Information processing methods, information optimization methods, information processing equipment and program

Abstract

An information processing method for optimizing a plurality of control parameters in a device that performs a plurality of operations based on the plurality of control parameters, wherein the method, through an information processing device in the control parameter optimization processing, includes selecting a representative operation that contains at least one operation from the plurality of operations that can be performed by the device, causing the device to perform the selected representative operation, acquiring measurement data relating to an operation of the device, wherein the measurement data are measured by performing the representative operation, calculating an evaluation value of a predetermined evaluation index based on the acquired measurement data, and updating the plurality of control parameters based on the calculated evaluation value;and includes multiple executions of the control parameter optimization process while changing an evaluation criterion of the control parameter optimization process.

Description

Technical field

[0001] The present disclosure relates to an information processing method, an information optimization method, an information processing device and a program. Technical background

[0002] A conventionally known method is a control parameter generation method for generating control parameters (see e.g. patent literature 1).

[0003] Conventionally, the desire was expressed to efficiently generate suitable control parameters. Quotation list of patent literature

[0004] Patent literature 1: WO 2018 / 151215 A Summary of the invention

[0005] One objective of the present disclosure is to provide an information processing method, an information optimization method, an information processing device and a program that is capable of efficiently generating suitable control parameters. Means to solve the problem

[0006] An information processing method according to one aspect of the present disclosure is an information processing method for optimizing a plurality of control parameters in a device that performs a plurality of operations based on the plurality of control parameters, wherein the method, through an information processing device in the control parameter optimization processing, selects a representative operation that includes at least one operation from the plurality of operations that can be performed by the device, causes the device to perform the selected representative operation, and acquires measurement data relating to an operation of the device, wherein the measurement data are measured by performing the representative operation.This includes calculating a rating value of a predetermined rating index based on the recorded measurement data and updating the multitude of control parameters based on the calculated rating value; and repeatedly executing the control parameter optimization processing while changing a rating criterion of the control parameter optimization processing.

[0007] An information optimization procedure according to one aspect of the present disclosure comprises performing a first optimization processing of information based on a first evaluation criterion; defining a search range of the information based on a plurality of evaluation values ​​calculated in the first optimization processing; and performing a second optimization processing of the information over the defined search range using a second evaluation criterion by an information processing device.

[0008] An information processing device according to one aspect of the present disclosure is an information processing device, an information processing device that optimizes a plurality of control parameters in a device that performs a plurality of operations based on the plurality of control parameters, wherein the device comprises a selection unit, a control unit, a detection unit, a computation unit, and an update unit; in optimizing the control parameters, the selection unit selects a representative operation that includes at least one operation from the plurality of operations that can be performed by the device; the control unit causes the device to perform the representative operation selected by the selection unit; the detection unit detects measurement data about an operation of the device that was measured during the performance of the representative operation.The calculation unit calculates a rating value of a predetermined rating index based on the measurement data acquired by the acquisition unit, the update unit updates the multitude of control parameters based on the rating value calculated by the calculation unit, and the control parameter optimization processing is executed several times, changing a rating criterion of the control parameter optimization processing.

[0009] A program according to one aspect of the present disclosure is a program for causing an information processing device to function as a selection means, control means, acquisition means, computation means, and update means, wherein the information processing device optimizes a plurality of control parameters in a device that performs a plurality of operations based on the plurality of control parameters, wherein in the control parameter optimization processing, the selection means selects a representative operation comprising at least one operation from the plurality of operations that can be performed by the device, the control means causes the device to perform the representative operation selected by the selection means, and the acquisition means acquires measurement data about an operation of the device that were measured during the performance of the representative operation.The calculation tool calculates a rating value of a predetermined rating index based on the measurement data acquired by the acquisition tool, the update tool updates the multitude of control parameters based on the rating value calculated by the calculation tool, and the control parameter optimization processing is executed several times, changing a rating criterion of the control parameter optimization processing. Effect of the invention

[0010] According to the present disclosure, suitable control parameters can be generated efficiently. Brief description of the drawings Fig. Figure 1 is a schematic diagram showing an overview of a control parameter generation system according to a first embodiment. Fig. Figure 2 is a block diagram showing a configuration of the control parameter generation system according to the first embodiment. Fig. Figure 3 is a perspective view showing an example of a production device according to the first embodiment. Fig. Figure 4 is a data configuration diagram showing an example of the control parameters stored in a memory according to the first embodiment. Fig. Figure 5 is a schematic diagram showing an example of the transition of a positional deviation of a driven object in relation to a target position. Fig. Figure 6 is a data configuration table that provides an example of measurement data output by the sensor according to the first embodiment. Fig. Figure 7 is a flowchart of the first control parameter generation process. Fig. Figure 8 is a sequence diagram of the first control parameter generation. Fig. Figure 9 is a schematic diagram showing an example of an image displayed by a display unit according to the first embodiment. Fig. Figure 10 is a flowchart of condition capture processing. Fig. Figure 11 is a schematic diagram that represents an example of an image displayed by the display unit according to the first embodiment. Fig. Figure 12 is a flowchart of a labeling process for representative operations. Fig. Figure 13 is a schematic diagram that represents an example of an image displayed by the display unit according to the first embodiment. Fig. Figure 14 is a schematic diagram showing an experimental result of an experiment carried out by the inventors. Fig. Figure 15 is a block diagram showing a configuration of a control parameter generation system according to a second embodiment. Fig. Figure 16A is a schematic diagram showing an example of the transition of a positional deviation of a driven object with respect to a target position. Fig. Figure 16B is a schematic diagram showing an example of the transition of the positional deviation of the object being driven with respect to a target position. Fig. 17 is a flowchart of the processing of the second control parameter generation. Fig. 18 is a flowchart of the third control parameter generation. Fig. Figure 19 is a schematic diagram showing an example of a condition in which a determining unit according to a third embodiment X selects representative operations from Y operations. Fig. Figure 20 is a flowchart of parameter updates through all operations. Fig. 21 is a flowchart of the processing of the first control parameter generation. Fig. Figure 22 is a flowchart showing a processing flow performed by an information processing unit. Fig. Figure 23 is a diagram that schematically illustrates a procedure for setting a search range by a generating unit. Fig. Figure 24 is a diagram for displaying operating condition information, in which an operating condition of each operation performed by the production device is described in a partially simplified manner. Fig. Figure 25 is a flowchart that shows the processing sequence by the information processing unit in conjunction with notifying a user of status information. Fig. Figure 26 is a diagram showing an example of a status notification image. Description of the embodiments (How one aspect of the present disclosure came about)

[0011] As a method for generating suitable control parameters of a drive source in a production device (e.g. an assembly device) that contains the drive source (e.g. a servo motor) that drives an object to be driven, a method for generating suitable control parameters by searching for suitable control parameters using a machine learning model or the like has been proposed in recent years (see e.g. patent literature 1).

[0012] In general, the number of control parameters of the drive source used in the production device can be 50 or more. Furthermore, the number of adjustment steps can be 100 or more.

[0013] For example, if the production device performs 80 operations, the number of control parameters of the drive source is 50, and the number of adjustment steps of the control parameters is 100, then the number of combinations of these is 100. 50 × 80.

[0014] The inventors identified the problem that, in a case where control parameters are generated for such a huge number of combinations, using a method to search for suitable control parameters using a machine learning model or the like requires an enormous amount of time to search for suitable control parameters, or, no matter how much time is required, no suitable control parameter can be found due to an excessively large search range.

[0015] For this reason, the inventors conducted intensive experiments and studies to develop a method for generating parameters that is capable of efficiently generating suitable control parameters even when control parameters are generated for an enormous number of combinations.

[0016] Through the experiments and studies described above, the inventors have learned that in a case where, for example, 80 operations are performed by the production device, suitable control parameters can be generated more efficiently and reliably for combinations of all 80 operations by repeating the steps described below and ultimately searching for suitable parameters for all 80 operations, without having to search for suitable control parameters for all large combinations from the outset. The steps include an initial search for suitable control parameters for some of the 80 operations, for example, only a single combination of operations.only some combinations among the huge combinations, a next step of increasing the number of operations performed by the production device and searching for suitable control parameters for a combination of two operations using a search result in the first step, and a still further step of further increasing the number of operations performed by the production device and searching for suitable control parameters, for example for a combination of four operations using a search result in the previous step.

[0017] The inventors further conducted experiments and studies based on the above findings and devised a method for generating control parameters and the like in accordance with the present disclosure, which is described below.

[0018] An information processing method according to a first aspect of the present disclosure is an information processing method for optimizing a plurality of control parameters in a device that performs a plurality of operations based on the plurality of control parameters, wherein the method is carried out by an information processing device, in the control parameter optimization processing: selecting a representative operation that includes at least one operation from the plurality of operations that can be performed by the device, causing the device to perform the selected representative operation, acquiring measurement data relating to an operation of the device, wherein the measurement data are measured by performing the representative operation.Calculating a rating value of a predetermined rating index based on the recorded measurement data and updating the multitude of control parameters based on the calculated rating value; and includes repeatedly executing the control parameter optimization processing while changing a rating criterion of the control parameter optimization processing.

[0019] According to the first aspect, the control parameter optimization process is executed a large number of times while the evaluation criterion for the control parameter optimization process is changed. As described above, suitable control parameters can be efficiently generated by repeatedly executing the control parameter optimization process while changing the evaluation criterion.

[0020] According to a second aspect of the present disclosure, in the information processing procedure according to the first aspect, the change of the evaluation criterion may involve a change of the representative operation.

[0021] According to the second aspect, the evaluation criterion can be changed by changing the representative operation.

[0022] According to a third aspect of the present disclosure, in the information processing procedure according to the second aspect, changing the representative operation may involve changing a number of operations in the representative operation.

[0023] According to the third aspect, the evaluation criterion can be changed by changing the number of operations in the representative operation.

[0024] According to a fourth aspect of the present disclosure, in the information processing procedure according to the third aspect, the change in the number of operations may involve an increase in the number of operations.

[0025] According to the fourth aspect, suitable control parameters can be efficiently generated by repeatedly optimizing the control parameters while gradually increasing the number of operations included in the representative operation.

[0026] According to a fifth aspect of the present disclosure, in the information processing procedure according to the second aspect, changing the representative operation may include changing the content of an operation contained in the representative operation.

[0027] According to the fifth aspect, the evaluation criterion can be changed by modifying the content of an operation that is included in the representative operation.

[0028] According to a sixth aspect of the present disclosure, in the information processing procedure according to the fifth aspect, changing the content of the operation may involve making the content of the operation more complicated.

[0029] According to the sixth aspect, suitable control parameters can be efficiently generated by repeatedly performing the control parameter optimization processing, while progressively complicating the content of the operation contained in the representative operation.

[0030] According to a seventh aspect of the present disclosure, in the information processing procedure according to one of the second to sixth aspects, when changing the representative operation, all of the several operations can be classified into several groups based on similarity, an operation to be improved can be determined among the several operations contained in each of the several groups based on the rating value or a past average rating value, and several of the operations to be improved that have been determined for the several groups can be selected as the representative operation in the control parameter optimization processing at a later time.

[0031] According to the seventh aspect, suitable control parameters can be efficiently generated by selecting the multitude of operations to be improved, which are intended for the multitude of groups, as a representative operation in the control parameter optimization processing at a later time.

[0032] According to an eighth aspect of the present disclosure, in the information processing procedure according to one of the first to seventh aspects, the change of the evaluation criterion may involve the change of the evaluation index.

[0033] According to the eighth aspect, the evaluation criterion can be changed by changing the evaluation index.

[0034] According to a ninth aspect of the present disclosure, in the information processing method according to the eighth aspect, each of the several operations is an operation that causes the device to transfer an object into a target position, and the evaluation index may include a settling time until a position deviation between a position of the object and the target position converges within an acceptable range.

[0035] According to the ninth aspect, control parameters can be appropriately evaluated by using the settling time as an evaluation index.

[0036] According to a tenth aspect of the present disclosure, in the information processing method according to the eighth aspect, each of the several operations is an operation that causes the device to transfer an object to a target position, and the evaluation index may include an integrated value of a deviation time during which a position deviation between a position of the object and the target position deviates from an allowable range, or a position deviation amount.

[0037] According to the tenth aspect, tax parameters can be appropriately assessed by using the integrated value of the deviation time or the position deviation amount as an assessment index.

[0038] According to an eleventh aspect of the present disclosure, the information processing method according to one of the first to tenth aspects may further include setting a search range of the control parameters that are update candidates in the control parameter optimization processing at a future time, based on a plurality of the evaluation values ​​calculated in the control parameter optimization processing at a current time.

[0039] According to the eleventh aspect, by transferring the setting information via the search area of ​​the control parameters from the control parameter optimization processing at the current time to the control parameter optimization processing at the next time, suitable control parameters can be efficiently searched for in the control parameter optimization processing at the next time.

[0040] According to a twelfth aspect of the present disclosure, the information processing method according to any of the first to eleventh aspects may further include: causing the device to perform a predetermined evaluation operation for the comprehensive evaluation of an operation of the device in a comprehensive evaluation process; acquiring measurement data relating to the operation of the device, which are measured during the performance of the evaluation operation; calculating an evaluation value of the evaluation index based on the acquired measurement data; and performing the comprehensive evaluation based on the calculated evaluation value.

[0041] According to the twelfth aspect, the progress of the control parameter optimization in all operations of the device can be evaluated through comprehensive evaluation processing.

[0042] According to a thirteenth aspect of the present disclosure, in the information processing procedure according to the twelfth aspect, the evaluation operation can include all operations.

[0043] According to the thirteenth aspect, an accurate, comprehensive evaluation can be carried out by causing the device to perform all operations as evaluation operations.

[0044] According to a fourteenth aspect of the present disclosure, in the information processing procedure according to the twelfth aspect, the evaluation operation may be a difference operation between all operations and a most recent representative operation with respect to the evaluation operation.

[0045] According to the fourteenth aspect, the efficiency of the evaluation operation can be improved while maintaining the accuracy of the comprehensive evaluation by causing the device to perform, as the evaluation operation, the difference operation between all operations and the last representative operation with respect to the evaluation operation.

[0046] According to a fifteenth aspect of the present disclosure, in the information processing procedure according to the twelfth aspect, the evaluation operation may be a prescribed operation that is defined in advance from all operations.

[0047] According to the fifteenth aspect, the efficiency of the evaluation operation can be improved by causing the device to perform the prescribed operation, which has been defined in advance from all operations.

[0048] According to a sixteenth aspect of the present disclosure, the information processing procedure according to one of the twelfth to fifteenth aspects may further include: determining whether the evaluation result of the comprehensive evaluation satisfies a predetermined end condition, and terminating the control parameter optimization processing in a case where the evaluation result satisfies the end condition.

[0049] According to the sixteenth aspect, in a case where the evaluation result of the comprehensive evaluation fulfills the predetermined end condition, the control parameter optimization processing ends even before the control parameter optimization processing reaches the final stage, and thus the time required for processing can be reduced.

[0050] According to a seventeenth aspect of the present disclosure, in the information processing method according to one of the first to sixteenth aspects, each of the several operations is an operation that causes the device to transfer an object to a target position, and the method may further include the output of status information to a user for notification, which relates to at least one of the following elements: an elapsed time since the start of the control parameter optimization processing; a remaining time until a maximum time for the continuation of the control parameter optimization processing; an operating condition which includes at least identification information, a transfer amount, a transfer rate, an acceleration time, and a delay time with respect to an operation that is currently being performed under the at least one operation that is included in the representative operation;a number of operations included in the representative operation, a number of control parameter update times; and a remaining number of times up to a maximum number of control parameter update times.

[0051] According to the seventeenth aspect, the user can easily check the progress status, operating conditions, or similar aspects of the control parameter optimization processing through notification, by issuing the status information to the user, thus improving user convenience.

[0052] According to an eighteenth aspect of the present disclosure, the information processing procedure according to the seventeenth aspect may further include updating the status information whenever the evaluation criterion changes.

[0053] According to the eighteenth aspect, the latest status information can be communicated to the user by updating the status information each time the evaluation criterion is changed.

[0054] According to a nineteenth aspect of the present disclosure, the information processing method according to the seventeenth aspect may further include setting the maximum time, operating condition and maximum number of times based on condition setting information entered by a user.

[0055] According to the nineteenth aspect, the user can randomly set the maximum time, the operating conditions, and the maximum number of times.

[0056] According to a twentieth aspect of the present disclosure, in the information processing method according to the seventeenth aspect, the operating condition for each device is preset, and the method may further include setting the operating condition in accordance with the selected device based on the device selection information entered by a user.

[0057] According to the twentieth aspect, it is possible to automatically set a suitable operating condition in accordance with the device selected by the user.

[0058] According to a twenty-first aspect of the present disclosure, the information processing method according to any of the first to twenty aspects may further include the recording of operation history information including an execution time and an operating condition for each operation performed by the device during control parameter optimization processing.

[0059] According to the twenty-first aspect, information on the operational history can be made available to a user by recording the operational history information, including an execution time and an operating condition, for each operation performed by the device.

[0060] An information optimization procedure according to a twenty-second aspect of the present disclosure comprises performing a first optimization processing of information based on a first evaluation criterion; defining a search range of the information based on a plurality of evaluation values ​​calculated in the first optimization processing; and performing a second optimization processing of the information over the defined search range using a second evaluation criterion by an information processing device.

[0061] According to the twenty-second aspect, the second optimization processing can be carried out efficiently by transferring the setting information about the search area from the first optimization processing to the second optimization processing.

[0062] An information processing device according to a twenty-third aspect of the present disclosure is an information processing device that optimizes a plurality of control parameters in a device that performs a plurality of operations based on the plurality of control parameters, wherein the device comprises a selection unit, a control unit, a detection unit, a computation unit, and an update unit; in optimizing the control parameters, the selection unit selects a representative operation that includes at least one operation from the plurality of operations that can be performed by the device; the control unit causes the device to perform the representative operation selected by the selection unit; the detection unit detects measurement data about an operation of the device that was measured during the performance of the representative operation.The calculation unit calculates a rating value of a predetermined rating index based on the measurement data acquired by the acquisition unit, the update unit updates the multitude of control parameters based on the rating value calculated by the calculation unit, and the control parameter optimization processing is executed several times, changing a rating criterion of the control parameter optimization processing.

[0063] According to the twenty-third aspect, the control parameter optimization process is executed a multitude of times while the evaluation criterion for the control parameter optimization process is changed. As described above, suitable control parameters can be efficiently generated by repeatedly executing the control parameter optimization process while changing the evaluation criterion.

[0064] A program according to a twenty-fourth aspect of the present disclosure is a program for causing an information processing device to function as a selection device, control device, acquisition device, computation device, and update device, wherein the information processing device optimizes a plurality of control parameters in a device that performs a plurality of operations based on the plurality of control parameters, wherein in the control parameter optimization processing, the selection device selects a representative operation comprising at least one operation from the plurality of operations that can be performed by the device, the control device causes the device to perform the representative operation selected by the selection device, and the acquisition device acquires measurement data about an operation of the device that were measured during the performance of the representative operation.The calculation tool calculates a rating value of a predetermined rating index based on the measurement data acquired by the acquisition tool, the update tool updates the multitude of control parameters based on the rating value calculated by the calculation tool, and the control parameter optimization processing is executed several times, changing a rating criterion of the control parameter optimization processing.

[0065] According to the twenty-fourth aspect, the control parameter optimization process is executed a multitude of times while the evaluation criterion for the control parameter optimization process is changed. As described above, suitable control parameters can be efficiently generated by repeatedly executing the control parameter optimization process while changing the evaluation criterion.

[0066] Specific examples of the control parameter generation system according to one aspect of the present disclosure are described below with reference to the drawings. Each embodiment described here illustrates a specific example of the present disclosure. Therefore, the following embodiments describe numerical values, shapes, components, the arrangement of components, connection types, steps, the sequence of steps, and the like, which are merely examples and are not intended to limit the present disclosure. Each of the drawings is a schematic diagram and is not necessarily strictly illustrated. Essentially the same components are designated with the same reference numerals in the drawings, and redundant descriptions are omitted or simplified. (First embodiment)

[0067] A control parameter generation system according to a first embodiment is described below. This control parameter generation system is a control parameter generation system for a production device with a drive source that drives an object to be driven. <konfiguration>

[0068] Fig. Figure 1 is a schematic diagram showing an overview of a control parameter generation system 1 according to the first embodiment.

[0069] Fig. Figure 2 is a block diagram showing a configuration of the control parameter generation system 1.

[0070] As in Fig. As shown in Figure 1, the control parameter generation system 1 comprises a control parameter generation device 10, a production device 20 and a sensor 30.

[0071] Production device 20 is a device used for the manufacture of equipment and performs the assembly, processing, machining, transport, and similar operations of the equipment. Production device 20 is installed, for example, in a factory production line. Specifically, production device 20 is an assembly device, a processing device, a machining device, a transport device, or something similar.

[0072] Production device 20 performs N (N is an integer of 3 or more) operations. The integer N is, for example, 80.

[0073] As in Fig. As shown in Figure 2, the production device 20 comprises a storage unit 21, a control circuit 22, a drive source 23 and a driven object 24.

[0074] The control circuit 22 controls the operation of the drive source 23 and drives the object 24 to be driven.

[0075] Specifically, the drive source 23 is, for example, a servo motor, a fluid directional control valve for controlling a pneumatic arm with artificial muscles, or a fluid directional control valve for controlling a hydraulic arm. The servo motor could be, for example, a rotary motor or a linear motor.

[0076] The object 24 to be driven is an object that is driven by the drive source 23. For example, if the drive source 23 is a servo motor, the object 24 to be driven is a head carrying a part to be machined, a nozzle provided on the head to draw in the part to be machined, or the like. Furthermore, if the drive source 23 is a directional control valve, the object 24 to be driven is a pneumatic artificial muscle arm, a hydraulic arm, or the like.

[0077] Fig. Figure 3 is a perspective view of the production device 20 with a configuration in which the drive source 23 is a servo motor and the object to be driven 24 is a nozzle, which is provided, for example, on a head.

[0078] As in Fig. As shown in Figure 3, the production device 20 can, for example, be an assembly device in which components are mounted on a substrate 120 which lies on a machine table 110.

[0079] The production device 20 comprises, for example, a nozzle 81 that draws in a component, a head 80 with the nozzle 81, a servomotor 23A, which serves as a drive source 23 for moving the head 80 in an X-axis direction in the top view of the machine table 110, and a servomotor 23B, which serves as a drive source 23 for moving the head in a Y-axis direction. Here, the head 80 is connected to the servomotor 23A via an arm 72 and the servomotor 23B.

[0080] The description of the control parameter generation system 1 continues by referring back to the Fig. 1 and Fig. 2 is used.

[0081] The control circuit 22 issues a command to the drive source 23 to set the position of the object 24 to be driven to a predetermined target position in order to control the drive source 23. The command issued by the control circuit 22 to the drive source 23 can, for example, be a position command to specify the position of the drive source 23 or the object 24 to be driven, or it can, for example, be a torque command to specify a torque of the drive source 23.

[0082] The control circuit 22 controls the drive source 23 based on the control parameters stored in memory 21. In other words, the control circuit 22 uses the control parameters stored in memory 21 when controlling the drive source 23. The number of control parameters is, for example, 50.

[0083] Memory 21 stores control parameters that are used when the control circuit 22 controls the drive source 23. The control parameters stored in memory 21 are control parameters that are output by the control parameter generating device 10.

[0084] When the control parameters are output by the control parameter generating device 10, the memory 21 captures the output control parameters and updates the control parameters to be stored using the captured control parameters, i.e., it overwrites and stores the control parameters.

[0085] Fig. Figure 4 is a data configuration diagram showing an example of the control parameters stored in memory 21.

[0086] As in Fig. As shown in Figure 4, the control parameters stored in memory 21 include the parameters a1 and a2 for setting a vibration frequency of the object 24 to be driven, the parameters b1 and b2 for setting an increase in the speed of the object 24 to be driven, the parameters c1 and c2 for setting the depth of a singular point in the vibration characteristic of the object 24 to be driven, the parameters d1 and d2 for setting the vibration amplitude of the object 24 to be driven, and the like.

[0087] The control parameters generally include parameters that are in a trade-off relationship to each other, such as parameters b1 and b2 for setting the rate of increase of the velocity, parameters c1 and c2 for setting the depth of the singular point in the vibration characteristic, and parameters d1 and d2 for setting the vibration amplitude.

[0088] The description of the control parameter generation system 1 continues by referring back to the Fig. 1 and Fig. 2 is used.

[0089] The sensor 30 measures the position of the object 24 to be driven in the production device 20, which performs at least one operation among N operations along the time series. Measurement data indicating the measured position for each of the at least one operation are then output to the control parameter generation device 10.

[0090] Fig. Figure 5 is a schematic diagram showing an example of the transition of a position deviation of the object 24 to be driven with respect to a target position when the production device 20 moves the object 24 to be driven into the target position.

[0091] In Fig. In 5, the horizontal axis represents time and the vertical axis represents the positional deviation of the object 24 to be driven in relation to the target position.

[0092] As in Fig. As shown in Figure 5, in this specification the permissible range means a range in which the positional deviation from the target position is within the required accuracy.

[0093] As in Fig. As shown in Figure 5, in this description the time (hereinafter also referred to as "settling time") of reaching the permissible position, which can be considered as reaching the target position, is understood to be the time at which the object 24 to be driven finally reaches the permissible range, if the object to be driven has not deviated from the permissible range again after reaching the permissible range.

[0094] As in Fig. As shown in Figure 5, the settling time in this description means the time from the start of the stopping of the object 24 to be driven, based on the command to set the position of the object 24 to be driven to the target position, until the object 24 to be driven arrives at the permissible position at which it can be evaluated to reach the target position. That is, the settling time is the time from the start time of stopping until the settling time, or the time from the start of the transfer of the object 24 to be driven, based on the command to set the position of the object 24 to be driven to the target position, until the object 24 to be driven arrives at the permissible position at which it can be evaluated to reach the target position—that is, the time from the start time of the transfer until the settling time.

[0095] Fig. Figure 6 is a data configuration diagram showing an example of the output of measurement data by sensor 30.

[0096] As in Fig. As shown in Figure 6, the measurement data consists, for example, of data in which an elapsed time [ms] after a reference time and a deviation amount [mm] from the target position are assigned on a one-to-one basis. The reference time is either a stop-start time of the object 24 to be driven, based on the command to set the position of the object 24 to be driven to the target position, or a transfer-start time of the object 24 to be driven, based on the command to set the position of the object 24 to be driven to the target position.

[0097] The description of the control parameter generation system 1 continues by referring back to the Fig. 1 and Fig. 2 is used.

[0098] The control parameter generating device 10 generates control parameters that are used for the production facility 20.

[0099] The control parameter generation device 10 is implemented, for example, in a computer device with a processor, memory, and an input / output interface, wherein the processor executes a program stored in memory. A personal computer is an example of such a computer device.

[0100] As in Fig. As shown in Figure 2, the control parameter generating device 10 includes an information processing unit 41, such as a processor, a storage unit 42, such as a memory, an input unit 44, such as a mouse or a keyboard, a display unit 17, such as a liquid crystal display or an organic electroluminescent (EL) display, and a communication unit 43, such as a communication module.

[0101] The information processing unit 41, which includes functions implemented by the processor that executes the program read from a recording medium such as a computer-readable read-only memory (ROM), comprises a determination unit 13, a selection unit 19, a control unit 18, a detection unit 11, an output unit 12, an operator receiving unit 15, an image generation unit 16 and a generation unit 14.That is, the program is a program that causes the information processing unit 41 to function as an information processing device attached to the control parameter generating device 10, as the determination unit 13 (determination device), the selection unit 19 (selection device), the control unit 18 (control device), the acquisition unit 11 (acquisition device), the output unit 12 (output device), the operating receiving unit 15 (operating receiving device), the image generating unit 16 (image generating device) and the generation unit 14 (generation device).

[0102] The selection unit 19 selects a representative operation that includes at least one operation from all operations that can be performed by the production device 20.

[0103] The control unit 18 instructs the production facility 20 to perform the representative operation selected by the selection unit 19, or all operations.

[0104] The acquisition unit 11 acquires measurement data output by the sensor 30 and corresponding to one or more operations performed by the production device 20.

[0105] For each of the one or more operations detected by the detection unit 11, the determination unit 13, based on the measurement data corresponding to the operations, determines the time from the start of the stopping or the start of the transfer of the object 24 to be driven in response to the command to set the position of the object 24 to be driven to the target position until the object to be driven arrives at a permissible position at which its arrival at the target position can be evaluated, i.e., a settling time. That is, the determination unit 13 acts as a calculation unit that, based on the measurement data detected by the detection unit 11, calculates an evaluation value of an evaluation index (in the example of the present embodiment, the settling time).

[0106] The generating unit 14 generates update control parameters by updating the control parameters in the optimization processing to shorten at least the longest settling time among one or more settling times, each corresponding to one or more operations detected by the sensing unit 11 and determined by the determination unit 13. That is, the generating unit 14 acts as an update unit that updates the control parameters based on the evaluation value calculated by the determination unit 13 as the computation unit.

[0107] This means that the generating unit 14 optimizes at least the longest settling time of one or more settling times as the evaluation value to be optimized.

[0108] It should be noted that the rating value can be an average of the setting times or an average of P (P is a value smaller than L) longest setting times among L setting times.

[0109] As in Fig. As shown in Figure 2, the generating unit 14 contains an optimization algorithm 140 for optimizing the control parameters in order to shorten the settling time. The generating unit 14 then uses the optimization algorithm 140 to perform an optimization process to shorten at least the longest settling time among those determined by the determining unit 13.

[0110] The optimization algorithm 140 can, for example, be a well-known algorithm such as a Bayesian optimization algorithm, an evolutionary strategy algorithm (CMA-ES), or a genetic algorithm (GA). Furthermore, the optimization process for reducing the settling time using optimization algorithm 140 can, for example, be a well-known process performed using the known algorithm described above.

[0111] For example, the generating unit 14 can generate the update control parameters by executing the optimization processing once, or generate the update control parameters by repeatedly executing the optimization processing until a termination condition of the optimization processing is met.

[0112] Here, the end condition for the optimization process is, for example, a time interval during which the optimization process is repeated. In this case, generation unit 14 repeats the optimization process for a predetermined time interval.

[0113] Furthermore, the end condition for the optimization process is, for example, a number of repetitions of the optimization process. In this case, the generation unit 14 repeats the optimization process a predetermined number of times.

[0114] Furthermore, the end condition for the optimization process is, for example, a time corresponding to one or more settling times. In this case, the generation unit 14 repeats the optimization process until one or more settling times are equal to or shorter than a predetermined time.

[0115] The output unit 12 outputs the control parameters generated by the generation unit 14 to the production facility 20 in order to store the control parameters in memory 21.

[0116] The operating receiver unit 15 receives an operation for entering the setting information or the like from the input unit 44 in the control parameter generating device 10, the operation being carried out by a user using the control parameter generating system 1.

[0117] Display unit 17 shows an image to the user operating control parameter generation system 1. It should be noted that the method of communicating information to the user is not limited to image display, but can also include speech output or similar methods.

[0118] The image generation unit 16 produces an image that is displayed by the display unit 17. <ablauf>

[0119] The following describes a process that is carried out by the control parameter generation system 1 with the configuration described above.

[0120] The control parameter generation system 1 performs an initial processing to generate control parameters, a processing to capture conditions, and a processing to determine representative operations.

[0121] The above procedure is described below with reference to the drawings.

[0122] First, the initial processing of the control parameters is described.

[0123] The first processing step for generating control parameters is a processing step for generating control parameters that are used for the production device 20.

[0124] The first control parameter generation processing is started, for example, by the user of the control parameter generation system 1 performing an operation to start the first control parameter generation processing via the operating receiving unit 15.

[0125] Fig. Figure 7 is a flowchart of the initial control parameter generation, and Fig. Figure 8 is a sequence diagram of the first control parameter generation.

[0126] As in Fig. 7 and Fig. As shown in Figure 8, the operating receiver unit 15 starts a predetermined program to execute the first control parameter generation processing (step S5) when the first control parameter generation processing is started.

[0127] When the predefined program is started, output unit 12 outputs initial values ​​of the control parameters to memory 21 (step S10). At this point, output unit 12 can, for example, output initial values ​​of control parameters containing predefined values, it can, for example, output initial values ​​of control parameters containing user-defined values, or it can, for example, output initial values ​​of control parameters containing values ​​calculated using a user-defined calculation method.

[0128] When the control parameters are output by output unit 12, memory 21 stores the control parameters output by output unit 12 (step S15).

[0129] Then the control parameter generation device 10 replaces the initial value 1 with an int X (step S20).

[0130] The description assumes that the initial value to be replaced in int X is 1, but the initial value is not necessarily limited to 1; it can be an integer between 1 and N-1 inclusive. The initial value to be replaced in int X can, for example, be determined by the user.

[0131] After the selection unit 19 has selected representative operations comprising X operations, the production device 20 next performs X operations among N operations under the control of the control unit 18 (step S25). The X operations selected by the selection unit 19 can be, for example, user-defined operations, predefined operations, or operations actively determined using a user-defined determination method. In a case where the user determines X operations to be performed by the production device 20, the determination is achieved, for example, by executing the representative operation determination processing described later.

[0132] When the production device 20 performs the X operations, the sensor 30 outputs X measurement data, each corresponding to the X operations, to the control parameter generating device 10 (step S30).

[0133] The acquisition unit 11 then acquires the X measurement data, each corresponding to the X operations of the sensor 30 (step S35).

[0134] When the acquisition unit 11 acquires the X measurement data, the determination unit 13 determines the settling time for each of the X measurement data (step S40).

[0135] When the determining unit 13 determines the X setting times, the generating unit 14 checks whether the end condition for the optimization processing is met (step S45).

[0136] In step S45, if the end condition for the optimization processing is not met (step S45: No), the generation unit 14 performs the optimization processing to shorten at least the longest settling time among the X settling times (step S50). Preferably, the control parameter optimization processing is performed such that all X settling times are equal to or less than a target value. The generation unit 14 then generates update control parameters that are optimized such that at least the longest of the X settling times is shortened in the optimization processing (step S55).

[0137] The output unit 12 outputs the generated update control parameters to the production facility 20 to store these parameters in memory 21 (step S60).

[0138] Memory 21 captures the output control parameters and updates the control parameters to be stored using the captured control parameters (step S65).

[0139] When the processing of step S65 ends, the processing of the first control parameter generation continues with the processing of step S25.

[0140] In the processing of step S45, the control parameter generation device 10 checks, in a case where the end condition of the optimization processing is met (step S45: Yes), whether the value of int X is equal to N (step S70).

[0141] During the processing of step S70, the control parameter generating device 10 replaces int X with an integer between X+1 and N, inclusive, in a case where the value of int X is not equal to N (step S70: No), i.e., in a case where the value of int X is less than N (step S75).

[0142] When the processing of step S75 ends, the processing of the first control parameter generation continues with the processing of step S25.

[0143] In the processing of step S70, the processing of the first control parameter generation ends when the value int X equals N (step S70: Yes).

[0144] It should be noted that if the determination unit 13 determines the X compensation times in the processing of step S40, the image generation unit 16 can generate an image that shows the status of the optimization processing at the present time, and the display unit 17 can output the image generated by the image generation unit 16.

[0145] Fig. Figure 9 is a schematic diagram showing an example of the image described above, which is displayed by the display unit 17.

[0146] In Fig. The display “5” in the right-hand column of the “Optimization Level” column indicates that the number of times an integer in int X is replaced in the first control parameter generation process currently being executed is 5 times; that is, the first control parameter generation process currently being executed is a process to repeat the loop processing from the processing of step S25 via the processing of step S45: Yes and the processing of step S70: No and returning four times to the processing of step S25.

[0147] The display of “1” in the “Number of representative operations” column in the “first stage” indicates that the integer “1” is being used in int X for the first time, i.e., during the processing of step S20.

[0148] The display of “2” in the “Number of representative operations” column in “the second stage” indicates that the integer “2” is being used for the second time in int X, i.e., during the processing of step S75, which is being executed for the first time in the loop processing.

[0149] The display of “8” in the “Number of representative operations” column in “the third stage” indicates that the integer “8” is being replaced in int X for the third time, i.e., during the processing of step S75, which is being executed for the second time in the loop processing.

[0150] The display of “32” in the “Number of representative operations” column in “the fourth stage” indicates that the integer “32” is being replaced in int X for the fourth time, i.e., during the processing of step S75, which is being executed for the third time in the loop processing.

[0151] The display of “80” in the “Number of representative operations” column in the “fifth stage” indicates that the integer “80” is being inserted into int X for the fifth time, i.e., during the processing of step S75, which is being executed for the fourth time (namely, the last time) in the loop processing.

[0152] The display of “2” in the “Maximum optimization time (h)” column in the “first stage” to “fifth stage” indicates that the end condition for the optimization processing in each stage includes a condition that the specified time period during which the optimization processing (i.e., the processing of step S50) is repeated is two hours, i.e., a condition that the upper limit for the repetition of the optimization processing in each stage is two hours.

[0153] The display of “12” in the column “Settling time (ms) for the termination of optimization” in “the first stage” indicates that the termination condition for the optimization processing in the first stage contains a condition where the settling time for the repetition of the optimization processing is 12 ms, i.e., a condition where an upper limit for the repetition of the optimization processing in the first stage is that the settling time determined during the processing of step S40 is 12 ms.

[0154] The display “23” in the column “Settling time (ms) for the end of the optimization” in “the second stage” to “the fifth stage” indicates that the end condition for the optimization processing in each of the second stage to the fifth stage includes a condition that the settling time for the repetition of the optimization processing is 23 ms, i.e., a condition that an upper limit for the repetition of the optimization processing in each of the second stage to the fifth stage is that the X settling times determined during the processing of step S40 become 23 ms or less.

[0155] The display of “12” in the “minimal settling time” column in “the first stage” means that a minimum value of the settling time determined in the first stage is 12 ms.

[0156] The display “23” in the “minimal settling time” column in “the second stage” means that a minimum value of the settling time determined in the second stage is 23 ms.

[0157] The display “45” in the “minimal settling time” column in “the third stage” indicates that a minimum value of the settling time determined in the third stage is currently 45 ms.

[0158] Empty sections in the columns “minimal settling time” in “the fourth stage” and “the fifth stage” indicate that the settling time in the fourth and fifth stages is not determined.

[0159] A line graph 210 in a right-hand diagram shows the time transition of the settling time determined in the first stage, a line graph 220 shows the time transition of the settling time determined in the second stage, and a line graph 230 shows the time transition of the settling time determined in the third stage.

[0160] Next, the processing of the condition capture will be described.

[0161] The condition capture processing is a processing operation to capture a condition at the time of execution of the first control parameter generation processing operation.

[0162] Here, the condition acquisition processing is described as processing to acquire the number of times an integer is replaced in int X, a numeric value is replaced at a time of an integer replacement in int X, and the optimization processing end condition, which is used for processing in step S65 in the first control parameter generation processing. The end condition for the optimization processing is such that the optimization processing is executed for a predetermined duration, or the X settling times, determined in the processing of step S40, are equal to or less than a predetermined time.

[0163] The condition acquisition processing is started, for example, by the user of the control parameter generation system 1 performing an operation to start the condition acquisition processing via the operating receiver unit 15.

[0164] Fig. Figure 10 is a flowchart of condition capture processing.

[0165] As in Fig. As shown in Figure 10, when the condition acquisition processing is started, the operating receiving unit 15 starts a predetermined program to execute the condition acquisition processing (step S110).

[0166] When the specified program is started, the image generation unit 16 generates an image to prompt the user of the control parameter generation system 1 to enter conditions for executing the first control parameter generation process. The display unit 17 then shows the generated image (step S120).

[0167] When the image is displayed, the operating receiver unit 15 waits until the user has finished entering the conditions for executing the first control parameter generation processing (step S130: No, repeat loop of step S120).

[0168] Fig. Figure 11 is a schematic diagram showing an example of the image described above, which is displayed by the display unit 17. Fig. Figure 11 shows an example of the drawing in a state where a condition for the execution of the first control parameter generation processing is entered by the user.

[0169] In Fig. 11 indicates that the display “5” in the right column of the “Optimization Level” column shows that the number of replacements of an integer in int X in the first control parameter generation processing is 5, where the integer is entered by the user.

[0170] The "1" displayed in the "Number of Representative Operations" column in the "first stage" indicates that the integer to be replaced in int X is initially "1", where the integer is either entered by the user or set as a default value. It should be noted that, as described above, the initial value to be replaced in int X is set to the default value "1", so the user does not need to enter the initial value.

[0171] The display of “2” in the “Number of representative operations” column in the “second stage” indicates that the integer to be replaced a second time in int X is “2”, where the integer is entered by the user.

[0172] The display of “8” in the “Number of representative operations” column in the “third stage” means that the integer to be replaced in int X on the third occasion is “8”, where the integer is entered by the user.

[0173] The display “32” in the “Number of representative operations” column in the “fourth level” indicates that the integer to be replaced for the fourth time in int X is “32”, where the integer is entered by the user.

[0174] The display of “80” in the “Number of Representative Operations” column in the “fifth level” indicates that the integer inserted into int X for the fifth time is “80”, where the integer is entered by the user.

[0175] The display of "2" in the "Maximum Optimization Time (h)" column for stages one through five indicates that the predefined time period in the optimization condition is 2 hours at each stage, with the predefined time period being entered by the user. In other words, the display of "2" indicates that a condition where the upper limit for repetition of the optimization process at each stage is 2 hours is entered by the user as the end condition for the optimization process at each stage.

[0176] The display "12" in the "Settling time (ms) for the end of optimization" column in the "first stage" indicates that the predetermined time in the end condition of the optimization processing in the first stage is 12 ms, where the predetermined time is entered by the user. That is, the above display indicates that the upper limit of the optimization processing iteration in the first stage is set to the settling time, determined in the processing of step S40, which is 12 ms. This is the condition entered by the user as the optimization processing end condition in the first stage.

[0177] The display "23" in the column "Settling time (ms) to end optimization" in each of the "second stage" through the "fifth stage" indicates that the predetermined time interval in the end condition of the optimization processing in each of the second through the fifth stage is 23 ms, where the predetermined time interval is entered by the user. That is, the above display indicates that the user must enter as the optimization processing end condition in each of the second through the fifth stage a condition such that the upper limit of the optimization processing iteration is set to 23 ms, the settling time determined in the processing of step S40.

[0178] Returning to Fig. The description of the condition recording continues in section 10.

[0179] When the user has finished entering the condition for executing the first control parameter generation processing in step S130 (step S130: Yes), the operator receiving unit 15 captures the condition for executing the first control parameter generation processing, where the condition is entered by the user (step S140).

[0180] When processing ends in step S140, the processing of the condition capture is terminated.

[0181] Next, the processing of the representative operation name will be described.

[0182] The processing to determine representative operations is a process to determine each of the X operations to be executed in the respective stages when the initial control parameter generation process is performed. Hereinafter, the X operations to be executed in the respective stages are also referred to as the "representative operations" in those stages.

[0183] The processing of the representative operation name is started, for example, by the user of the control parameter generation system 1 performing an operation to start the processing of the representative operation name via the operating receiver unit 15.

[0184] Fig. Figure 12 is a flowchart of the label processing for representative operations.

[0185] As in Fig. As shown in Figure 12, when the identification processing for representative operations is started, the operating receiving unit 15 starts a predetermined program to execute the identification processing for representative operations (step S210).

[0186] When the predetermined program is started, the image generation unit 16 generates an image to prompt the user of the control parameter generation system 1 to specify the X operations to be performed in the respective phases when the first control parameter generation processing is executed. The display unit 17 then displays the generated image (step S220).

[0187] When the image is displayed, the operator receiving unit 15 waits until the user completes the determination to perform the X operations automatically at each stage when the first control parameter generation processing is executed, or the determination to perform the X operations manually at each stage when the first control parameter generation processing is executed (repeat loop processing in step S230: No and in step S220).

[0188] Fig. Figure 13 is a schematic diagram showing an example of the image described above, which is displayed by the display unit 17. Fig. Figure 13 shows an example of (1) the user determination to manually determine the X operations to be performed at each stage, and the drawing above in a state where (2) the user has manually determined the X operations to be performed at each stage.

[0189] In Fig. 13. A black circle on the left side of the "manual representative selection" indicates that the user has made a determination to manually define the X operations to be performed in each stage. Conversely, if the user has made a determination to automatically define the X operations to be performed in each stage, the black circle is displayed on the left side of the "automatic representative selection".

[0190] A white circle on the left side of “representative operation in the first stage” indicates that corresponding operations (the operations designated by the operation names at the left end of the table, the same applies below) have been determined by the user as the X operations to be performed in the first stage.

[0191] Similarly, the white circles in the columns “representative operation in the second stage” to “representative operation in the fifth stage” indicate that the corresponding operations have been determined by the user to be the X operations to be performed in the second to fifth stages.

[0192] Returning to Fig. The description of the condition recording continues in section 12.

[0193] In the processing of step S230, when the user completes the determination to automatically perform the X operations to be carried out in each stage during the execution of the first control parameter generation processing, or the determination to manually perform the X operations to be carried out in each stage during the execution of the first control parameter generation processing (step S230: Yes), the operating receiving unit 15 checks whether the user has made the determination to automatically perform the X operations to be carried out in each stage during the execution of the first control parameter generation processing (step S240).

[0194] In the processing of step S240, if the user has not specified to automatically execute the X operations to be performed at each stage during the execution of the first control parameter generation processing (step S240: No), i.e., if the user has specified to manually execute the X operations to be performed at each stage during the execution of the first control parameter generation processing, the operator receiving unit 15 determines the X operations to be performed at each user-specified stage as the X representative operations at each stage (step S250).

[0195] In the processing of step S240, if the user has determined to automatically perform the X operations to be carried out at each stage during the execution of the first control parameter generation processing (step S240: Yes), the operator receiving unit 15 determines the X operations to be carried out at each stage during the execution of the first control parameter generation processing based on a predetermined algorithm (step S260).

[0196] For example, the operating receiving unit 15 can determine the predetermined operations as the X operations to be performed at each stage, or operations that satisfy a predetermined condition as the X operations to be performed at each stage.

[0197] When the processing of step S260 ends, the operating receiving unit 15 determines the X operations to be performed in each stage, wherein the X operations are determined during the processing of step S260 as the X representative operations in each stage (step S270).

[0198] In a case where the processing of step S250 ends, and in a case where the processing of step S270 ends, the processing of the representative operation label ends. <diskussion>

[0199] The control parameter generating device 10 with the configuration described above does not directly search for suitable control parameters for all N (e.g., 80) operations to be performed by the production device 20, but first searches for suitable control parameters for one or some (e.g., one) of the N operations, searches for suitable control parameters based on a previous search result while incrementally increasing the number of target operations, and finally searches for suitable control parameters for all N operations in order to generate the appropriate control parameters.

[0200] Therefore, the control parameter generating device 10 with the above configuration can generate control parameters more efficiently and reliably than generating the appropriate control parameters by directly searching for the appropriate control parameters for all N operations to be performed by the production device 20.

[0201] As described above, the control parameter generating device 10 can efficiently generate suitable control parameters with the configuration described above.

[0202] Furthermore, the inventors conducted an experiment using a simulation model for a production device by comparing the settling time achieved when the control parameters are generated using the conventional method of generating suitable control parameters by directly searching for the appropriate control parameters for all N operations to be performed by the production device 20 with the settling time achieved when the control parameters used for the production device 20 are generated using the control parameter generating device 10.

[0203] Fig. Figure 14 is a schematic diagram showing an experimental result.

[0204] As in Fig. As shown in Figure 14, the settling time achieved when the control parameters are generated using the conventional method is 36 [ms], and the settling time achieved when the control parameters are generated using the control parameter generation device 10 is 23 [ms].

[0205] As described above, the inventors verified through this experiment that the settling time can be reduced by about 35% when the control parameter generating device generates 10 control parameters, compared to using the conventional method. (Second embodiment)

[0206] A control parameter generation system according to a second embodiment is described below. This system is configured by partially modifying the configuration of the control parameter generation system 1 according to the first embodiment.

[0207] The control parameter generation system 1 according to the first embodiment is an example of a configuration in which the optimization processing performed by the control parameter generation device 10 is a processing to shorten the settling time. On the other hand, the control parameter generation system according to the second embodiment is an example of a configuration in which the optimization processing performed by a control parameter generation device according to the second embodiment is a processing to reduce a degree of deviation, which will be described later.

[0208] Here, in the control parameter generation system according to the second embodiment, components similar to those of control parameter generation system 1 have already been described and designated with the same reference numbers; a detailed description of these is omitted, and differences from control parameter generation system 1 are mainly described. <konfiguration>

[0209] Fig. Figure 15 is a block diagram showing a configuration of a control parameter generation system 1A according to the second embodiment.

[0210] As in Fig. As shown in Figure 15, the control parameter generation system 1A is configured by changing the control parameter generation device 10 of the control parameter generation system 1 according to the first embodiment into a control parameter generation device 10A. Furthermore, the control parameter generation device 10A is configured such that the determination unit 13, the generation unit 14, and the optimization algorithm 140 of the control parameter generation device 10 are each changed into a determination unit 13A, a generation unit 14A, and an optimization algorithm 140A, respectively.

[0211] For each of the one or more operations recorded by the detection unit 11, the determination unit 13A, in a case where a time zone exists in which the object to be driven 24 does not fall within a permissible range allowed by the target position when the position of the object to be driven 24 is set to the target position, determines for the operations, based on the measurement data corresponding to the operations, an extent to which the object to be driven does not fall within the permissible range in the time zone, i.e., an extent of deviation.That is, while in the first embodiment the evaluation index is the settling time until the position deviation between the position of the object 24 to be driven and the target position converges within the permissible range, in the second embodiment the evaluation index is an integrated value of a deviation time during which the position deviation between the position of the object 24 to be driven and the target position deviates from the permissible range or a position deviation amount.

[0212] The following is a specific example of the extent of deviation determined by the unit of measurement 13A, with reference to the drawings.

[0213] Fig. 16A and Fig. Figure 16B shows schematic representations illustrating an example of the transition of the position deviation of the object 24 to be driven with respect to the target position when the production device 20 moves the object 24 to be driven into the target position.

[0214] In Fig. 16A and Fig. In 16B, the horizontal axis represents time and the vertical axis represents the positional deviation of the object 24 to be driven relative to the target position.

[0215] As in Fig. 16A and Fig. As shown in Figure 16B, when its position is set to the target position, the object 24 to be driven occasionally deviates from the permissible range after the object 24 to be driven has reached the permissible range.

[0216] In such a case, as for example in Fig. As shown in 16A, the determination unit 13A determines the sum of the times during which the object 24 to be driven does not fall within the permissible range after the object 24 to be driven has first reached the permissible range (hereinafter also referred to as the "first sum") as the extent of the deviation.

[0217] It should be noted that the determination unit 13A can calculate the first sum by adding a weight based on the elapsed time since the start of the stop or the start of the transfer of the object 24 to be driven. That is, the determination unit 13A can calculate the first sum by adding a larger weight (penalty) if the elapsed time since the start of the stop or the transfer of the object 24 to be driven is longer. This can reduce a relatively large fluctuation of the object 24 to be driven after a relatively long time has elapsed since the start of the stop or the transfer of the object 24 to be driven.

[0218] Alternatively, in such a case, the determination unit 13A determines, for example as in Fig. Figure 16B shows the sum of the integrated values ​​of the position deviation at the times when the object 24 to be driven does not fall within the permissible range, after the object 24 to be driven has initially reached the permissible range (hereinafter also referred to as the "second sum"), as the extent of the deviation.

[0219] It should be noted that if the length of time during which the object 24 to be driven does not fall within the permissible range is equal to or less than a threshold value, the determination unit 13A can exclude this time period from an addition target of the second sum. This can provide resistance to sensor noise generated in a short time.

[0220] The description of the control parameter generation system 1A is given in Fig. Continued on page 15.

[0221] The generating unit 14A generates update control parameters by updating the control parameters in the optimization processing to reduce at least the largest extent of deviation among one or more extents of deviation, each corresponding to one or more operations detected by the acquiring unit 11 and determined by the determining unit 13A.

[0222] As in Fig. As shown in Figure 15, the generating unit 14A contains an optimization algorithm 140A for optimizing the control parameters to reduce the deviation time. The generating unit 14A then uses the optimization algorithm 140A to perform the optimization processing in order to reduce at least the largest extent of the deviation among the one or more extents of the deviation determined by the determining unit 13A.

[0223] The optimization algorithm 140A can, for example, be a known algorithm such as a Bayesian optimization algorithm, an evolutionary strategy algorithm (CMA-ES), or a genetic algorithm (GA), as described for the optimization algorithm 140 according to the first embodiment. Furthermore, the optimization processing for reducing the magnitude of the deviation using the optimization algorithm 140A can, for example, be a known processing operation performed using the known algorithm described above.

[0224] Similar to the generating unit 14 according to the first embodiment, the generating unit 14A can generate the update control parameters by performing the optimization processing once, or it can generate the update control parameters by repeatedly performing the optimization processing until the end condition for the optimization processing is satisfied.

[0225] Here, the end condition for the optimization process is, for example, a time interval during which the optimization process is repeated. In this case, the generation unit 14A repeats the optimization process for a predetermined time interval.

[0226] Furthermore, the end condition for the optimization process is, for example, a number of repetitions of the optimization process. In this case, the generation unit 14A repeats the optimization process a certain number of times.

[0227] Furthermore, the end condition for the optimization processing is, for example, a measure that is satisfied by one or more measures of the deviation. In this case, the generating unit 14A repeats the optimization processing until one or more measures of the deviation become equal to or less than a predetermined measure. <ablauf>

[0228] The following describes a process that is carried out by the control parameter generation system 1A with the above configuration.

[0229] Instead of the first control parameter generation processing according to the first embodiment, the control parameter generation system 1A performs a second control parameter generation processing in which part of the first control parameter generation processing is modified.

[0230] The second processing step for generating control parameters is a processing step for generating control parameters that are used for the production device 20, similar to the first processing step for generating control parameters.

[0231] Fig. Figure 17 is a flowchart of the second control parameter generation.

[0232] In the second control parameter generation process, the processing of steps S305 to S335, S345, and S360 to S375 is similar to the processing of steps S5 to S35, S45, and S60 to S75 in the first control parameter generation process. Control parameter generation device 10, destination unit 13, and generation unit 14 in the first control parameter generation process are each read as control parameter generation device 10A, destination unit 13A, and generation unit 14A, respectively, and the first control parameter generation process is read as the second control parameter generation process.

[0233] Therefore, the processing of the second control parameter generation is described here, with a focus on the processing in step S340, the processing in step S350 and the processing in step S355.

[0234] When the acquisition unit 11 acquires X measurement data in step S335, the determination unit 13A determines a magnitude of deviation for each of the X measurement data (step S340). The processing then continues with the processing of step S345.

[0235] In the processing of step S345, if the end condition for the optimization processing is not met (step S345: No), the generating unit 14A performs the optimization processing to reduce at least the largest deviation among the X deviation dimensions (step S350). Preferably, the control parameter optimization processing is performed such that all X deviation dimensions are equal to or less than a target value. The generating unit 14A then generates update control parameters that are optimized to reduce at least the largest deviation among the X deviation dimensions in the optimization processing (step S355). The processing then continues with the processing of step S345. <diskussion>

[0236] Similar to the control parameter generating device 10, the control parameter generating device 10A with the above configuration does not directly search for suitable control parameters for all N (e.g. 80) operations to be performed by the production device 20, but first searches for suitable control parameters for one or some (e.g. one) of the N operations, searches for suitable control parameters based on a previous search result while the number of target operations is incrementally increased, and finally searches for suitable control parameters for all N operations in order to generate the appropriate control parameters.

[0237] Therefore, with the above configuration, the control parameter generating device 10A, similar to the control parameter generating device 10, can generate the control parameters more efficiently and reliably than generating the appropriate control parameters by directly searching for the appropriate control parameters for all N operations performed by the production device 20.

[0238] As described above, the control parameter generating device 10A, with the configuration described above, can efficiently generate suitable control parameters similarly to the control parameter generating device 10. (Third embodiment)

[0239] A control parameter generation system according to a third embodiment is described below. This system is configured by partially modifying the operations of control parameter generation system 1 according to the first embodiment. <konfiguration>

[0240] The control parameter generation system according to the third embodiment has the same hardware configuration as the control parameter generation system according to the first embodiment, but the software to be executed is partially changed.

[0241] In the control parameter generation system according to the third embodiment, the components that are similar to those of control parameter generation system 1 and are designated with the same reference numbers have already been described. Therefore, a detailed description is omitted, and mainly the differences are described. <ablauf>

[0242] Instead of the first control parameter generation processing and the representative operation determination processing according to the first embodiment, the control parameter generation system according to the third embodiment performs a third control parameter generation processing in which the first control parameter generation processing is partially modified.

[0243] The third processing step for generating control parameters is a processing step for generating control parameters that are used for production device 20, similar to the first processing step for generating control parameters.

[0244] Fig. Figure 18 is a flowchart of the third control parameter generation process.

[0245] In the third control parameter generation process, the processing from step S405 to the processing in step S465 is similar to the processing from step S5 to the processing of step S65 in the first control parameter generation process. The first control parameter generation process is read as the third control parameter generation process.

[0246] Therefore, the third control parameter generation processing is described here, with a focus on the processing from step S525 to the processing of step S545 and the processing from step S570 to the processing of step S580.

[0247] When the processing of step S420 ends, the production device performs 20 Y operations (step S525), where Y is an integer between X+1 and N (inclusive).

[0248] When the production device 20 performs the Y operations, the sensor 30 outputs Y measurement data, each corresponding to the Y operations, to the control parameter generating device 10 (step S530).

[0249] The acquisition unit 11 then acquires the Y measurement data, each corresponding to the Y operations of the sensor 30 (step S535).

[0250] When the acquisition unit 11 acquires the Y measurement data, the determination unit 13 determines a settling time for each of the Y measurement data (step S540).

[0251] When determining the settling time for each of the Y measurement data, the determination unit 13 selects representative operations from the Y operations based on a predetermined algorithm X (step S545).

[0252] Fig. Figure 19 is a schematic diagram showing an example of a state in which the determining unit 13 selects the X representative operations from the Y operations. The in Fig. Example 19 is an example for the case where Y equals 40 and X equals 2.

[0253] As in Fig. As shown in Figure 19, the determining unit 13 can, for example, determine the settling times of the Y operations that occur in the processing of step S540 (see (a) in Fig. 19) were determined, sort in ascending order of settling times (see (b) in Fig. 19) and X operations that are in a predetermined order as the representative operations (see (c) in Fig. 19).

[0254] Returning to Fig. Section 18 continues the description of the third control parameter generation process.

[0255] When the processing of step S545 ends, the processing of the third control parameter generation continues with the processing of step S445.

[0256] In the processing of step S445, if the end condition for the optimization processing is met (step S445: Yes), the control parameter generator 10 replaces int X with an integer between X+1 and N (inclusive) (step S570). The control parameter generator 10 then checks whether the value of int X is equal to N (step S575).

[0257] In the processing of step S575, in a case where the value of int X is not equal to N (step S575: No), i.e., in a case where the value of int X is less than N, the third control parameter generation processing goes back to step S525.

[0258] In the processing of step S575, according to the third embodiment, in a case where the value of int X is equal to N (step S575: Yes), the control parameter generation system performs a processing to update the parameters through all operations (step S580).

[0259] Fig. Figure 20 is a flowchart of the parameter update processing through all operations.

[0260] As in Fig. As shown in Figure 20, when the processing of the parameter update through all operations has started, the production device 20 performs the N operations under the control of the control unit 18 (step S581).

[0261] When the production device 20 performs the N operations, the sensor 30 outputs N measurement data, each corresponding to the N operations, to the control parameter generating device 10 (step S582).

[0262] The acquisition unit 11 then records the N measurement data, each corresponding to the N operations of the sensor 30 (step S583).

[0263] When the acquisition unit 11 acquires the N measurement data, the determination unit 13 determines a settling time for each of the N measurement data (step S584).

[0264] When the determining unit 13 determines the N settling times, the generating unit 14 checks whether the end condition for the optimization processing is met (step S585).

[0265] In the processing of step S585, if the end condition for the optimization processing is not met (step S585: No), the generation unit 14 performs the optimization processing to at least shorten the longest settling time among the N settling times (step S586). The generation unit 14 then generates update control parameters that are optimized to at least shorten the longest settling time among the N settling times in the optimization processing (step S587).

[0266] The output unit 12 outputs the generated update control parameters to the production facility 20 to store these parameters in memory 21 (step S588).

[0267] Then, memory 21 records the output control parameters and updates the control parameters to be stored using the recorded control parameters (step S589).

[0268] When the processing of step S589 ends, the processing of the parameter update through all operations resumes with the processing of step S581.

[0269] In the processing of step S585, if the end condition of the optimization processing is met (step S585: Yes), the processing of the parameter update by all operations ends.

[0270] Returning to Fig. Section 18 continues the description of the third control parameter generation.

[0271] When the processing of step S580, i.e., the processing of parameter generation through all operations, ends, the processing of the third control parameter generation also ends.

[0272] It should be noted that, as described, during the processing of step S545, the determination unit 13 sorts the determined Y settling times in ascending order and selects X operations that are in the specified order as representative operations. However, the determination unit 13 is not necessarily limited to the example where the X operations are selected as the representative operations using this procedure. For example, the determination unit 13 can group the Y operations into X operation groups containing similar operations and select one operation with the most characteristic settling time (e.g., the longest settling time) in each operation group as the X representative operations. <diskussion>

[0273] Similar to the control parameter generating device 10 according to the first embodiment, the control parameter generating device 10 according to the third embodiment, which performs the above operations, does not directly search for suitable control parameters for all N (e.g. 80) operations to be performed by the production device 20, but first searches for suitable control parameters for one or some (e.g. one) of the N operations, searches for suitable control parameters based on a previous search result while incrementally increasing the number of target operations, and finally searches for suitable control parameters for all N operations in order to generate the suitable control parameters.

[0274] Therefore, the control parameter generating device 10 according to the third embodiment, which performs the above operations, can generate the control parameters more efficiently and reliably than the generation of the suitable control parameters by directly searching for the suitable control parameters for all N operations to be performed by the production device 20, similar to the control parameter generating device 10 according to the first embodiment.

[0275] In this way, the control parameter generating device 10 according to the third embodiment, which performs the above operations, can efficiently generate suitable control parameters, similar to the control parameter generating device 10. (Fourth embodiment)

[0276] In the third embodiment, the parameter update processing is performed by all N operations in the last stage among a plurality of stages in the control parameter optimization processing as an evaluation operation for the comprehensive evaluation of the operations of the production device 20. However, the parameter update processing can be performed at least once in a specific stage midway through the plurality of stages, either instead of in the last stage or in addition to the execution in the last stage. The evaluation operation is performed in at least one time interval during which the representative operations are carried out in each stage, and in a transition interval from a specific stage to the next stage. A precise comprehensive evaluation can be performed by causing the production device 20 to perform all operations as an evaluation operation, as in the third embodiment.

[0277] The evaluation operation is not limited to all operations, but can be a difference operation between all operations and the last representative operation with respect to the evaluation operation. The difference operation is a remaining operation obtained from all N operations by excluding the operation contained in the last representative operation. During the evaluation operation, the control unit 18 instructs the production device 2 to execute only the difference operation. By instructing the production device 2 to perform the difference operation between all operations and the last representative operation with respect to the evaluation operation, the efficiency of the evaluation operation can be improved while maintaining the accuracy of the comprehensive evaluation.Alternatively, the evaluation operation is not limited to all operations and can be a prescribed operation selected from all available operations. For example, a variety of predetermined operations are identified as the prescribed operations in descending order of their influence on the operational performance of production device 20 among all operations. In the evaluation operation, the control unit 18 instructs production device 2 to execute only the prescribed operations. As an evaluation operation, the efficiency of the evaluation operation can be improved by instructing production device 20 to execute one prescribed operation from among all available operations.

[0278] Control unit 18 determines whether the evaluation result of the comprehensive evaluation meets a predetermined optimization end condition and terminates the control parameter optimization processing if the evaluation result meets the optimization end condition. The optimization end condition can be a target value of the evaluation value with respect to the evaluation operation, an upper limit on the total time of the optimization processing repetitions in all stages up to the current time, or an upper limit on the execution time of the optimization processing in all stages up to the current time.For example, in a case where the target value of the evaluation is defined as the optimization end condition, control unit 18 determines that the optimization end condition is not met if the evaluation value of the last evaluation operation exceeds a target value, but determines that the optimization end condition is met if the evaluation value of the last evaluation operation is equal to or less than the target value. In a case where the evaluation result of the comprehensive evaluation fulfills the optimization end condition by performing the evaluation operation, the optimization processing ends even before the representative operations reach the final stage, and thus the time required for the optimization processing can be reduced. (Fifth embodiment)

[0279] In each of the above embodiments, the number (X) of representative operations is incrementally increased as the stages of control parameter optimization processing progress through the multitude of stages, but the content of the operations can be changed without increasing the number of operations.

[0280] For example, the number of representative operations can be set to four (X = 4) in all multiple stages, and the selection unit 19 can reselect four representative operations each time the end condition for optimization processing is satisfied and the stages continue.

[0281] An example of a method for selecting the X representative operations at each stage by the selection unit 19 is as follows. It should be noted that the selection method described below is not limited to the fifth embodiment, in which the number of representative operations is fixed at all stages, and is also applicable to the first through fourth embodiments, in which the number of representative operations is changed at each stage.

[0282] In a first example, the selection unit 19 randomly selects X representative operations from all N operations.

[0283] As a second example, selection unit 19 selects the X representative operations according to a predefined selection rule. An example of a selection rule to be set could be a rule according to which simpler operations are selected earlier and more complex operations later. That is, a rule could be designed such that the content of the representative operations becomes more complex as the control parameter optimization processing progresses.

[0284] As a third example, the selection unit 19 randomly arranges all N operations, and the first X operations in each order are selected as representative operations. When the selection position reaches the end of the field, the selection unit 19 returns to the top of the same field and repeats the selection.

[0285] As a fourth example, selection unit 19 randomly orders all N operations, and the first X operations are selected as representative operations. When the selection position reaches the end of the array, selection unit 19 again randomly orders all N operations and selects the operations in order of their head.

[0286] As a fifth example, the selection unit 19 divides all N operations into X groups and randomly selects a representative operation from each group.

[0287] As a sixth example, the selection unit 19 classifies all N operations into X groups containing similar operations based on a similarity, such as a waveform of the measurement data or the rating value, randomly arranges a multitude of operations belonging to each group, and sequentially selects one operation from the arrangement in each group as the representative operation.

[0288] As a seventh example, the selection unit classifies 19 all N operations into X groups based on the similarity described above, identifies an operation with the highest rating (e.g., the most recent rating) or the highest past average rating among the multitude of operations belonging to each group as an operation to be improved, and selects X operations to be improved, each of which is designated as the representative operation for the X groups in the next control parameter optimization processing. The past average rating can be an average of the ratings over the entire period or an average of a predetermined number of the most recent ratings.

[0289] As an eighth example, the selection unit classifies all N operations into X groups based on a correlation similarity that represents a change tendency of the multitude of evaluation values, identifies an operation with the largest evaluation value (e.g., the most recent evaluation value) or the largest past average of the evaluation values ​​among the multitude of operations belonging to each group as the operation to be improved, and selects X operations to be improved, each of which is determined for the X groups as the representative operations in the next control parameter optimization processing. The past average can be an average of the evaluation values ​​over the entire period or an average of a predetermined number of the most recent evaluation values.

[0290] It should be noted that selection unit 19 can perform the group classification in examples five through eight multiple times. Selection unit 19 can reclassify the groups each time the evaluation operation described later (step S71) is performed, it can reclassify the groups at regular intervals, or it can reclassify the groups each time the evaluation result of the representative operation or the evaluation operation improves by a certain threshold or more.

[0291] As a ninth example, the selection unit 19 randomly selects the X representative operations from all N operations and randomly selects the X representative operations from the unselected operations, excluding the selected operation, in the next and subsequent operations. If the number of unselected operations is less than X, X representative operations are again randomly selected from all N operations.

[0292] As a tenth example, the selection unit 19 randomly selects X representative operations from all N operations and, for the next and subsequent operations, randomly selects X-1 representative operations from the unselected operations, with the exception of one operation that has the lowest score among the current X representative operations and the selected operation. If the number of unselected operations is less than X, X representative operations are again randomly selected from all N operations.

[0293] It should be noted that in each of the multiple stages of the control parameter optimization processing, X representative operations can only be performed once, or that a multitude of sets, each containing X representative operations, can be performed until the end condition for the optimization processing is satisfied.

[0294] Furthermore, as in the fourth embodiment, at least one evaluation operation can be performed in the middle of the plurality of stages. Fig. Figure 21 is a flowchart of the first control parameter generation process. As shown in Fig. As shown in Figure 21, the evaluation operation can be performed after each of the several stages of the control parameter optimization processing (step S71). If the evaluation result meets the optimization end condition (step S72: Yes), the optimization processing can be terminated. If the evaluation result does not meet the optimization end condition (step S72: No), the next X representative operations can be selected (step S24), and the control parameter optimization processing can be performed in the next stage. (Sixth embodiment)

[0295] The sixth embodiment describes details of the optimization algorithm 140 used by the generation unit 14. The optimization algorithm 140 is essentially the evolutionary strategy algorithm (CMA-ES). This algorithm is used to define a search range of control parameters for update candidates in the next stage of the control parameter optimization processing, based on a plurality of evaluation values ​​calculated in the current stage of the control parameter optimization processing, and to change an evaluation criterion of the control parameter optimization processing between the current stage and the next stage.That is, using the optimization algorithm 140, the generation unit 14 performs the first optimization processing on the information (in this example, control parameters) using a first evaluation criterion, sets the search range of the information based on the multitude of evaluation values ​​calculated in the first optimization processing, and performs the second optimization processing on the information using a second evaluation criterion that differs from the first evaluation criterion for the set search range.

[0296] Here, changing the evaluation criterion includes, for example, changing the representative operation, as in the first and fifth embodiments. Changing the representative operation includes, for example, changing the number of operations contained in the representative operation at each of the multiple stages, as in the first embodiment. Changing the number of operations includes, for example, increasing the number of operations as the stage progresses, as in the first embodiment. Changing the representative operation includes specifying the number of operations contained in the representative operation at each of the multiple stages, as in the fifth embodiment, and changing the content of the operations. Furthermore, changing the content of the operations includes making the content of the operations more complex as the stage progresses, as in the fifth embodiment.

[0297] Furthermore, changing the evaluation criterion involves changing an evaluation index at each of the multiple stages. For example, in a case where the settling time is currently used as the evaluation index, the magnitude of the deviation (an integrated value of a deviation time or a position deviation amount) will be used as the evaluation index at the next stage. Evaluation indices other than the settling time and the magnitude of the deviation can also be used. Alternatively, the weighted sum of the evaluation indices for the settling time and the magnitude of the deviation can be used, and the weight value to be multiplied by each evaluation index can be changed at each of the multiple stages.

[0298] In information optimization, the process can progress faster by using a different rating index, a weighted sum of several rating indices, or a weighted sum of the rating index to be improved and another rating index than by using the rating index ultimately to be improved. However, it is not always clear which rating index to use effectively, or the effective weighting value of each rating index is unknown. In this procedure, the generating unit 14 dynamically changes the rating index or weighting value to be used to cope with a case where the rating index or weighting value is unknown. It should be noted that not only the weighted sum, but also any rating calculation (e.g.,(logarithmic sum) can be used with a variety of evaluation values ​​from a variety of evaluation indices. Furthermore, in this procedure, the user can select a desired evaluation calculation from a variety of evaluation calculations stored in advance in memory unit 42, or the generation unit 14 can dynamically change the evaluation calculation at any stage of the optimization processing.

[0299] Furthermore, the generating unit 14 can repeatedly perform the information optimization processing, stochastically changing the rating index or weighting value to be used, and store a database in the storage unit 42 or another storage unit in which a correspondence relationship between the rating index or weighting value used and the final rating value of the rating index to be improved is accumulated. The progress of the optimization can be promoted by increasing the probability that the rating index or weighting value with which the good rating value is obtained will be easily selected again. It should be noted that the generating unit 14 can change the rating index or weighting value to be used in each of the several stages of the optimization processing or once in several stages.Furthermore, the generating unit 14 can randomly change the rating index or weighting value to be used in each stage, use the same rating index or weighting value in several consecutive stages, or use the same rating index or weighting value in several non-consecutive stages.

[0300] Since the effective setting of the rating index or weighting value to be used changes in each of the several stages of the optimization processing, the progress of the optimization can be promoted by dynamically changing the rating index or weighting value as described above.

[0301] Furthermore, in a case where a large number of rating indices are to be improved simultaneously, the generating unit 14 can change the number of rating indices alternatively or randomly, or the rating index or the weighting value to be used in accordance with a predefined rule. In this case, the generating unit 14 can increase the frequency of use of this rating index if the number of rating indices includes a rating index that has not met a target.

[0302] Furthermore, the generating unit 14 can change the evaluation index by switching the sensor used to measure an object during the optimization process. For example, the generating unit 14 can first perform a coarse optimization using a primary sensor with low measurement accuracy but high noise resistance, which can be measured quickly. It can then perform a fine optimization using a secondary sensor with high measurement accuracy but low noise resistance, which requires more time for measurement due to the need for multiple measurements.

[0303] Furthermore, the generating unit 14 can change the evaluation index by switching the content of the preprocessing applied during the execution of the optimization processing. For example, the generating unit 14 can switch to use the time-domain measurement data obtained from a measured waveform and the measurement data obtained by frequency analysis of the earlier measurement data to convert it into a frequency domain.

[0304] The generation unit 14 can change a parameter to be set during the execution of the optimization processing.

[0305] Fig. Figure 22 is a flowchart showing a processing sequence performed by the information processing unit 41.

[0306] First, in step S100, the generation unit 14 sets the initial values ​​of the control parameters as in steps S5 to S20. Fig. 7.

[0307] Next, in step S101, selection unit 19 chooses a representative operation from all N operations to be performed in the first stage.

[0308] In step S102, the control unit 18 causes the production device 20 to perform the representative operation selected by the selection unit 19, as described in step S25 of Fig. 7.

[0309] In step S103, the acquisition unit 11 records measurement data relating to the operations of the production device 20, wherein the measurement data are measured by the sensor 30 during the performance of the representative operations, as in steps S30 to S35 of Fig. 7.

[0310] In step S104, the determination unit 13 calculates a rating value of the rating index based on the measurement data recorded by the acquisition unit 11, as in step S40 of Fig. 7.

[0311] Next, in step S105, the generation unit 14 determines whether the end condition for the optimization processing is met.

[0312] In a case where the end condition for the optimization processing is not met (step S105: No), the generating unit 14 updates the control parameters in step S106 based on the evaluation value calculated by the determining unit 13, as in steps S50 to S65 of Fig. 7, and repeats the processing in step S102 and the following steps.

[0313] In a case where the end condition for the optimization processing is met (step S105: Yes), the control unit 18 in step S107 causes the production device 20 to perform the evaluation operation as in step S71 of Fig. 21.

[0314] Next, in step S108, the generation unit 14 determines whether the evaluation result satisfies the optimization end condition, as in step S72 of Fig. 21.

[0315] If the condition for the end of the optimization is met (step S108: Yes), the processing of the control parameter optimization is terminated.

[0316] In a case where the optimization end condition is not met (step S108: No), the generating unit 14 in step S109 uses the optimization algorithm 140 to determine the search range of the control parameters of the update candidates in the control parameter optimization processing in the next stage based on the multitude of evaluation values ​​calculated in the control parameter optimization processing in the current stage.

[0317] Next, in step S110, the generating unit 14 changes the evaluation criterion (the number of representative operations in the example of Fig. 7), e.g. as in step S75 of Fig. 7. In the next stage of the control parameter optimization processing, the control parameter optimization processing is carried out using the search area defined in step S109 and the evaluation criterion changed in step S110.

[0318] It should be noted that in the sixth embodiment, the image generation unit 16 also produces an image similar to that in Fig. 9 can generate (i.e., an image indicating the status of the optimization processing), and the display unit 17 can display the image as in the first embodiment. In this case, the total number of evaluation criteria to be applied can be used instead of the “optimization levels” of the one in Fig. The information shown in Figure 9 can be displayed. Instead of the "Number of representative operations," the content of the evaluation criterion applied at each stage can be displayed. Instead of the "Maximum optimization time," the maximum execution time of the optimization process using the evaluation criterion applied at each stage can be displayed. Instead of the "Settling time for the completion of the optimization," the target performance (e.g., the target evaluation value) of the optimization process using the evaluation criterion applied at each stage can be displayed. Furthermore, instead of the "Minimum settling time," the best execution value of the optimization process using the evaluation criterion applied at each stage can be displayed.

[0319] Fig. Figure 23 is a diagram that schematically illustrates a procedure for setting a search area using the generation unit 14. For simplicity, only two control parameters, P1 and P2, are considered here. The horizontal coordinate axis shows the value of control parameter P1, and the vertical axis shows the value of control parameter P2.

[0320] In the first phase, the optimization of the control parameters is performed using an evaluation criterion V1, and a multitude of (in this example, six) evaluation values ​​are plotted on the coordinates. Each recorded evaluation value is the worst value among the X evaluation values ​​obtained by the X representative operations. The generation unit 14 determines a multitude of top evaluation values ​​from the multitude of recorded evaluation values. Fig. Figure 23 shows the multitude of top ratings with white circles and the other ratings with black circles. The generation unit 14 calculates the central coordinates and the covariance matrix of the multiple top ratings using the optimization algorithm 140 of CMA-ES to define a search area W1 for the next stage. The wide search area W1 is defined when the multitude of top ratings is dispersed over a wide area, and the narrow search area W1 is defined when the multitude of top ratings is concentrated in a narrow area.

[0321] In the second stage, the control parameter optimization processing for the search area W1 is performed using an evaluation criterion V2 that differs from the evaluation criterion V1, and a plurality of (in this example, six) evaluation values ​​are plotted on the coordinates. As described above, the generating unit 14 determines a plurality of upper evaluation values ​​from the plurality of recorded evaluation values ​​and calculates the mean coordinates and the covariance matrix of the plurality of upper evaluation values ​​using the optimization algorithm 140 of CMA-ES to define a search area W2 for the next stage.

[0322] In the third stage, the control parameter optimization processing for the search area W2 is performed using a rating criterion V3 that differs from rating criterion V2, and a plurality of (in this example, six) rating values ​​are plotted on the coordinates. As described above, the generating unit 14 determines a plurality of top rating values ​​from the plurality of recorded rating values ​​and calculates the mean coordinates and the covariance matrix of the plurality of top rating values ​​using the optimization algorithm 140 of CMA-ES to define a search area W3 for the next stage. The same processing as described above is then repeated in the fourth and subsequent stages, and the values ​​of the control parameters P1 and P2 that ultimately yield the best rating values ​​are adopted.

[0323] According to the sixth embodiment, the control parameter optimization process is executed multiple times while the evaluation criterion for the control parameter optimization process is changed. As described above, suitable control parameters can be efficiently generated by repeatedly executing the control parameter optimization process while changing the evaluation criterion.

[0324] Furthermore, by transferring the setting information via the search area W of the control parameters from the current (current-stage) control parameter optimization processing to the next (next-stage) control parameter optimization processing, suitable control parameters can be efficiently searched for in the next control parameter optimization processing.

[0325] In the sixth embodiment, the description was given using a simple implementation example of the CMA-ES, which is an example of the evolutionary strategy. However, a more complex implementation or a different scheme of the evolutionary strategy can also be used. (Seventh embodiment)

[0326] The seventh embodiment illustrates a method for notifying the user of status information indicating the progress of the control parameter optimization processing and the operating condition. Each operation performed by the production device 20 is an operation carried out by the production device 20 to move the driven object 24 into a target position.

[0327] Fig. Figure 24 is a diagram showing part of the operating condition information 400, which partially simplifies and describes an execution condition for each operation performed by the production device 20. The operating condition information 400 is stored in the memory unit 42. The operating condition information 400 contains an ID as identification information for each operation performed by the production device 20. The operating condition information 400 also contains user-defined settings for a transmission speed, an acceleration and deceleration time (an acceleration time and a deceleration time), the number of iterations, a waiting time, and a stop position, all associated with each ID. It should be noted that the operating condition does not refer to the operation described in Figure 24. Fig. The example shown in section 24 is limited as long as the condition contains at least one element of the ID, the transmission amount, the transmission speed, the acceleration time, and the deceleration time. Furthermore, the condition can also include other elements. Fig. The operating condition contains 24 elements not shown. A user can randomly set the operating condition of each operation by operating input unit 44 to enter the condition setting information. Furthermore, the user can randomly set the maximum time for the continuation of the control parameter optimization processing and the maximum number of control parameter updates by operating input unit 44 to enter the condition setting information. The operating condition information 400 also includes default setting elements relating to the transmission speed and the acceleration and deceleration times associated with each ID. If the user does not enter the condition setting information via input unit 44, the respective default values ​​for the transmission speed and the acceleration and deceleration times are used.It should be noted that in a case where different operating conditions are set by default for each device to be set, the user can enter device selection information to select the device to be set via input unit 44, so that the appropriate default setting value for the selected device is used.

[0328] Fig. Figure 25 is a flowchart showing the process carried out by the information processing unit 41 in conjunction with a notification to a user about status information.

[0329] First, in step S200, the acquisition unit 11 acquires the operating condition information 400 from the storage unit 42.

[0330] Next, in step S201, the image generation unit 16 acquires the status information based on the operating condition information 400 acquired by the acquisition unit 11 and the progress information from the control parameter optimization processing. The image generation unit 16 acquires the progress information from the control unit 18. The control unit 18 creates a database of operation history information, including the execution time and operating condition for each operation performed by the production device 20 during the control parameter optimization processing, and stores the database in the storage unit 42. The output unit 12 can display the operation history information read from the storage unit 42 on the display unit 17 or output the operation history information externally.

[0331] The operating condition information 400 contains information about the maximum time for the continuation of the control parameter optimization processing, which is set based on the condition setting information, and the maximum number of control parameter updates. The progress information contains information indicating a stage currently being executed among the multiple stages of the control parameter optimization processing, and information indicating an operation currently being set among the multiple representative operations. Furthermore, the progress information contains information about the elapsed time (time passed since the start of the optimization) and the number of control parameter update times (the number of parameter update times) from the start of the first stage of the control parameter optimization processing until the present time.The image generation unit 16 calculates the remaining time (remaining adjustment time) until the maximum time by subtracting the elapsed time from the start of the adjustment until the present from the maximum time, and it calculates the remaining number of time points (the number of remaining update time points) until the maximum number of time points by subtracting the number of parameter update time points until the present from the maximum number of time points.

[0332] In step S202, the image generation unit 16 creates a status notification image to notify the user of the status information.

[0333] Fig. Figure 26 is a diagram showing an example of a status message screen. The status message screen contains elements 300, which indicate elapsed time (the time elapsed since the start of the adjustment) and remaining time (the remaining time of the adjustment); elements 301, which indicate the number of update times (the number of parameter update times) and the number of remaining times (the number of remaining update times); an element 302, which indicates the current number of operations to be adjusted (i.e., the current number of representative operations); and elements 303, which indicate operating conditions relating to one of the representative operations currently being adjusted. It should be noted that the status message screen does not refer to the one in Figure 26. Fig. The example shown in 26 is limited, and that the Fig. Some of the information presented in section 26 may be omitted or different, as shown in the original text. Fig. 26 additional pieces of information may be included that are not shown. Furthermore, the elapsed time since the start of the adjustment, the remaining adjustment time, the number of parameter updates, and the number of remaining updates can be displayed using a progress bar, allowing the user to easily and intuitively understand their relationships.

[0334] Next, in step S203, the image generation unit 16 inputs the image data of the generated status message image into the display unit 17. Based on the input image data, the display unit 17 shows the Fig. The status notification image shown is 26. It should be noted that a mode for notifying the user about status information is not limited to displaying an image, but can also include voice output or similar via a speaker.

[0335] According to the seventh embodiment, by outputting the status information for user notification, the user can easily check the progress status, operating conditions, or similar aspects of the control parameter optimization processing through the notification, thus improving user convenience. (Additional information)

[0336] The technology disclosed in the present application has been described above with reference to the first to seventh embodiments. However, the present disclosure is not limited to the first to seventh embodiments. The scope of one or more aspects of the present disclosure may include aspects in which various modifications conceivable by those skilled in the art are applied to the present embodiments or modifications, or aspects formed by combining components in different embodiments or modifications without departing from the core of the present disclosure.

[0337] (1) The first to seventh embodiments have shown, by way of example, that the control parameter generating devices 10 and 10A are implemented by a computer device. However, the control parameter generating devices 10 and 10A are not necessarily limited to the example achieved by a computer device, as long as the same functions can be achieved. The control parameter generating devices 10 and 10A can, for example, be implemented by a plurality of computer devices that can communicate with each other.

[0338] (2) The comprehensive or specific aspects of this disclosure may be implemented by a system, a device, a method, an integrated circuit, a computer program, or a computer-readable, non-transitory recording medium, such as a compact disc read-only storage device (CD-ROM). Furthermore, the aspects may be implemented by any combination of a system, a device, a method, an integrated circuit, a program, and a non-transitory recording medium. For example, this disclosure may be implemented as a program that causes a computer device to perform processing carried out by a control parameter generating device. Commercial applicability

[0339] The present disclosure is generally applicable to a system or similar device that generates control parameters. QUOTES INCLUDED IN THE DESCRIPTION

[0000] This list of documents cited by the applicant was automatically generated and is included solely for the reader's convenience. The list is not part of the German patent or utility model application. The DPMA accepts no liability for any errors or omissions. Cited patent literature

[0000] WO 2018 / 151215 A

[0004] < / diskussion> < / ablauf> < / konfiguration> < / diskussion> < / ablauf> < / konfiguration> < / diskussion> < / ablauf> < / konfiguration>

Claims

[1] An information processing method for optimizing a plurality of control parameters in a device that performs a plurality of operations based on the plurality of control parameters, the method comprising: by an information processing device, in the control parameter optimization processing: selecting a representative operation including at least one operation from the plurality of operations that can be performed by the device, causing the device to perform the selected representative operation, acquiring measurement data relating to an operation of the device, the measurement data being measured by performing the representative operation, calculating an evaluation value of a predetermined evaluation index based on the acquired measurement data, and updating the plurality of control parameters based on the calculated evaluation value; and Executing the control parameter optimization processing multiple times while changing an evaluation criterion of the control parameter optimization processing. [2] The information processing method according to claim 1, wherein the change in the evaluation criterion includes a change in the representative operation. [3] The information processing method according to claim 2, wherein the change of the representative operation includes a change of a number of operations in the representative operation. [4] The information processing method according to claim 3, wherein the change in the number of operations includes an increase in the number of operations. [5] The information processing method according to claim 2, wherein the change of the representative operation includes a change of a content of an operation included in the representative operation. [6] The information processing method according to claim 5, wherein the change in the content of the operation includes complicating a content of the operation. [7] The information processing method according to claim 2, wherein, in changing the representative operation, all of the plurality of operations are classified into a plurality of groups based on the similarity, an operation to be improved from the plurality of operations included in each of the plurality of groups is determined based on the evaluation value or a past average value of the evaluation value, and a plurality of the operations to be improved determined for the plurality of groups are selected as the representative operation in the control parameter optimization processing at a next time point. [8] The information processing method according to claim 1, wherein the change in the evaluation criterion includes a change in the evaluation index. [9] Information processing method according to claim 8, wherein each of the plurality of operations is an operation that causes the device to transfer an object to a target position, and the evaluation index includes a settling time until a position deviation between a position of the object and the target position converges within an allowable range. [10] Information processing method according to claim 8, wherein each of the plurality of operations is an operation that causes the device to transfer an object to a target position, and the evaluation index includes an integrated value of a deviation time at which a position deviation between a position of the object and the target position deviates from an allowable range, or a position deviation amount. [11] The information processing method according to claim 1, further comprising: setting a search range of the control parameters that are update candidates in the control parameter optimization processing at a next time point based on a plurality of the evaluation values calculated in the control parameter optimization processing at a current time point. [12] The information processing method according to claim 1, further comprising: causing the device to perform a predetermined evaluation operation for comprehensively evaluating an operation of the device in comprehensive evaluation processing; acquiring measurement data regarding the operation of the device measured in performing the evaluation operation; calculating an evaluation value of the evaluation index based on the acquired measurement data; and performing the comprehensive evaluation based on the calculated evaluation value. [13] The information processing method according to claim 12, wherein the evaluation operation is all operations. [14] The information processing method according to claim 12, wherein the evaluation operation is a difference operation between all operations and a last representative operation with respect to the evaluation operation. [15] The information processing method according to claim 12, wherein the evaluation operation is a prescribed operation defined in advance from all the operations. [16] The information processing method according to claim 12, further comprising: determining whether the evaluation result of the comprehensive evaluation satisfies a predetermined end condition; and terminating the control parameter optimization processing in a case where the evaluation result satisfies the end condition. [17] Information processing method according to claim 1, wherein each of the plurality of operations is an operation that causes the device to move an object to a target position, the method further comprises outputting status information to a user for notification relating to at least one of the following elements: the time elapsed since the start of the optimization of the control parameters; a remaining time up to a maximum time for continuing the optimization of the control parameters; an operation condition including at least one of the following information: identification information, a transmission amount, a transmission speed, an acceleration time, and a deceleration time with respect to an operation currently being performed among the at least one operation included in the representative operation; a number of operations included in the representative operation; a number of update times of the control parameters; and a remaining number of times up to a maximum number of times of updating the control parameters. [18] The information processing method according to claim 17, further comprising updating the status information upon each change in the evaluation criterion. [19] The information processing method according to claim 17, further comprising setting the maximum time, the operation condition and the maximum number of times based on condition setting information input by a user. [20] The information processing method according to claim 17, wherein the operating condition is preset for each device, the method further comprising setting the operating condition in accordance with the selected device based on device selection information input by a user. [21] The information processing method according to claim 1, further comprising recording operation history information including an execution time and an operation condition for each operation performed by the device in the control parameter optimization processing. [22] Information optimization methods, including: by an information processing device, Performing a first optimization processing of information based on a first evaluation criterion; Setting a search range of the information based on a plurality of evaluation values calculated in the first optimization processing; and Performing second optimization processing on the information about the specified search range using a second evaluation criterion. [23] An information processing apparatus that optimizes a plurality of control parameters in a device that performs a plurality of operations based on the plurality of control parameters, the apparatus comprising: a selection unit, a control unit, a recording unit, a calculation unit and an updating unit, in optimizing control parameters, the selection unit selects a representative operation that includes at least one operation from the plurality of operations that can be performed by the device, the control unit causes the device to perform the representative operation selected by the selection unit, the acquisition unit acquires measurement data on an operation of the device which were measured when performing the representative operation, the calculation unit calculates an evaluation value of a predetermined evaluation index based on the measurement data acquired by the acquisition unit, the updating unit updates the plurality of control parameters based on the evaluation value calculated by the calculating unit, and the control parameter optimization processing is executed multiple times while changing an evaluation criterion of the control parameter optimization processing. [24] A program for causing an information processing device to function as a selection means, a control means, a detection means, a calculation means and an updating means, wherein the information processing device optimizes a plurality of control parameters in a device that performs a plurality of operations based on the plurality of control parameters, where in the control parameter optimization processing, the selection means selects a representative operation comprising at least one operation from the plurality of operations that can be performed by the device, the control means causes the device to perform the representative operation selected by the selection means, the detection means detects measurement data on an operation of the device which were measured when the representative operation was carried out, the calculation means calculates an evaluation value of a predetermined evaluation index on the basis of the measurement data acquired by the acquisition means, the updating means updates the plurality of control parameters based on the evaluation value calculated by the calculating means, and the control parameter optimization processing is executed multiple times while changing an evaluation criterion of the control parameter optimization processing.

Images