodiment, although the machine tool is described as an example of an industrial machine, the present invention is not limited thereto and the present disclosure can also be applied to other industrial machines such as a robot having a servo motor.

[0130] In addition, for example, in the above-described embodiment, the virtual environment 50 is configured to include the control target model 40 , but the present invention is not limited thereto and the present disclosure can be applied even to a virtual environment that does not include the control target model 40 .

[0131] In addition, for example, in the modified example of the second embodiment, the virtual environments 51, 52, ... 50n are configured to have the servo motor models 31, 32, ... 30n and the control object models 41, 42, ... 40n. This is not limited to this. It is also possible to configure that at least one of the multiple virtual environments has a servo motor model and a control object model, and the other virtual environments do not have a servo motor model and a control object model.

[0132] Explanation of symbols

[0133] 1. A, 1B servo adjustment system

[0134] 10, 10A, 10B Servo adjustment device

[0135] 11 Multi-Environment Management Department

[0136] 20, 21, 22, 20n Virtual control device

[0137] 30, 31, 32, 30n servo motor models

[0138] 40, 41, 42, 40n Control object model

[0139] 50, 51, 52, 50n virtual environment

[0140] 60 Machine Learning Device

[0141] 70 Learning Data Storage.

Claims

1. A servo adjustment system for adjusting control parameter setting information of a servo motor controlled by a control device of an industrial machine, characterized in that: The servo adjustment system comprises: A servo motor model obtained by virtualizing the motion of the servo motor; a virtual control device that executes an evaluation program based on the control parameter setting information to virtually control the servo motor model; and A servo adjustment device determines the control parameter setting information based on virtual feedback information obtained by executing the evaluation program a plurality of times in the virtual control device based on different control parameter setting information.

2. The servo adjustment system according to claim 1, characterized in that: The servo adjustment system further comprises: a control object model obtained by virtualizing the industrial machine; The servo adjustment device acquires the virtual feedback information by driving the control object model using the servo motor model virtually controlled by the virtual control device.

3. The servo adjustment system according to claim 1 or 2, characterized in that: The servo adjustment system further comprises: a machine learning device, which uses the virtual feedback information to perform machine learning on the control parameter setting information, The servo adjustment device determines the control parameter setting information based on the learning result of the machine learning device.

4. The servo adjustment system according to claim 3, characterized in that: The servo adjustment system comprises: a plurality of virtual environments having at least one of the servo motor models and the virtual control device, The servo adjustment device comprises: a multi-environment management unit that manages the control parameter setting information applied to the plurality of virtual environments; The machine learning device uses the virtual feedback information obtained from the multiple virtual environments to perform machine learning on the control parameter setting information.

Citation Information

Patent Citations

  • Controller at end point of machine

    JP2006172149A

  • Setting support apparatus, setting support method, information processing program, and record medium

    JP2017167607A

  • Adjusting device and adjustment method

    JP2018180764A