Information processing method, information processing device, and program

Abstract

This information processing device: selects at least one representative operation from among all operations that can be executed by equipment; causes the equipment to execute the selected representative operation; acquires measurement data of a predetermined evaluation index as measured during the execution of the representative operation; and updates control parameters on the basis of the acquired measurement data. Further, the information processing device: causes the equipment to execute a predetermined evaluation operation for comprehensively evaluating the operation of the equipment, in at least one of a first period during which a first representative operation is executed, a second period during which a second representative operation is executed, and a third period between the first period and the second period; acquires measurement data of the evaluation index as measured during the execution of the evaluation operation; and performs the comprehensive evaluation on the basis of the acquired measurement data, and outputs result data indicating the evaluation result of the comprehensive evaluation.

Description

[Technical Field]

[0001] The present disclosure relates to an information processing method, an information processing apparatus, and a program. [Background Art]

[0002] A method for generating control parameters according to background art is disclosed in, for example, Patent Document 1.

[0003] Conventionally, generation of appropriate control parameters has been desired. [Prior Art Literature] [Patent Literature]

[0004] [Patent Document 1] International Publication No. 2018 / 151215 [Summary of the Invention]

[0005] An object of the present disclosure is to obtain an information processing method, an information processing apparatus, and a program that can efficiently generate appropriate control parameters.

[0006] An information processing method according to one aspect of the present disclosure is an information processing method for optimizing control parameters in a device that performs multiple operations based on multiple control parameters, wherein the information processing device, in a control parameter optimization process, selects at least one representative operation from all operations that the device can perform, causes the device to perform the selected representative operation, acquires measurement data of a predetermined evaluation index measured during the execution of the representative operation, updates the control parameters based on the acquired measurement data, the representative operation includes a first representative operation and a second representative operation performed after the first representative operation, and in an evaluation result output process, causes the device to perform a predetermined evaluation operation for comprehensively evaluating the operation of the device during at least one of the first period in which the first representative operation is performed, the second period in which the second representative operation is performed, and the third period between the first and second periods, acquires measurement data of the evaluation index measured during the execution of the evaluation operation, performs the comprehensive evaluation based on the acquired measurement data, and outputs result data showing the evaluation result of the comprehensive evaluation. [Brief explanation of the drawing]

[0007] [Figure 1] This figure shows a simplified configuration of a control parameter generation device according to an embodiment of the present disclosure. [Figure 2] This diagram shows a simplified example of control parameters. [Figure 3] This diagram shows a simplified example of a selection rule. [Figure 4] This is a schematic diagram illustrating an example of the change in the positional deviation of the driven object relative to the target position. [Figure 5] This diagram shows a simplified example of measurement data output by a sensor. [Figure 6] This flowchart shows the processes performed by the information processing unit. [Figure 7] This flowchart shows the details of the control parameter optimization process. [Figure 8] This flowchart shows the details of the evaluation result output process. [Figure 9]This figure shows a simplified example of an image containing evaluation results for representative and evaluation actions. [Figure 10] This figure shows a simplified variation of an image containing evaluation results related to representative and evaluation actions. [Figure 11] This figure shows a magnified portion of the image shown in Figure 9. [Figure 12] This figure shows a magnified view of some other examples of images containing evaluation results. [Modes for carrying out the invention]

[0008] (Knowledge that forms the basis of this disclosure) In production equipment equipped with drive units such as servo motors that drive objects, a method has recently been proposed to generate appropriate control parameters for the drive unit by searching for appropriate control parameters using machine learning models or the like (see, for example, Patent Document 1).

[0009] Generally, the control parameters for drive units used in production equipment can number 50 or more. Furthermore, the adjustment gradations can exceed 100.

[0010] For example, if a production machine performs 80 operations, has 50 control parameters for the drive source, and has 100 adjustment levels for the control parameters, then the number of combinations of these is 100. 50 This results in 80 different combinations.

[0011] The inventors found a problem in that when generating control parameters for such a vast number of combinations, using machine learning models or the like to search for appropriate control parameters can result in an enormous amount of time being required to find appropriate control parameters due to the search range being too broad, or even a situation where appropriate control parameters cannot be reached no matter how much time is spent.

[0012] Therefore, the inventors diligently conducted experiments and studies to realize a parameter generation method that can efficiently generate appropriate control parameters even when generating control parameters for a vast number of combinations.

[0013] Through the above experiments and studies, the inventors found that instead of searching for appropriate control parameters for all of the vast number of combinations from the beginning, if the production equipment performs, for example, 80 operations, the first step is to search for appropriate control parameters for only a few of these 80 operations, for example, just one operation, that is, for only a portion of the vast number of combinations. In the next step, the number of operations performed by the production equipment is increased, for example, to combinations of two operations, and appropriate control parameters are searched for using the search results from the first step as a starting point. In the next step, the number of operations performed by the production equipment is further increased, for example, to combinations of four operations, and appropriate control parameters are searched using the search results from the previous step as a starting point. By repeating this process and finally searching for appropriate control parameters for all 80 operation combinations, the inventors found that it is possible to generate appropriate control parameters for all 80 operation combinations more efficiently and reliably.

[0014] Based on this knowledge, the inventors conducted further experiments and studies, and arrived at the control parameter generation method and other related inventions described below.

[0015] Next, we will describe each aspect of this disclosure.

[0016] An information processing method according to a first aspect of the present disclosure is an information processing method for optimizing the control parameters in an apparatus that executes a plurality of operations based on a plurality of control parameters, wherein an information processing apparatus: in a control parameter optimization process, selects at least one representative operation from among all operations executable by the apparatus, causes the apparatus to execute the selected representative operation, acquires measurement data of a predetermined evaluation index measured during execution of the representative operation, and updates the control parameters based on the acquired measurement data; the representative operation includes a first representative operation and a second representative operation executed after the first representative operation; and in an evaluation result output process, causes the apparatus to execute a predetermined evaluation operation for comprehensively evaluating the operation of the apparatus in at least one of a first period in which the first representative operation is executed, a second period in which the second representative operation is executed, and a third period between the first period and the second period, acquires measurement data of the evaluation index measured during execution of the evaluation operation, performs the comprehensive evaluation based on the acquired measurement data, and outputs result data indicating an evaluation result of the comprehensive evaluation.

[0017] According to the first aspect, appropriate control parameters can be efficiently generated by updating the control parameters by causing the apparatus to execute representative operations among all operations, and repeating the optimization process while gradually increasing the number of operations included in the representative operations, for example. Further, since comprehensive evaluation is performed by causing the apparatus to execute a predetermined evaluation operation in at least one of the first period in which the first representative operation is executed, the second period in which the second representative operation is executed, and the third period between the first period and the second period, and result data indicating the evaluation result is output, it is possible to present to a user the progress of optimization of control parameters for the overall operation of the apparatus in an intermediate stage of the optimization process.

[0018] An information processing method according to a second aspect of the present disclosure is the information processing method according to the first aspect, wherein the evaluation operation is preferably all of the operations.

[0019] According to the second aspect, accurate comprehensive evaluation can be performed by causing the apparatus to execute all operations as the evaluation operation.

[0020] In the third aspect of this disclosure, the information processing method, in the second aspect, allows for selecting the next representative operation based on the execution results of all operations performed as the evaluation operation in the control parameter optimization process.

[0021] According to the third embodiment, the next representative operation can be appropriately selected based on the results of the most recent operations.

[0022] In the information processing method according to the fourth aspect of this disclosure, in the third aspect, in the control parameter optimization process, all operations performed as evaluation operations are clustered into multiple clusters, and the next representative operation is selected from each cluster.

[0023] According to the fourth aspect, the next representative operation can be appropriately selected.

[0024] In the fifth aspect of this disclosure, the information processing method is such that, in the first aspect, the evaluation operation is the difference operation between the total operation and the most recent representative operation of the evaluation operation.

[0025] According to the fifth embodiment, by having the device perform the difference between the total operation and the most recent representative operation of the evaluation operation as an evaluation operation, it becomes possible to improve the efficiency of the evaluation operation while maintaining the accuracy of the overall evaluation.

[0026] In the information processing method relating to the sixth aspect of this disclosure, in the first aspect, the evaluation operation is a predetermined operation selected from all operations.

[0027] According to the sixth embodiment, the efficiency of the evaluation operation can be improved by having the device execute predetermined operations selected from all operations as the evaluation operation.

[0028] In the information processing method according to the seventh aspect of this disclosure, in the first aspect, when outputting the result data, an image showing the evaluation result is generated as the result data, and the generated image is displayed on the display unit.

[0029] According to the seventh embodiment, by displaying an image showing the evaluation results on the display unit, it becomes possible to clearly present to the user the progress of the control parameter optimization.

[0030] The information processing method according to the eighth aspect of this disclosure, in the seventh aspect, further calculates an evaluation value of the evaluation index for the representative operation based on the measurement data acquired in connection with the execution of the representative operation, and the image preferably includes time-series data of the evaluation value for the representative operation and time-series data of the evaluation value for the evaluation operation.

[0031] According to the eighth aspect, the image showing the evaluation results includes time-series data of evaluation values ​​related to representative operations and time-series data of evaluation values ​​related to evaluation operations, thereby making it possible to present the progress of control parameter optimization to the user in an easy-to-understand manner.

[0032] In the ninth aspect of this disclosure, the information processing method further includes, in the eighth aspect, the addition of time-series data of the evaluation values ​​for the representative operation by extracting evaluation values ​​corresponding to the representative operation from among the evaluation values ​​of the evaluation index for the evaluation operation.

[0033] According to the ninth aspect, by extracting evaluation values ​​corresponding to representative actions from the evaluation values ​​of evaluation indicators related to evaluation actions, it becomes possible to add time-series data of evaluation values ​​related to representative actions and present their characteristics to the user in an extended or retrospective manner.

[0034] In the eighth aspect of the information processing method according to the tenth aspect of this disclosure, it is preferable to further accept an input operation by the user requesting the selection of one evaluation value from the time-series data of the evaluation values ​​relating to the representative operation, and to set the control parameters for the next time the evaluation operation is executed based on the control parameters when the representative operation corresponding to the one evaluation value is executed.

[0035] According to the tenth embodiment, the user can easily set the control parameters for the next evaluation operation by inputting while looking at the screen displayed on the display unit, thereby improving user convenience.

[0036] In the first embodiment, the information processing method according to the eleventh aspect of this disclosure further determines whether the evaluation result of the overall evaluation satisfies a predetermined termination condition, and if the evaluation result satisfies the termination condition, the optimization process of the control parameters is terminated.

[0037] According to the 11th embodiment, if the evaluation result of the overall evaluation satisfies predetermined termination conditions, the optimization process is terminated even before the representative operation reaches the final stage, thereby shortening the time required for the optimization process.

[0038] In the first embodiment, the information processing method according to the twelfth aspect of this disclosure further accepts an input operation from a user requesting the execution of the evaluation operation, and causes the device to execute the evaluation operation based on the execution request.

[0039] According to the twelfth embodiment, the user can have the device perform an evaluation operation by inputting a request to perform an evaluation operation, thereby improving user convenience.

[0040] In the first embodiment, the information processing method according to the thirteenth aspect of this disclosure further calculates an evaluation value of the evaluation index for the representative action based on the measurement data acquired in connection with the execution of the representative action, calculates the variance of the multiple evaluation values ​​for the multiple representative actions, and sets the number of times to execute the evaluation action next based on the variance.

[0041] According to the 13th embodiment, the number of times an evaluation action to be performed next can be appropriately set based on the variance of multiple evaluation values ​​for multiple representative actions, thereby improving the accuracy of the overall evaluation.

[0042] In the first embodiment, the information processing method according to the fourteenth aspect of this disclosure further calculates an evaluation value of the evaluation index for the representative operation based on the measurement data acquired in connection with the execution of the representative operation, and sets the control parameters for the next time the evaluation operation is executed based on the multiple evaluation values ​​for the multiple representative operations.

[0043] According to the 14th embodiment, it becomes possible to appropriately set the control parameters for the next time an evaluation operation is performed based on multiple evaluation values ​​for multiple representative operations.

[0044] In the information processing method according to the 15th aspect of this disclosure, in the 14th aspect, when setting the control parameters, the control parameters used when executing the representative operation corresponding to the best evaluation value among the plurality of evaluation values ​​are set as the control parameters when executing the evaluation operation next time.

[0045] According to the 15th embodiment, the control parameters for the next evaluation operation can be appropriately set based on the control parameters used when executing the representative operation corresponding to the best evaluation value among multiple evaluation values, thereby improving the accuracy of the overall evaluation.

[0046] An information processing method according to a 16th aspect of the present disclosure is an information processing method for optimizing control parameters in a device that performs multiple operations based on multiple control parameters, wherein the information processing device selects at least one representative operation from all operations that the device can perform, causes the device to perform the selected representative operation, acquires measurement data of a predetermined evaluation index measured during the execution of the representative operation, updates the control parameters based on the acquired measurement data, causes the device to perform a predetermined evaluation operation for comprehensively evaluating the operation of the device during the period in which the representative operation is performed, acquires measurement data of the evaluation index measured during the execution of the evaluation operation, performs the comprehensive evaluation based on the acquired measurement data, and selects the next representative operation based on the result of the execution of the evaluation operation.

[0047] According to the 16th embodiment, the next representative operation can be appropriately selected based on the results of the most recent evaluation operation.

[0048] An information processing device according to a 17th aspect of this disclosure is an information processing device for optimizing control parameters in a device that performs multiple operations based on multiple control parameters, comprising a selection unit, a control unit, an acquisition unit, an update unit, and an output unit, wherein in a control parameter optimization process, the selection unit selects at least one representative operation from all operations that the device can perform, the control unit causes the device to perform the representative operation selected by the selection unit, the acquisition unit acquires measurement data of a predetermined evaluation index measured during the execution of the representative operation, and the update unit updates the control parameters based on the measurement data acquired by the acquisition unit. The representative operation includes a first representative operation and a second representative operation performed after the first representative operation. In the evaluation result output processing, the control unit causes the device to perform a predetermined evaluation operation for comprehensively evaluating the operation of the device during at least one of the following periods: a first period during which the first representative operation is performed, a second period during which the second representative operation is performed, and a third period between the first and second periods. The acquisition unit acquires measurement data of the evaluation index measured during the execution of the evaluation operation. The output unit performs the comprehensive evaluation based on the measurement data acquired by the acquisition unit and outputs result data indicating the evaluation result of the comprehensive evaluation.

[0049] According to the 17th embodiment, by having the device execute a representative operation from among all operations, the control parameters are updated, and by gradually increasing the number of operations included in the representative operation and repeating the optimization process, it becomes possible to efficiently generate appropriate control parameters. Furthermore, by having the device execute a predetermined evaluation operation during at least one of the first period in which the first representative operation is executed, the second period in which the second representative operation is executed, and the third period between the first and second periods, an overall evaluation is performed, and result data showing the evaluation result is output, making it possible to present the user with the progress of the optimization of the control parameters for the entire operation of the device at an intermediate stage of the optimization process.

[0050] A program according to the 18th aspect of this disclosure is a program for causing an information processing device for optimizing control parameters in a device that performs multiple operations based on multiple control parameters to perform a selection process, a control process, an acquisition process, an update process, and an output process, wherein in the control parameter optimization process, the selection process selects at least one representative operation from all operations that the device can execute, the control process causes the device to execute the representative operation selected by the selection process, the acquisition process acquires measurement data of a predetermined evaluation index measured during the execution of the representative operation, and the update process uses the measurement data acquired by the acquisition process to perform the control parameter optimization process. The parameters are updated, the representative operation includes a first representative operation and a second representative operation performed after the first representative operation, and in the evaluation result output process, the control process causes the device to perform a predetermined evaluation operation for comprehensively evaluating the operation of the device during at least one of the following periods: a first period during which the first representative operation is performed, a second period during which the second representative operation is performed, and a third period between the first and second periods, the acquisition process acquires measurement data of the evaluation index measured during the execution of the evaluation operation, and the output process performs the comprehensive evaluation based on the measurement data acquired by the acquisition process and outputs result data showing the evaluation result of the comprehensive evaluation.

[0051] According to the 18th embodiment, control parameters are updated by having the device execute a representative operation from among all operations, and by gradually increasing the number of operations included in the representative operation and repeating the optimization process, it becomes possible to efficiently generate appropriate control parameters. Furthermore, a comprehensive evaluation is performed by having the device execute a predetermined evaluation operation during at least one of the first period in which the first representative operation is executed, the second period in which the second representative operation is executed, and the third period between the first and second periods, and result data showing the evaluation results is output. This makes it possible to present the user with the progress of the optimization of the control parameters for the entire operation of the device at an intermediate stage of the optimization process.

[0052] This disclosure can also be implemented as a program that causes a computer to execute each characteristic configuration included in such a method or apparatus, or as a system that operates using such a program. It goes without saying that such a computer program can be distributed via a computer-readable, non-temporary recording medium such as a CD-ROM, or via a communication network such as the Internet.

[0053] (Embodiments of the present disclosure) Embodiments of this disclosure will be described in detail below with reference to the drawings. Elements denoted by the same reference numeral in different drawings refer to the same or corresponding elements. Furthermore, the components, their arrangement, connection configurations, and operating sequences shown in the following embodiments are examples and are not intended to limit this disclosure. This disclosure is limited only by the claims. Therefore, among the components in the following embodiments, those not described in the independent claims representing the highest-level concepts of this disclosure are described as constituting a more preferable configuration, even though they are not necessarily required to achieve the object of this disclosure.

[0054] Figure 1 is a simplified diagram showing the configuration of a control parameter generation system according to an embodiment of this disclosure. The control parameter generation system is a system that optimizes control parameters 31 by generating and updating control parameters 31 used for the target production equipment 2. The control parameter generation system comprises a control parameter generation device 1 and a sensor 3.

[0055] Production equipment 2 is equipment used to produce machinery, and is a mounting device, processing device, machining device, or transport device, etc., for mounting, processing, manufacturing, or transporting machinery. Production equipment 2 is installed, for example, on a factory production line.

[0056] Production apparatus 2 is capable of performing N operations (where N is an integer greater than or equal to 3). For example, N is 80. This disclosure is not limited to production apparatus 2, but is applicable to any apparatus capable of performing N operations.

[0057] The production apparatus 2 includes a storage unit 41, a control unit 42, a drive unit 43, and a drive target object 44.

[0058] The storage unit 41 is configured using an HDD, SSD, or semiconductor memory, etc.

[0059] The control unit 42 is configured using a processor such as a CPU.

[0060] The drive unit 43 is controlled by the control unit 42 to drive the object to be driven 44.

[0061] The drive unit 43 is, for example, a servo motor, a directional flow control valve for a fluid used to control a pneumatic artificial muscle arm, or a directional flow control valve for a fluid used to control a hydraulic arm. The servo motor may be, for example, a rotary motor or a linear motor.

[0062] The object to be driven 44 is an object driven by the drive unit 43. When the drive unit 43 is a servo motor, the object to be driven 44 is a head that transports the workpiece, or a nozzle attached to the head for picking up the workpiece. When the drive unit 43 is a directional flow control valve, the object to be driven 44 is a pneumatic artificial muscle arm or a hydraulic arm.

[0063] The control unit 42 controls the drive unit 43 by outputting a command to the drive unit 43 to move the drive object 44 to a predetermined target position. The command output by the control unit 42 to the drive unit 43 may be, for example, a position command that commands the position of the drive unit 43 or the drive object 44, or a torque command that commands the torque of the drive unit 43.

[0064] The memory unit 41 stores the control parameters 31 generated and updated by the control parameter generation device 1. The control unit 42 controls the drive unit 43 based on the control parameters 31 read from the memory unit 41. In other words, the control unit 42 uses the control parameters 31 when controlling the drive unit 43. The number of control parameters 31 is, for example, 50.

[0065] The control parameter generation device 1 includes an information processing unit 11, a storage unit 12, an input unit 13, a display unit 14, and a communication unit 15.

[0066] The information processing unit 11 is configured using a processor such as a CPU. The information processing unit 11 includes a selection unit 21, a control unit 22, an acquisition unit 23, an update unit 24, and an output unit 25, which are functions realized by the processor executing a program read from a computer-readable non-volatile recording medium such as a ROM. In other words, the above program is a program that causes the information processing unit 11, which is an information processing device mounted on the control parameter generation device 1, to function as a selection unit 21 (selection means), a control unit 22 (control means), an acquisition unit 23 (acquisition means), an update unit 24 (update means), and an output unit 25 (output means). Details of the processing content executed by each processing unit will be described later.

[0067] The storage unit 12 is configured using an HDD, SSD, or semiconductor memory, etc. The storage unit 12 stores control parameters 31, selection rules 32, measurement data 33, and estimation models 34.

[0068] Figure 2 is a simplified diagram showing an example of control parameters 31. Control parameters 31 include parameters a1 and a2 for adjusting the vibration frequency of the driven object 44, parameters b1 and b2 for adjusting the speed of the driven object 44, parameters c1 and c2 for adjusting the depth of singularities in the vibration characteristics of the driven object 44, and parameters d1 and d2 for adjusting the vibration amplitude of the driven object 44. Some of the control parameters 31 may have trade-off relationships with each other, such as parameters b1 and b2, and parameters c1 and c2 and parameters d1 and d2.

[0069] Figure 3 is a simplified diagram showing an example of selection rule 32. Selection rule 32 shows the rules for when the selection unit 21 selects at least one representative operation from all N operations that the production device 2 can perform. The representative operation is an operation that the control parameter generation device 1 has the production device 2 perform during the control parameter optimization process. In the example shown in Figure 3, the representative operation is performed in eight stages, from the first to the eighth stage, and the number of operations X included in the representative operation increases as the stage progresses. For example, the number of operations X in the first stage is 1, and the representative operation includes only operation 2. Also, the number of operations X in the second stage is 2, and the representative operation includes operations 3 and 6. Also, the number of operations X in the third stage is 4, and the representative operation includes operations 2, 7, 9... Also, the number of operations X in the fourth stage is 8, and the representative operation includes operations 1, 3, 7, 9... Also, the number of operations X in the fifth stage is 16, and the representative operation includes operations 2, 4, 6, 8, 10... Furthermore, the number of actions X in the 6th stage is 32, and the representative actions include actions 1, 3, 5, 7, 9, 10... Furthermore, the number of actions X in the 7th stage is 64, and the representative actions include actions 1, 2, 3, 5, 6, 7, 9, 10... Furthermore, the representative actions of the 8th stage include all actions 1 to 50.

[0070] The selection rule 32 is pre-specified by the user through operation input using the input unit 13. However, the selection rule 32 is not limited to user specification; the number and actions of representative actions at each stage may be pre-set according to a predetermined rule, or the number and actions of representative actions at each stage may be dynamically changed by a specific method specified by the user.

[0071] Furthermore, selection rule 32 may include setting information for the operations to be performed in the evaluation operation from among all N operations that the production device 2 can perform. The evaluation operation is an operation that the control parameter generation device 1 causes the production device 2 to perform in the evaluation result output processing in order to comprehensively evaluate the operation of the production device 2. In the example of this embodiment, the evaluation operation includes all operations. The evaluation operation is performed during the period in which the representative operation of each stage is performed, and during the transition period from one stage to the next, or at least one of the above. Note that in the example shown in Figure 3, the representative operation of the 8th stage, which includes all operations, may be performed as an evaluation operation that includes all operations.

[0072] Furthermore, the next representative action may be selected not only using selection rule 32, but also based on the execution results of all the most recent actions (step SP062) performed as evaluation actions. For example, multiple actions may be identified from all actions in order of worst evaluation value, and these multiple actions may be selected as the next representative action. Alternatively, all actions performed as evaluation actions may be clustered into multiple clusters, and the action with the worst evaluation value within each cluster, or an action randomly selected from each cluster, may be selected as the next representative action. This allows for the appropriate selection of the next representative action based on the execution results of all the most recent actions, which reflect the latest situation.

[0073] The evaluation action is not limited to all actions; it may also be the difference between all actions and the most recent representative action of the evaluation action in question. For example, during the period in which the representative action of the fourth stage is performed, since the representative action includes actions 1, 3, 7, 9, etc., the evaluation actions performed during that period include actions 2, 4, 5, 6, 8, 10, etc., which are the difference between all actions and the representative action. Similarly, during the period in which the representative action of the fifth stage is performed, since the representative action includes actions 2, 4, 6, 8, 10, etc., the evaluation actions performed during the transition period from the fifth stage to the sixth stage include actions 1, 3, 5, 7, 9, etc., which are the difference between all actions and the representative action.

[0074] Furthermore, the evaluation operation is not limited to all operations; it may also be a predetermined set of operations selected from all operations. For example, a set of operations can be designated as predetermined operations, in order of their impact on the operational performance of the production device 2. In the evaluation operation, the control parameter generation device 1 causes the production device 2 to execute only the predetermined operations.

[0075] Referring to Figure 1, the measurement data 33 is data showing the measured values ​​of predetermined evaluation indicators measured by the sensor 3 during the execution of representative and evaluation operations. Multiple measurement data 33 are stored in the storage unit 12 to form a database. The evaluation indicator can be any indicator that can quantitatively evaluate the operation of the production apparatus 2, and in this embodiment, settling time is used.

[0076] Sensor 3 measures the position of the driven object 44 in a time series during the representative operation and evaluation operation. It then transmits measurement data 33, which indicates the measurement position corresponding to each operation included in the representative operation and evaluation operation, to the control parameter generation device 1.

[0077] Figure 4 is a schematic diagram showing an example of the change in the positional deviation of the driven object 44 relative to the target position during the operation in which the production device 2 moves the driven object 44 to the target position.

[0078] In Figure 4, the horizontal axis represents time, and the vertical axis represents the positional deviation of the driven object 44 relative to the target position.

[0079] As shown in Figure 4, in this specification, the tolerance range refers to the range in which the positional deviation from the target position is within the required accuracy.

[0080] Furthermore, as shown in Figure 4, in this specification, the time at which the object to be driven 44 reaches an acceptable position that can be evaluated as having reached the target position (hereinafter also referred to as the "settlement time") refers to the time at which the object to be driven 44 last reached the acceptable range and then stopped deviating from the acceptable range again.

[0081] Furthermore, as shown in Figure 4, in this specification, the settling time refers to the time from when the driven object 44 starts to stop based on a command to move the driven object 44 to the target position until the driven object 44 reaches an acceptable position where it can be evaluated that it has reached the target position, that is, the time from the start of stopping to the settling time. Alternatively, the settling time refers to the time from when the driven object 44 starts to move based on a command to move the driven object 44 to the target position until the driven object 44 reaches an acceptable position where it can be evaluated that it has reached the target position, that is, the time from the start of movement to the settling time.

[0082] Figure 5 is a simplified diagram showing an example of measurement data 33 output by sensor 3.

[0083] As shown in Figure 5, the measurement data 33 is data that provides a one-to-one correspondence between the elapsed time [ms] after the reference time and the deviation amount [mm] from the target position. Here, the reference time is the start time when the driven object 44 stops based on the command to move the driven object 44 to the target position, or the start time when the driven object 44 starts moving based on the command to move the driven object 44 to the target position.

[0084] Referring to Figure 1, the estimation model 34 is a machine learning-trained model for optimizing the control parameters 31. The estimation model 34 may include a machine learning program. Alternatively, the control parameters 31 may be optimized using a machine learning program instead of the estimation model 34. The update unit 24 uses the estimation model 34 to perform an optimization that shortens the longest settling time among the settling times corresponding to each operation included in the representative operation. This updates the control parameters 31. Note that the target of optimization is not limited to the longest settling time, but may also be the average value of multiple settling times, or a predetermined number of settling times in descending order of length, or their average value.

[0085] For optimization, known algorithms such as Bayesian optimization algorithms, evolutionary strategy algorithms (CMA-ES), genetic algorithms (GA), or deep reinforcement learning can be used.

[0086] The information processing unit 11 and / or storage unit 12 may be implemented in an external terminal or server device capable of communicating with the control parameter generation device 1. External terminals include personal computers, smartphones, or tablet devices. Server devices include edge servers or cloud servers.

[0087] The input unit 13 is configured using any input device such as a mouse, keyboard, or touch panel.

[0088] The display unit 14 is configured using any display device such as a liquid crystal display or an organic EL display.

[0089] The communication unit 15 is configured using a communication module that supports any communication method such as Bluetooth (registered trademark) or Wi-Fi.

[0090] The communication unit 15 transmits the control parameters 31 stored in the memory unit 12 to the production device 2. When the production device 2 receives the control parameters 31 from the control parameter generation device 1, the memory unit 41 overwrites the stored control parameters 31 with the newly received control parameters 31. In other words, it updates the control parameters 31.

[0091] Furthermore, the communication unit 15 transmits a control signal to the production device 2 to execute a representative operation or an evaluation operation. When the production device 2 receives the control signal from the control parameter generation device 1, the control unit 42 executes the representative operation or evaluation operation by controlling the drive unit 43 based on the control signal and the control parameters 31 read from the storage unit 41.

[0092] Figure 6 is a flowchart showing the processes executed by the information processing unit 11.

[0093] First, in step SP01, the update unit 24 sets the initial value of the control parameter 31. The initial value may be a predetermined value, a value specified by the user through an operation input using the input unit 13, or a value calculated by the update unit 24 using a calculation method specified by the user through an operation input using the input unit 13. The initial value of the control parameter 31 set by the update unit 24 is stored in the storage unit 12 and transmitted to the production device 2 by the communication unit 15. The production device 2 stores the received initial value of the control parameter 31 in the storage unit 41.

[0094] Next, in step SP02, the selection unit 21 sets an initial value for an integer variable that represents the number of operations X for the representative operation. By referring to the selection rule 32, the selection unit 21 sets the initial value of the integer variable to 1 as the number of operations X for the first stage. In this embodiment, an example is given where the initial value of the integer variable is 1, but the initial value can be any integer between 1 and N-1, and is not necessarily limited to 1. Furthermore, the initial value of the integer variable may be specified by the user through operation input using the input unit 13.

[0095] Next, in step SP03, the information processing unit 11 performs control parameter optimization processing.

[0096] Figure 7 is a flowchart showing the details of the control parameter optimization process.

[0097] First, in step SP031, the selection unit 21 selects X representative operations from all N operations by referring to the selection rule 32. Specifically, the selection unit 21 selects one operation 2 as the representative operation for the first stage. As mentioned above, the selection is not limited to using the selection rule 32; the next representative operation may also be selected based on the execution results of all the most recent operations executed as evaluation operations (step SP062). For example, multiple operations may be identified from all operations in order of worst evaluation value, and these multiple operations may be selected as the next representative operation. Alternatively, all operations executed as evaluation operations may be clustered into multiple clusters, and the operation with the worst evaluation value in each cluster, or an operation randomly selected from each cluster, may be selected as the next representative operation.

[0098] Next, in step SP032, the control unit 22 generates a control signal that causes the production device 2 to execute the representative operation selected by the selection unit 21. The control signal generated by the control unit 22 is transmitted to the production device 2 by the communication unit 15. When the production device 2 receives the control signal, the control unit 42 controls the drive unit 43 based on the control signal and the control parameters 31 read from the storage unit 41 to execute the representative operation which includes X operations. When the production device 2 has executed the X operations, the sensor 3 transmits X measurement data 33 corresponding to each of the X operations included in the representative operation to the control parameter generation device 1. The communication unit 15 receives the X measurement data 33 transmitted from the sensor 3, stores them in the storage unit 12, and inputs them to the information processing unit 11.

[0099] Next, in step SP033, the acquisition unit 23 acquires X measurement data 33 corresponding to each of the X operations included in the representative operation from the communication unit 15.

[0100] Next, in step SP034, the update unit 24 calculates an evaluation value for the evaluation index for each of the X measurement data 33 acquired by the acquisition unit 23. In this embodiment, the update unit 24 calculates the settling time for each of the X measurement data 33.

[0101] Next, in step SP035, the update unit 24 updates the control parameter 31 by performing optimization using the estimation model 34 to shorten the longest of the X settling times related to the X calculated measurement data 33. The updated control parameter 31 by the update unit 24 is stored in the storage unit 12 and transmitted to the production device 2 by the communication unit 15. The production device 2 stores the received updated control parameter 31 in the storage unit 41.

[0102] Next, in step SP036, the output unit 25 generates image data including evaluation results for the representative operation based on the X settling times related to the X measurement data 33 calculated in step SP034, and outputs the generated image data. For example, the output unit 25 adopts the longest settling time among the X settling times as the evaluation value for the representative operation, and generates image data including evaluation results showing that evaluation value. The image data output from the output unit 25 is input to the display unit 14, and the display unit 14 displays an image based on the input image data.

[0103] Note that while Figure 7 shows an example where the selection of a representative action (step SP031) is performed before the execution of the representative action (step SP032) each time, this is not the only example. The selection of a representative action may be performed every predetermined number of times the representative action is executed (for example, tens to hundreds of times), or at predetermined time intervals. This allows for faster operation compared to performing the selection of a representative action every time.

[0104] Referring to Figure 6, in step SP04, following step SP03, the control unit 22 determines whether a predetermined representative operation termination condition is met. The representative operation termination condition may include setting a target value for the evaluation value at each stage, setting an upper limit on the number of iterations of the optimization process at each stage, or setting an upper limit on the execution time of the optimization process at each stage. For example, if a target value for the evaluation value is set as the representative operation termination condition, the control unit 22 determines that the representative operation termination condition is not met if the evaluation value of the most recent representative operation (the longest settling time among X) exceeds the target value, and determines that the representative operation termination condition is met if the evaluation value of the most recent representative operation is less than or equal to the target value.

[0105] If the representative operation termination condition is not met (step SP04: NO), then in step SP05, the control unit 22 determines whether a predetermined evaluation execution condition is met. The evaluation execution condition includes the fact that a certain amount of time has elapsed from the reference time. The reference time includes the start time of the first representative operation in each stage and the start time of the previous evaluation operation. The control unit 22 has a timer and resets the timer value at the reference time. When the timer value becomes equal to or greater than a threshold, it determines that a certain amount of time has elapsed from the reference time. The evaluation execution condition also includes the fact that the number of representative operations in each stage has reached a certain number. The control unit 22 has a counter and resets the counter value before the start of the first representative operation in each stage. When the representative operation is executed, the control unit 22 determines that the number of representative operations in each stage has reached a certain number.

[0106] If the evaluation execution conditions are not met (Step SP05: NO), the processes from Step SP03 onwards will be executed.

[0107] If the evaluation execution conditions are met (Step SP05: YES), then in Step SP06, the information processing unit 11 executes the evaluation result output process. The process in Step SP06 corresponds to the evaluation result output process that is executed within the period during which the representative operation of each stage is performed.

[0108] Figure 8 is a flowchart showing the details of the evaluation result output process.

[0109] First, in step SP061, the control unit 22 sets the evaluation operation conditions for executing the evaluation operation.

[0110] The evaluation operation conditions include operation specification information that specifies the operation to be performed in the evaluation operation from among all N operations. The evaluation operation may be all operations. By having the production device 2 execute all operations as the evaluation operation, it becomes possible to perform an accurate overall evaluation. Alternatively, the evaluation operation may be the difference operation between all operations and the most recent representative operation of the evaluation operation. By having the production device 2 execute the difference operation between all operations and the most recent representative operation of the evaluation operation as the evaluation operation, it becomes possible to improve the efficiency of the evaluation operation while maintaining the accuracy of the overall evaluation. Alternatively, the evaluation operation may be a predetermined predetermined operation from among all operations. By having the production device 2 execute a predetermined predetermined operation from among all operations as the evaluation operation, it becomes possible to improve the efficiency of the evaluation operation.

[0111] Furthermore, the evaluation operation conditions include setting information for the values ​​of the control parameters 31 when executing the evaluation operation. The latest control parameters 31 currently stored in the memory unit 41 may be used as the control parameters 31 when executing the evaluation operation. Alternatively, the control parameters 31 for the next evaluation operation may be set based on multiple evaluation values ​​related to multiple representative operations executed between the time of the previous evaluation operation and the present. For example, the control unit 22 identifies the best evaluation value from among multiple evaluation values ​​related to multiple representative operations executed between the time of the previous evaluation operation and the present, and sets the control parameters 31 that were set when the representative operation corresponding to that best evaluation value was executed as the control parameters 31 for the next evaluation operation. This makes it possible to improve the evaluation accuracy of the overall evaluation by executing the evaluation operation.

[0112] Next, in step SP062, the control unit 22 generates a control signal that causes the production device 2 to execute the evaluation operation set in step SP061. The control signal generated by the control unit 22 is transmitted to the production device 2 by the communication unit 15. When the production device 2 receives the control signal, the control unit 42 executes the evaluation operation by controlling the drive unit 43 based on the control signal and the control parameters 31 read from the storage unit 41. When the production device 2 executes the evaluation operation, the sensor 3 transmits measurement data 33 corresponding to each operation included in the evaluation operation to the control parameter generation device 1. The communication unit 15 receives the measurement data 33 transmitted from the sensor 3, stores it in the storage unit 12, and inputs it to the information processing unit 11.

[0113] Next, in step SP063, the acquisition unit 23 acquires measurement data 33 corresponding to each operation included in the evaluation operation from the communication unit 15.

[0114] Next, in step SP064, the output unit 25 calculates an evaluation value for the evaluation index for each measurement data 33 acquired by the acquisition unit 23. In this embodiment, the output unit 25 calculates a settling time for each measurement data 33, and the longest settling time among the multiple settling times for the multiple measurement data 33 is used as the evaluation value for the current evaluation operation.

[0115] Next, in step SP065, the output unit 25 generates image data including the evaluation results related to the evaluation operation and outputs the generated image data. The image data output from the output unit 25 is input to the display unit 14, and the display unit 14 displays an image based on the input image data.

[0116] Referring to Figure 6, in step SP07, following step SP06, the control unit 22 determines whether a predetermined optimization termination condition is met. The optimization termination condition may be a target value for the evaluation value related to the evaluation operation, an upper limit on the total number of iterations of the optimization process for all stages up to the present, or an upper limit on the execution time of the optimization process for all stages up to the present. For example, if a target value for the evaluation value is set as the optimization termination condition, the control unit 22 determines that the optimization termination condition is not met if the evaluation value of the most recent evaluation operation (longest settling time) exceeds the target value, and determines that the optimization termination condition is met if the evaluation value of the most recent evaluation operation is less than or equal to the target value.

[0117] If the optimization termination conditions are not met (Step SP07: NO), the processes from Step SP03 onwards will be executed.

[0118] If the optimization termination condition is met (Step SP07: YES), the optimization process for control parameter 31 is terminated. If the evaluation result of the overall evaluation by executing the evaluation operation meets the optimization termination condition, the optimization process is terminated even before the representative operation reaches the final stage, thus shortening the time required for the optimization process.

[0119] If the representative operation termination condition is met in the determination in step SP04 (step SP04: YES), then in step SP08, the selection unit 21 determines whether the number of operations X included in the representative operation is equal to the total number of operations N.

[0120] If X is equal to N (Step SP08: YES), the representative operation has reached its final stage (the 8th stage in the example in Figure 3), and the optimization process for the control parameter 31 is terminated.

[0121] If X is less than N (step SP08: NO), the representative actions have not reached the final stage, so in step SP09, the selection unit 21 updates X by referring to the selection rule 32. In other words, the selection unit 21 moves the selection of X representative actions from all N actions from the current stage to the next stage.

[0122] Next, in step SP10, the control unit 22 determines whether or not predetermined evaluation execution conditions are met. The evaluation execution conditions include the elapsed time from a reference time. The reference time includes the start time of the previous evaluation operation. The control unit 22 has a timer, and resets the timer value at the reference time. When the timer value becomes equal to or greater than a threshold, it determines that a certain amount of time has elapsed from the reference time.

[0123] If the evaluation execution conditions are not met (Step SP10: NO), the processes from Step SP03 onwards will be executed.

[0124] If the evaluation execution conditions are met (Step SP10: YES), the information processing unit 11 then executes the evaluation result output process in Step SP11. The process in Step SP11 corresponds to the evaluation result output process executed within the transition period from one stage to the next. Details of the evaluation result output process in Step SP11 are shown in the flowchart in Figure 8. Alternatively, the determination process in Step SP10 may be omitted, and Step SP11 may always be executed when X is updated.

[0125] Next, in step SP12, the control unit 22 determines whether or not predetermined optimization termination conditions are met. The details of the optimization termination conditions in step SP12 are the same as those in step SP07.

[0126] If the optimization termination conditions are not met (step SP12: NO), the processes from step SP03 onwards will be executed.

[0127] If the optimization termination condition is met (Step SP12: YES), the optimization process for control parameter 31 is terminated. If the evaluation result of the overall evaluation by executing the evaluation operation meets the optimization termination condition, the optimization process is terminated even before the representative operation reaches the final stage, thus shortening the time required for the optimization process.

[0128] Figure 9 is a simplified example of an image containing evaluation results for representative and evaluation actions. The image includes time-series data of evaluation value Q for the representative action and time-series data of evaluation value P for the evaluation action. In the example shown in Figure 9, the evaluation value is settling time on the vertical axis and elapsed time on the horizontal axis. Characteristic K1 is a line graph connecting the best values ​​among multiple evaluation values ​​Q for multiple representative actions repeated in the first stage, characteristic K2 is a line graph connecting the best values ​​among multiple evaluation values ​​Q for multiple representative actions repeated in the second stage, and characteristic K3 is a line graph connecting the best values ​​among multiple evaluation values ​​Q for multiple representative actions repeated in the third stage.

[0129] Evaluation value P01 is the evaluation value for the evaluation operation performed at time T02, a certain period of time after the start time T01 of the first representative operation in the first stage. Evaluation value P02 is the evaluation value for the evaluation operation performed at time T03, within the transition period from the first stage to the second stage. Evaluation value P03 is the evaluation value for the evaluation operation performed at time T05, a certain period of time after the start time T04 of the first representative operation in the second stage. Evaluation values ​​P04 to P07 are the evaluation values ​​for the evaluation operations performed at times T06 to T09, a certain period of time after times T05 to T08. Evaluation value P08 is the evaluation value for the evaluation operation performed at time T10, within the transition period from the second stage to the third stage. Evaluation value P09 is the evaluation value for the evaluation operation performed at time T12, a certain period of time after the start time T11 of the first representative operation in the third stage. The evaluation value P10 is the evaluation value for the evaluation operation performed at time T13, a certain period of time after time T12.

[0130] The image also includes an icon 50 labeled "Execute Evaluation." When a user clicks the icon 50 using the input unit 13, an execution request for the evaluation operation is input to the information processing unit 11. Upon receiving the execution request, the information processing unit 11 performs the same evaluation result output processing as in steps SP06 and SP11.

[0131] Figure 10 is a simplified diagram showing a modified image containing evaluation results for representative and evaluation operations. Characteristic KA is a line graph connecting the best values ​​among multiple evaluation values ​​P for the evaluation operation. In the example in Figure 10, evaluation value P04 is worse than evaluation value P03, so evaluation value P04 is excluded from characteristic KA. Furthermore, if a representative operation corresponding to characteristic K1 is included in the evaluation operations performed after time T02, characteristic K1 may be extended and displayed for time T02 and beyond by extracting the evaluation value Q corresponding to characteristic K1 from the evaluation values ​​P after time T02. The same applies to other characteristics K. In addition, if a representative operation corresponding to characteristic K2 is included in the evaluation operations performed before time T04, characteristic K2 may be retrospectively displayed for time T04 and beyond by extracting the evaluation value Q corresponding to characteristic K2 from the evaluation values ​​P before time T04. The same applies to other characteristics K.

[0132] Figure 11 is a magnified view of a portion of the image shown in Figure 9. In addition to the line graph of characteristic K, plots of multiple evaluation values ​​Q for multiple representative actions repeated at each stage may also be shown. Alternatively, only the plots of multiple evaluation values ​​Q may be shown, and the line graph of characteristic K may be omitted.

[0133] The user can select an evaluation value from the time-series data of evaluation value Q related to a representative operation by inputting an operation using the input unit 13. For example, if the user clicks on the evaluation value Q100 on characteristic K2 (or the time T100 on the horizontal axis), the selection information for evaluation value Q100 is input to the information processing unit 11. Upon receiving this selection information, the information processing unit 11 reads the control parameters 31 from the storage unit 12 when the representative operation corresponding to evaluation value Q100 was executed, and sets the control parameters 31 for the next evaluation operation based on these control parameters 31. For example, the control parameters 31 for the next evaluation operation are set to be equal to the control parameters 31 when the representative operation corresponding to evaluation value Q100 was executed. Since the user can easily set the control parameters 31 for the next evaluation operation by inputting an operation while looking at the screen displayed on the display unit 14, user convenience can be improved.

[0134] Figure 12 is a magnified view of another example of an image containing evaluation results. In the example above, the evaluation operation was performed once at each execution timing, but the number of times the evaluation operation is performed is not limited to one; it may be multiple times. The control unit 22 calculates the variance of multiple evaluation values ​​Q (multiple evaluation values ​​Q included in the area indicated by the dashed line in Figure 11) for multiple representative operations performed between the execution time T05 of the previous evaluation operation and the current time T06. Based on the calculated variance, the control unit 22 sets the number of times to be performed for the next evaluation operation. For example, the control unit 22 sets more executions when the variance is large and fewer executions when the variance is small. In the example shown in Figure 11, three evaluation operations are performed at time T06, and the evaluation values ​​P04a, P04b, and P04c for each evaluation operation are shown. This allows for the appropriate setting of the number of times to be performed for the next evaluation operation, thereby improving the accuracy of the overall evaluation.

[0135] As described above, according to this embodiment, the control parameters 31 are updated by having the production device 2 execute a representative operation out of all N operations, and the optimization process is repeated by gradually increasing the number of operations included in the representative operation. This makes it possible to efficiently generate appropriate control parameters 31.

[0136] Furthermore, according to this embodiment, for example, a comprehensive evaluation is performed by having the production device 2 execute a predetermined evaluation operation during at least one of the following periods: the first period (time T01-T02) in which the first representative operation (first representative operation) is executed, the second period (time T04-T09) in which the second representative operation (second representative operation) is executed, and the third period (time T02-T04) between the first and second periods. The output unit 25 outputs result data showing the evaluation result, making it possible to present the user with the progress of the optimization of the control parameters 31 for the entire operation of the production device 2 at an intermediate stage of the optimization process. [Industrial applicability]

[0137] This disclosure is broadly applicable to systems that generate control parameters, etc.

Claims

1. An information processing method for optimizing control parameters in a device that performs multiple operations based on multiple control parameters, Information processing device, In the control parameter optimization process, at least one representative operation is selected from all operations that the device can perform, the selected representative operation is performed by the device, measurement data of a predetermined evaluation index measured during the execution of the representative operation is acquired, and the control parameters are updated based on the acquired measurement data. The aforementioned representative action includes a first representative action and a second representative action which is performed after the first representative action. An information processing method comprising: in the evaluation result output processing, causing the device to perform a predetermined evaluation operation for comprehensively evaluating the operation of the device during at least one of the following periods: a first period during which the first representative operation is performed, a second period during which the second representative operation is performed, and a third period between the first and second periods; acquiring measurement data of the evaluation index measured during the execution of the evaluation operation; performing the comprehensive evaluation based on the acquired measurement data; and outputting result data indicating the evaluation result of the comprehensive evaluation.

2. The information processing method according to claim 1, wherein the evaluation operation is the entire operation.

3. The information processing method according to claim 2, wherein in the control parameter optimization process, the next representative operation is selected based on the execution results of all operations performed as the evaluation operation.

4. The information processing method according to claim 3, wherein, in the control parameter optimization process, all operations performed as evaluation operations are clustered into multiple clusters, and the next representative operation is selected from each cluster.

5. The information processing method according to claim 1, wherein the evaluation operation is the difference operation between the total operation and the most recent representative operation of the evaluation operation.

6. The information processing method according to claim 1, wherein the evaluation operation is a predetermined operation selected from all operations.

7. The information processing method according to claim 1, wherein, in outputting the result data, an image showing the evaluation result is generated as the result data, and the generated image is displayed on the display unit.

8. moreover, Based on the measurement data obtained in conjunction with the execution of the representative action, the evaluation value of the evaluation index related to the representative action is calculated. Based on the measurement data obtained in connection with the execution of the evaluation operation, the evaluation value of the evaluation index related to the evaluation operation is calculated. The aforementioned image is, The time-series data of the evaluation value relating to the representative operation, The time-series data of the evaluation value relating to the evaluation operation, The information processing method according to claim 7, including the method described in claim 7.

9. Furthermore, the information processing method according to claim 8, which adds time-series data of the evaluation values ​​related to the representative action by extracting an evaluation value corresponding to the representative action from the evaluation values ​​of the evaluation index related to the evaluation action.

10. moreover, The system accepts an input operation from the user requesting the selection of one evaluation value from the time-series data of the evaluation values ​​relating to the representative operation. The information processing method according to claim 8, wherein the control parameters for the next time the evaluation operation is performed are set based on the control parameters when the representative operation corresponding to the first evaluation value is performed.

11. Furthermore, the information processing method according to claim 1, which determines whether the evaluation result of the overall evaluation satisfies predetermined termination conditions, and terminates the control parameter optimization process if the evaluation result satisfies the termination conditions.

12. Furthermore, the system accepts input operations from the user requesting the execution of the aforementioned evaluation operation. The information processing method according to claim 1, wherein the device is made to perform the evaluation operation based on the execution request.

13. moreover, Based on the measurement data obtained in conjunction with the execution of the representative action, the evaluation value of the evaluation index related to the representative action is calculated. The variance of the multiple evaluation values ​​for the multiple representative operations is calculated, The information processing method according to claim 1, wherein the number of times the evaluation operation to be executed next is set based on the distribution.

14. moreover, Based on the measurement data obtained in conjunction with the execution of the representative action, the evaluation value of the evaluation index related to the representative action is calculated. The information processing method according to claim 1, wherein the control parameters for the next execution of the evaluation operation are set based on a plurality of evaluation values ​​relating to a plurality of the representative operations.

15. The information processing method according to claim 14, wherein, in setting the control parameters, the control parameters used when executing the representative operation corresponding to the best evaluation value among a plurality of evaluation values ​​are set as the control parameters to be used when executing the evaluation operation next time.

16. An information processing method for optimizing control parameters in a device that performs multiple operations based on multiple control parameters, Information processing device, The device selects at least one representative operation from all operations it can perform, has the device execute the selected representative operation, acquires measurement data of a predetermined evaluation index measured during the execution of the representative operation, and updates the control parameters based on the acquired measurement data. During the period in which the representative operation described above is performed, the device is made to perform a predetermined evaluation operation for comprehensively evaluating the operation of the device, measurement data of the evaluation indicator measured during the execution of the evaluation operation is acquired, and the comprehensive evaluation is performed based on the acquired measurement data. An information processing method that selects the next representative operation based on the results of the aforementioned evaluation operation.

17. An information processing device for optimizing control parameters in a device that performs multiple operations based on multiple control parameters, It comprises a selection unit, a control unit, an acquisition unit, an update unit, and an output unit. In the control parameter optimization process, the selection unit selects at least one representative operation from all operations that the device can perform, the control unit causes the device to execute the representative operation selected by the selection unit, the acquisition unit acquires measurement data of a predetermined evaluation index measured during the execution of the representative operation, and the update unit updates the control parameters based on the measurement data acquired by the acquisition unit. The aforementioned representative action includes a first representative action and a second representative action which is performed after the first representative action. Information processing device, in the evaluation result output processing, the control unit causes the device to perform a predetermined evaluation operation for comprehensively evaluating the operation of the device during at least one of the following periods: a first period during which the first representative operation is performed, a second period during which the second representative operation is performed, and a third period between the first and second periods; the acquisition unit acquires measurement data of the evaluation index measured during the execution of the evaluation operation; and the output unit performs the comprehensive evaluation based on the measurement data acquired by the acquisition unit and outputs result data indicating the evaluation result of the comprehensive evaluation.

18. A program for causing an information processing device for optimizing control parameters in a device that performs multiple operations based on multiple control parameters to perform selection processing, control processing, acquisition processing, update processing, and output processing, In the control parameter optimization process, the selection process selects at least one representative operation from all operations that the device can perform, the control process causes the device to execute the representative operation selected by the selection process, the acquisition process acquires measurement data of a predetermined evaluation index measured during the execution of the representative operation, and the update process updates the control parameters based on the measurement data acquired by the acquisition process. The aforementioned representative action includes a first representative action and a second representative action which is performed after the first representative action. A program that, in the evaluation result output processing, causes the control processing to have the device perform a predetermined evaluation operation for comprehensively evaluating the operation of the device during at least one of the following periods: the first period during which the first representative operation is performed, the second period during which the second representative operation is performed, and the third period between the first and second periods; the acquisition processing acquires measurement data of the evaluation index measured during the execution of the evaluation operation; and the output processing performs the comprehensive evaluation based on the measurement data acquired by the acquisition processing and outputs result data indicating the evaluation result of the comprehensive evaluation.

Images