Information processing method, information processing device, and program

Abstract

Provided is an information processing method for optimizing a control parameter, the information processing method comprising: acquiring first measurement data at a first time (S340); acquiring second measurement data at a second time after the first time (S440); calculating, on the basis of the first measurement data and the second measurement data, an environmental change degree indicating the degree of possibility that an environment related to a device (20) has changed between the first time and the second time (S446); and determining, on the basis of the environmental change degree, whether to display a display image based on the first measurement data and the second measurement data on a display unit 17 (S447).

Description

[Technical Field]

[0001] The present disclosure relates to an information processing method for optimizing control parameters. [Background Art]

[0002] Conventionally, information processing methods for optimizing control parameters of an apparatus that operates based on control parameters have been proposed (see, for example, Patent Document 1 and Patent Document 2). [Prior Art Literature] [Patent Literature]

[0003] [Patent Document 1] International Publication No. 2024 / 005137 [Patent Document 2] International Publication No. 2024 / 005138 [Summary of the Invention] [Problem to be Solved by the Invention]

[0004] Conventionally, it has been desired to provide a user with information useful for determining whether or not an environment related to an apparatus targeted for optimization of control parameters (hereinafter also referred to as "target apparatus") has changed during the period in which control parameters are being optimized. [Means for Solving the Problem]

[0005] 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 an operation based on control parameters, wherein an information processing unit causes the device to perform a first operation at a first time and acquires first measurement data relating to the movement of the device; causes the device to perform the first operation at a second time later than the first time and acquires second measurement data relating to the movement of the device; calculates an environmental change degree indicating the degree to which the environment relating to the device has changed between the first time and the second time based on the first measurement data and the second measurement data; and determines whether or not to display a display image based on the first measurement data and the second measurement data on a display unit based on the environmental change degree.

[0006] An information processing device according to one aspect of the present disclosure is an information processing device for optimizing control parameters in a device that performs an operation based on control parameters, comprising: an acquisition unit that, at a first time, causes the device to perform a first operation and acquires first measurement data relating to the movement of the device, and at a second time later than the first time, causes the device to perform the first operation and acquires second measurement data relating to the movement of the device; and a control unit that, based on the first measurement data and the second measurement data, calculates an environmental change degree indicating the degree to which the environment relating to the device has changed between the first time and the second time, and determines whether or not to display a display image based on the first measurement data and the second measurement data on a display unit based on the environmental change degree.

[0007] A program according to one aspect of the present disclosure is a program that causes an information processing device for optimizing control parameters in a device that performs an operation based on control parameters to perform a process, the process comprising: causing the device to perform a first operation at a first time to acquire first measurement data relating to the movement of the device; causing the device to perform the first operation at a second time later than the first time to acquire second measurement data relating to the movement of the device; calculating an environmental change degree indicating the degree to which the environment relating to the device has changed between the first time and the second time based on the first measurement data and the second measurement data; and determining whether or not to display a display image based on the first measurement data and the second measurement data on a display unit based on the environmental change degree. [Effects of the Invention]

[0008] According to one aspect of the present disclosure, an information processing device can provide the user with useful information for determining whether or not the environment related to the target device has changed during the period in which control parameters are being optimized. [Brief explanation of the drawing]

[0009] [Figure 1] Figure 1 is a schematic diagram showing an overview of the control parameter optimization system according to Embodiment 1. [Figure 2] Figure 2 is a block diagram showing the configuration of the control parameter optimization system according to Embodiment 1. [Figure 3] Figure 3 is a schematic diagram showing an example of control parameters according to Embodiment 1. [Figure 4] Figure 4 is a schematic diagram showing an example of the change in the positional deviation of the driven object relative to the target position. [Figure 5] Figure 5 is a data configuration diagram showing an example of measurement data according to Embodiment 1. [Figure 6] Figure 6 is a schematic diagram showing how the machine learning model according to Embodiment 1 outputs control parameters based on the results of learning the relationship between evaluation index data and control parameters. [Figure 7] FIG. 7 is an example of a display image generated by the generation unit according to the first embodiment. [Figure 8] FIG. 8 is an example of a display image generated by the generation unit according to the first embodiment. [Figure 9] FIG. 9 is a sequence diagram of the first control parameter optimization process according to the first embodiment. [Figure 10] FIG. 10 is a flowchart of the first control parameter optimization process according to the first embodiment. [Figure 11] FIG. 11 is a schematic diagram showing an overview of a control parameter optimization system according to the second embodiment. [Figure 12] FIG. 12 is a block diagram showing the configuration of a control parameter optimization system according to the second embodiment. [Figure 13] FIG. 13 is a sequence diagram of the second control parameter optimization process according to the second embodiment. [Figure 14] FIG. 14 is a flowchart of the second control parameter optimization process according to the second embodiment. [Figure 15] FIG. 15 is a schematic diagram showing an overview of a control parameter optimization system according to the third embodiment. [Figure 16] FIG. 16 is a block diagram showing the configuration of a control parameter optimization system according to the third embodiment. [Figure 17] FIG. 17 is an example of a display image generated by the generation unit according to the third embodiment. [Figure 18] FIG. 18 is an example of a display image generated by the generation unit according to the third embodiment. [Figure 19] FIG. 19 is an example of a display image generated by the generation unit according to the third embodiment. [Figure 20] FIG. 20 is an example of a display image generated by the generation unit according to the third embodiment. [Figure 21] FIG. 21 is an example of a display image generated by the generation unit according to the third embodiment. [Figure 22]FIG. 22 is an example of a display image generated by the generation unit according to Embodiment 3. [Figure 23] FIG. 23 is an example of a display image generated by the generation unit according to Embodiment 3. [Figure 24] FIG. 24 is an example of a display image generated by the generation unit according to Embodiment 3. [Figure 25A] FIG. 25A is an example of a display image generated by the generation unit according to Embodiment 3. [Figure 25B] FIG. 25B is an example of a display image generated by the generation unit according to Embodiment 3. [Figure 25C] FIG. 25C is an example of a display image generated by the generation unit according to Embodiment 3. [Figure 26] FIG. 26 is an example of a display image generated by the generation unit according to Embodiment 3. [Figure 27] FIG. 27 is a flowchart of a third control parameter optimization process according to Embodiment 3. [Figure 28] FIG. 28 is a flowchart of a first restart process according to Embodiment 3. [Figure 29] FIG. 29 is a flowchart of a fourth control parameter optimization process according to Embodiment 3. [Figure 30] FIG. 30 is a flowchart of a second restart process according to Embodiment 3. [Figure 31] FIG. 31 is a flowchart of a fifth control parameter optimization process according to Embodiment 3. [Figure 32] FIG. 32 is a flowchart of a third restart process according to Embodiment 3. [Figure 33] FIG. 33 is a flowchart of a sixth control parameter optimization process according to Embodiment 3. [Figure 34] FIG. 34 is a flowchart of a fourth restart process according to Embodiment 3. [Figure 35] FIG. 35 is a flowchart of a seventh control parameter optimization process according to Embodiment 3. [Figure 36]Figure 36 is a flowchart of the fifth restart process according to Embodiment 3. [Figure 37] Figure 37 is a flowchart of the eighth control parameter optimization process according to Embodiment 3. [Figure 38] Figure 38 is a flowchart of the sixth restart process according to Embodiment 3. [Figure 39] Figure 39 is a flowchart of the ninth control parameter optimization process according to Embodiment 3. [Figure 40] Figure 40 is a flowchart of the seventh restart process according to Embodiment 3. [Modes for carrying out the invention]

[0010] (The circumstances that led to obtaining one aspect of this disclosure) In production equipment equipped with drive units such as servo motors that drive objects, methods have recently been proposed to optimize control parameters by searching for appropriate control parameters using machine learning models, etc., as a method for generating appropriate control parameters for the drive unit (see, for example, Patent Documents 1 and 2).

[0011] Generally, the control parameters for drive units used in production equipment can number 50 or more. Furthermore, the adjustment gradations can exceed 100.

[0012] 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 to the power of 50) × 80.

[0013] When optimizing control parameters for such a vast number of combinations, the process can sometimes take several days.

[0014] Thus, if the period for optimizing control parameters is long, the environment related to the target device may change during that period.

[0015] Examples of changes in the environment surrounding the target device include, for instance, when the screws fixing the sensors that sense physical quantities related to the target device become loose, when the position of the target device changes (for example, when it tilts), or when the temperature, humidity, etc., around the target device changes.

[0016] The inventors realized that if the environment surrounding the device changes, the physical quantities sensed by the sensor may change before and after the change.

[0017] The inventors then gained insight that in such cases, a phenomenon can occur where the control parameters are not properly optimized.

[0018] Therefore, the inventors diligently conducted experiments and studies on information processing methods that can provide users with useful information for determining whether or not there have been changes in the environment related to the target device during the period in which control parameters are being optimized.

[0019] As a result, the inventors came up with the information processing method, etc., described below in this disclosure.

[0020] 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 an operation based on control parameters, wherein an information processing unit causes the device to perform a first operation at a first time and acquires first measurement data relating to the movement of the device; causes the device to perform the first operation at a second time later than the first time and acquires second measurement data relating to the movement of the device; calculates an environmental change degree indicating the degree to which the environment relating to the device has changed between the first time and the second time based on the first measurement data and the second measurement data; and determines whether or not to display a display image based on the first measurement data and the second measurement data on a display unit based on the environmental change degree.

[0021] According to the above information processing method, the information processing unit determines whether or not to display the display image on the display unit based on the degree to which the environment related to the target device has changed between the first time and the second time during the period in which the control parameters are being optimized.

[0022] Therefore, users utilizing the above information processing method can obtain useful information for determining whether or not there have been environmental changes related to the target device between the first time and the second time by visually inspecting the display unit.

[0023] Thus, according to the above information processing method, useful information can be provided to the user in determining whether or not there have been any changes in the environment related to the target device during the period in which the control parameters are being optimized.

[0024] Furthermore, if the information processing unit determines that it should display the display image on the display unit, it may generate the display image including the image showing the degree of environmental change and display the display image on the display unit.

[0025] This allows us to provide the user with the above-mentioned useful information by displaying an image that includes an image showing the degree of environmental change in the display unit.

[0026] Alternatively, the information processing unit may obtain the first measurement data and the second measurement data by having the first operation be performed with similar control parameters.

[0027] This allows the above-mentioned useful information provided to users to be considered relatively reliable.

[0028] Furthermore, the information processing unit may generate a display image that includes at least one of the following images when the degree of environmental change is greater than a first threshold: an image relating to an inquiry about whether to review the installation status of the device, an image relating to an inquiry about whether to continue optimizing the control parameters, an image relating to an inquiry about whether to restart the optimization from the beginning, and an image relating to an inquiry about whether to change the algorithm used for the optimization.

[0029] This allows the system to ask the user whether to review the installation status of the target device, whether to continue optimizing the control parameters, whether to restart the optimization process from the beginning, and whether to change the algorithm used for optimization.

[0030] Furthermore, the information processing unit may also cause the device to perform the first operation at each of the one or more time points after the second time point to acquire one or more measurement data points related to the movement of the device, and generate the display image based on the one or more measurement data points.

[0031] This allows the above-mentioned useful information provided to users to be considered relatively reliable.

[0032] Furthermore, the information processing unit may also calculate the degree of environmental change based on the one or more measurement data mentioned above.

[0033] This allows us to obtain relatively accurate information on the degree of environmental change.

[0034] Furthermore, the information processing unit may acquire operation count information, which is input to the operation reception unit, indicating the number of times the device is instructed to perform the first operation after the second time, and at each of the one or more time intervals indicated by the operation count information, it may instruct the device to perform the first operation and acquire one or more measurement data relating to the operation of the device, corresponding to the one or more intervals indicated by the operation count information.

[0035] This allows the number of times the target device performs the first operation after the second time point to be set to a number specified by the user.

[0036] Furthermore, the information processing unit may generate the display image which includes a first measurement image relating to the first measurement data and a second measurement image relating to the second measurement data.

[0037] This allows the display unit to show a display image that includes the first measurement image and the second measurement image, thereby providing the user with the above-mentioned useful information.

[0038] Furthermore, the information processing unit may also calculate first evaluation index data based on evaluation indicators related to the operation of the device based on the first measurement data, calculate second evaluation index data based on the evaluation indicators based on the second measurement data, and generate a first measurement image showing the first evaluation index data and a second measurement image showing the second evaluation index data.

[0039] This allows the display unit to show a display image that includes a first measurement image showing the first evaluation index data and a second measurement image showing the second evaluation index data, thereby providing the user with the above-mentioned useful information.

[0040] Furthermore, the first measurement data and the second measurement data are time-series data, and the information processing unit may generate the display image which includes a first measurement image showing the time-series waveform of the first measurement data and a second measurement image showing the time-series waveform of the second measurement data.

[0041] This allows the display unit to show a display image that includes a first measurement image showing a time-series waveform and a second measurement image showing a time-series waveform, thereby providing the user with the above-mentioned useful information.

[0042] Furthermore, the information processing unit may generate the display image by superimposing the first measurement image and the second measurement image.

[0043] This allows the display unit to show a superimposed display image of a first measurement image showing a time-series waveform and a second measurement image showing a time-series waveform, thereby providing the user with the above-mentioned useful information.

[0044] Furthermore, the information processing unit may further calculate first evaluation index data based on an evaluation index relating to the operation of the device based on the first measurement data, calculate second evaluation index data based on the evaluation index based on the second measurement data, calculate one or more evaluation index data based on the evaluation index based on one or more measurement data, and if there is one or more difference evaluation index data among the second evaluation index data and the one or more evaluation index data that has a difference greater than the second threshold between the first evaluation index data and the second evaluation index data, it may generate the display image including an image relating to one or more difference measurement data corresponding to the one or more difference evaluation index data.

[0045] This allows the display unit to show an image that includes images related to one or more difference-showing evaluation data corresponding to one or more difference-showing evaluation data that have a difference greater than the second threshold between the first evaluation index data and the second threshold, thereby providing the user with the above-mentioned useful information.

[0046] Furthermore, the information processing unit may also acquire the second threshold value input to the operation reception unit.

[0047] This allows the second threshold to be set to a value specified by the user.

[0048] Furthermore, the information processing unit may acquire at least one of the first temperature, first humidity, and first operating status information relating to the operating status of an external device in the environment in which the device is installed at the first time, and acquire at least one of the second temperature, second humidity, and second operating status information relating to the operating status of the external device in the environment in which the device is installed at the second time, and generate the display image which includes an external device in the environment in which the device is installed at the first time, and first operating status information relating to the operating status of an external device.

[0049] This allows the user to be provided with the above-mentioned useful information by displaying an image on the display unit that includes an image showing at least one of the following at a first time: a first temperature, a first humidity, and the operating status of an external device, and an image showing at least one of the following at a second time: a second temperature, a second humidity, and the operating status of an external device.

[0050] Furthermore, the information processing unit may generate the display image including an image showing the time difference between the third time and the fourth time if the process for optimizing the control parameters is interrupted at a third time, which is after the first time and before the second time, and the interrupted process is resumed at a fourth time, which is after the third time and before the second time.

[0051] This allows the user to be notified of the length of time during which the process of optimizing the parameters was interrupted.

[0052] Furthermore, the information processing unit may, at a fifth time after the first time but before the second time, cause the device to perform the first operation or an additional operation which is a third operation different from the first operation, in order to acquire third measurement data relating to the movement of the device, and at a sixth time after the second time, cause the device to perform the additional operation, in order to acquire fourth measurement data relating to the movement of the device, and generate the display image based on the third measurement data and the fourth measurement data.

[0053] This allows the above-mentioned useful information provided to users to be considered relatively reliable.

[0054] Furthermore, the information processing unit may also calculate the degree of environmental change, which indicates the degree to which the environment related to the device has changed between the fifth time and the second time, based on the third measurement data and the fourth measurement data.

[0055] This allows us to obtain relatively accurate information on the degree of environmental change.

[0056] Furthermore, the information processing unit may also identify a recommended optimization algorithm suitable for the optimization algorithm based on the progress of the optimization of the control parameters, and generate the display image including an image showing the recommended optimization algorithm.

[0057] This allows the user to be notified of recommended optimization algorithms based on the progress of the control parameter optimization.

[0058] An information processing device according to one aspect of the present disclosure is an information processing device for optimizing control parameters in a device that performs an operation based on control parameters, comprising: an acquisition unit that, at a first time, causes the device to perform a first operation and acquires first measurement data relating to the movement of the device, and at a second time later than the first time, causes the device to perform the first operation and acquires second measurement data relating to the movement of the device; and a control unit that, based on the first measurement data and the second measurement data, calculates an environmental change degree indicating the degree to which the environment relating to the device has changed between the first time and the second time, and determines whether or not to display a display image based on the first measurement data and the second measurement data on a display unit based on the environmental change degree.

[0059] According to the above-described information processing device, the device determines whether or not to display an image on the display unit based on the degree of possibility that the environment related to the target device has changed between a first time and a second time during the period in which the control parameters are being optimized. Therefore, a user of the above-described information processing device can obtain useful information for determining whether or not there has been an environmental change related to the target device between the first time and the second time by visually inspecting the display unit.

[0060] Thus, the above-described information processing device can provide the user with useful information for determining whether or not there have been any changes in the environment related to the target device during the period in which the control parameters are being optimized.

[0061] A program according to one aspect of the present disclosure is a program that causes an information processing device for optimizing control parameters in a device that performs an operation based on control parameters to perform a process, the process comprising: causing the device to perform a first operation at a first time to acquire first measurement data relating to the movement of the device; causing the device to perform the first operation at a second time later than the first time to acquire second measurement data relating to the movement of the device; calculating an environmental change degree indicating the degree to which the environment relating to the device has changed between the first time and the second time based on the first measurement data and the second measurement data; and determining whether or not to display a display image based on the first measurement data and the second measurement data on a display unit based on the environmental change degree.

[0062] According to the above program, the information processing device executing the above program determines whether or not to display the display image on the display unit based on the degree to which the environment related to the target device has changed between a first time and a second time during the period in which the control parameters are being optimized.

[0063] Therefore, a user of the information processing device that executes the above program can obtain useful information for determining whether or not there has been an environmental change related to the target device between the first time and the second time by visually inspecting the display unit.

[0064] Thus, according to the above program, useful information can be provided to the user in determining whether or not there have been any changes in the environment related to the target device during the period in which the control parameters are being optimized.

[0065] The following describes a specific example of an information processing device according to one aspect of this disclosure, with reference to the drawings. The embodiments shown here are all examples of this disclosure. Therefore, the numerical values, shapes, components, arrangement and connection configurations of components, as well as the steps (processes) and the order of steps shown in the following embodiments are examples and are not intended to limit this disclosure. In addition, each figure is a schematic diagram and is not necessarily a strict illustration. In each figure, substantially identical components are denoted by the same reference numerals, and redundant explanations are omitted or simplified.

[0066] (Embodiment 1) The control parameter optimization system according to Embodiment 1 will be described below. This control parameter optimization system is a system for optimizing control parameters used in production equipment equipped with a drive unit that drives an object to be driven.

[0067] <Structure> Figure 1 is a schematic diagram showing an overview of the control parameter optimization system 1 according to Embodiment 1.

[0068] Figure 2 is a block diagram showing the configuration of the control parameter optimization system 1.

[0069] As shown in Figure 1, the control parameter optimization system 1 comprises an information processing device 10, a device 20, and a sensor 30.

[0070] Device 20 is a device that operates based on control parameters. Here, device 20 is described as a production device used to manufacture equipment, and is used for processing, mounting, transporting, etc., of equipment. Production devices are installed, for example, on a factory production line. Specifically, production devices include, for example, LED bonders, mounting machines, processing machines, and picking robots.

[0071] In this explanation, we assume that device 20 is a production device, but device 20 is not necessarily limited to a production device; it may be any device that performs operations based on control parameters.

[0072] As shown in Figure 2, the device 20 comprises a storage unit 21, a control unit 22, a drive unit 23, and a drive target object 24.

[0073] The drive unit 23 is controlled by the control unit 22 to drive the object to be driven 24. The drive unit 23 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.

[0074] The object to be driven 24 is an object driven by the drive unit 23. When the drive unit 23 is a servo motor, the object to be driven 24 is, for example, a head for transporting a workpiece, or a nozzle attached to the head for picking up the workpiece. When the drive unit 23 is a directional flow control valve, the object to be driven 24 is a pneumatic artificial muscle arm or a hydraulic arm.

[0075] The control unit 22 controls the drive unit 23 by outputting a command to the drive unit 23 to move the drive target object 24 to a predetermined target position. The command output by the control unit 22 to the drive unit 23 may be, for example, a position command that commands the position of the drive unit 23 or the drive target object 24, or it may be, for example, a torque command that commands the torque of the drive unit 23.

[0076] The control unit 22 controls the drive unit 23 based on the control parameters stored in the memory unit 21. In other words, the control unit 22 uses the control parameters stored in the memory unit 21 when controlling the drive unit 23.

[0077] The memory unit 21 stores the control parameters used by the control unit 22 when controlling the drive unit 23. The control parameters stored in the memory unit 21 are the control parameters output from the information processing device 10.

[0078] Figure 3 is a schematic diagram showing an example of control parameters stored in the memory unit 21.

[0079] As shown in Figure 3, the control parameters stored in the memory unit 21 include, for example, parameters a1 and a2 for adjusting the vibration frequency of the driven object 24, parameters b1 and b2 for adjusting the speed of the driven object 24, parameters c1 and c2 for adjusting the depth of singularities in the vibration characteristics of the driven object 24, and parameters d1 and d2 for adjusting the vibration amplitude of the driven object 24.

[0080] Generally, control parameters include parameters that have trade-off relationships with each other, such as parameters b1 and b2 that adjust the speed, parameters c1 and c2 that adjust the depth of singularities in the vibration characteristics, and parameters d1 and d2 that adjust the vibration amplitude.

[0081] Returning to Figures 1 and 2, we will continue our explanation of the control parameter optimization system 1.

[0082] The sensor 30 measures physical quantities related to the movement of the driven object 24. The sensor 30 then outputs the measurement data related to the movement of the driven object 24 to the information processing device 10.

[0083] In this explanation, the sensor 30 measures the position of the object to be driven 24 over time and outputs the measurement data representing the position of the object to be driven 24 to the information processing device 10.

[0084] Figure 4 is a schematic diagram showing an example of the change in the positional deviation of the object 24 relative to the target position when the device 20 drives the object 24 to the target position.

[0085] In Figure 4, the horizontal axis represents time, and the vertical axis represents the positional deviation of the driven object 24 relative to the target position.

[0086] As shown in Figure 4, in this specification, the allowable position is a position in which the positional deviation from the target position is within the required accuracy. Also, as shown in Figure 4, in this specification, the time at which the allowable position, which can be evaluated as having reached the target position, is reached (hereinafter also referred to as the "sett time") is the time (time sett_t in Figure 4) at which the driven object 24 last reached the allowable position after reaching the allowable position and no longer deviates from the allowable position.

[0087] Figure 5 is a data configuration diagram showing an example of measurement data output by sensor 30.

[0088] As shown in Figure 5, the measurement data, as an example, is data that provides a one-to-one correspondence between the elapsed time [ms] after reaching the acceptable position and the deviation amount [mm] from the target position.

[0089] Returning to Figures 1 and 2, we will continue our explanation of the control parameter optimization system 1.

[0090] The information processing device 10 generates control parameters (hereinafter also referred to as "update control parameters") for updating the control parameters stored in the memory unit 21 (hereinafter also referred to as "stored control parameters"). More specifically, the information processing device 10 sequentially acquires measurement data output from the sensor 30 as a result of the device 20 driving the object to be driven 24 to the target position using the stored control parameters, sequentially generates update control parameters based on the acquired measurement data, and sequentially outputs the generated update control parameters to the device 20.

[0091] In the control parameter optimization system 1, the information processing device 10 functions as a device that optimizes the control parameters in the device 20.

[0092] As shown in Figure 2, the information processing device 10 comprises an information processing unit 18, an operation reception unit 15, a display unit 17, and a machine learning model 14. The information processing unit 18 also comprises an acquisition unit 19, a generation unit 16, and an output unit 12. The acquisition unit 19 also comprises an input unit 11 and a control unit 13.

[0093] The information processing device 10 is implemented, for example, in a computer device that includes a processor, memory, and an input / output interface, by the processor executing a program stored in memory. Such a computer device is, for example, a personal computer (PC).

[0094] In other words, the information processing device 10 includes an input unit 11, an output unit 12, a control unit 13, a machine learning model 14, an operation reception unit 15, a generation unit 16, and a display unit 17, as functions realized by a processor executing a program read from a computer-readable non-volatile recording medium such as ROM. In other words, the above program is a program that causes the information processing device 10 to function as an input unit 11, an output unit 12, a control unit 13, a machine learning model 14, an operation reception unit 15, a generation unit 16, and a display unit 17.

[0095] In this explanation, the display unit 17 is assumed to be included in the information processing device 10, but the display unit 17 does not necessarily have to be included in the information processing device 10. For example, the display unit 17 may be included in an external device capable of communicating with the information processing device 10.

[0096] The input unit 11 acquires the measurement data output from the sensor 30.

[0097] The control unit 13 generates evaluation index data based on evaluation indices related to the operation of the device 20, based on the measurement data acquired by the input unit 11, and updates the control parameters using a machine learning model 14 that learns the relationship between the evaluation index data and the control parameters, based on the generated evaluation index data.

[0098] Here, the control unit 13 is described as generating evaluation index data indicating the vibration of the driven object 24 after a settling time, based on the measurement data acquired by the input unit 11.

[0099] The evaluation index data generated by the control unit 13 is one of the following: (1) the sum of the areas enclosed by the deviation waveform showing the vibration of the driven object 24 after the settling time and the reference axis (hereinafter also referred to as "summary area evaluation index data" or simply "summary area"), (2) the degree of variation of the deviation waveform showing the vibration of the driven object 24 after the settling time (hereinafter also referred to as "degree of variation evaluation index data" or simply "degree of variation"), and (3) the effective value of the deviation waveform showing the vibration of the driven object 24 after the settling time (hereinafter also referred to as "effective value evaluation index data" or simply "effective value"), or / or (4) the time from the time when the driven object 24 started to be driven to the settling time (hereinafter also referred to as "settling time evaluation index data" or simply "settling time").

[0100] The evaluation index data generated by the control unit 13 is specified by the user utilizing the control parameter optimization system 1.

[0101] The total area evaluation index data, variability evaluation index data, and effective value evaluation index data generated by the control unit 13 will be explained in more detail below with reference to Figure 4.

[0102] As shown in Figure 4, the total area evaluation index data generated by the control unit 13 is calculated more specifically by the formulas shown in (Equation 1), (Equation 2), or (Equation 3), where the position deviation f of the driven object relative to the target position is expressed as f = E(t), with time t as the variable.

[0103]

number

[0104]

number

[0105]

number

[0106] Here, the starting point of the integration interval, sett_t, is the settling time, and the ending point of the integration interval, cal_e, is a time set by the user. Note that, although we assume here that the starting point of the integration interval, sett_t, is the settling time, it may be either the settling time or any time after the settling time.

[0107] cal_e may be set to, for example, the time when the position deviation of the driven object 24 relative to the target position last reached within 1 / 10 of the required accuracy after the position deviation had reached within 1 / 10 of the required accuracy and no longer deviated from within 1 / 10 of the required accuracy; or it may be set to, for example, the time when the number of data points included in the measurement data acquired by the input unit 11 reaches a predetermined number; or it may be set to a time specified to have elapsed from the settling time.

[0108] The variation degree evaluation index data generated by the control unit 13 is calculated more specifically by the formula shown in (Equation 4) when def = cal_e - sett_t.

[0109]

number

[0110] The effective value evaluation index data generated by the control unit 13 is calculated more specifically by the formula shown in (Equation 5).

[0111]

number

[0112] Returning to Figures 1 and 2, we will continue our explanation of the control parameter optimization system 1.

[0113] The machine learning model 14 is a machine learning model that learns the relationship between evaluation metric data and control parameters. Each time evaluation metric data is input sequentially from the control unit 13, it learns the relationship between the evaluation metric data and control parameters and outputs the control parameters sequentially to the control unit 13 based on the learning results.

[0114] More specifically, the machine learning model 14 uses a Bayesian optimization algorithm to learn the relationship between evaluation metric data and the corresponding control parameters (hereinafter also referred to as "corresponding control parameters") each time evaluation metric data is sequentially input from the control unit 13. Based on the learning results, it outputs to the control unit 13 the control parameters that are predicted to result in the smallest evaluation metric data.

[0115] Figure 6 is a schematic diagram showing how the machine learning model 14 learns the relationship between evaluation metric data and corresponding control parameters, and based on the learned results, outputs the control parameters that are predicted to result in the smallest evaluation metric data.

[0116] In Figure 6, the horizontal axis represents the control parameter values, and the vertical axis represents the evaluation metric data values. Furthermore, the points plotted as circles in Figure 6 indicate the corresponding control parameter values ​​for each evaluation metric data value previously input into the machine learning model 14.

[0117] As shown in Figure 6, the machine learning model 14 uses a Bayesian optimization algorithm to predict the relationship between evaluation metric data and corresponding control parameters within a certain range, and uses the predicted relationship to output the control parameter that is predicted to result in the smallest evaluation metric data.

[0118] Here, we will assume that the algorithm used by machine learning model 14 during training is a Bayesian optimization algorithm. However, the algorithm used by machine learning model 14 during training is not necessarily limited to a Bayesian optimization algorithm. Examples of other algorithms include evolutionary strategy algorithms (CMA-ES) and genetic algorithms (GA).

[0119] Returning to Figures 1 and 2, we will continue our explanation of the control parameter optimization system 1.

[0120] The output unit 12 outputs the control parameters updated by the control unit 13 to the device 20 in order to store them in the storage unit 21.

[0121] As described above, the acquisition unit 19 comprises an input unit 11 and a control unit 13. The acquisition unit 19 works by having the control unit 13 control the input unit 11 and the output unit 12, causing the device 20 to perform an operation using the control parameters updated by the control unit 13, and acquiring measurement data related to the movement of the device 20 (in this case, measurement data indicating the position of the driven object, measured by the sensor 30 in a time series).

[0122] The operation reception unit 15 receives input operations to the information processing device 10 from a user utilizing the control parameter optimization system 1.

[0123] The display unit 17 displays an image to be provided to the user using the control parameter optimization system 1.

[0124] The generation unit 16 generates a display image to be displayed by the display unit 17, and displays the generated display image on the display unit 17.

[0125] Figure 7 is an example of a display image generated by the generation unit 16. Figure 7 is an example of an image (hereinafter also referred to as the "evaluation index data specification image") that prompts the user of the control parameter optimization system 1 to specify which evaluation index data the control unit 13 should generate when the control parameter optimization system 1 starts the first control parameter optimization process described later.

[0126] As shown in Figure 7, the information processing device 10 prompts the user to specify one of the following evaluation index data to be generated by the control unit 13: settling time evaluation index data, / and / total area evaluation index data, variation degree evaluation index data, and effective value evaluation index data (hereinafter, these three evaluation index data are also referred to as "vibration evaluation index data").

[0127] For example, a user can specify the settling time evaluation index data as evaluation index data by checking the box next to "Settling Time" for an image that specifies evaluation index data. For example, a user can specify the total area evaluation index data as evaluation index data by checking the box next to "Vibration" and placing a circle next to "Area" for an image that specifies evaluation index data. For example, a user can specify the degree of variation evaluation index data as evaluation index data by checking the box next to "Vibration" and placing a circle next to "Variance" for an image that specifies evaluation index data. For example, a user can specify the RMS (effective value) evaluation index data as evaluation index data by checking the box next to "Vibration" and placing a circle next to "RMS (effective value)" for an image that specifies evaluation index data.

[0128] Furthermore, the user can specify settling time evaluation index data and vibration evaluation index data as evaluation index data by, for example, checking both the box next to "settling time" and the box next to "vibration" for the image used to specify evaluation index data. In this case, the control unit 13 may use evaluation index data where the value of the settling time evaluation index data is the sum of the value of the vibration evaluation index data, or it may use evaluation index data where the value of the evaluation index data is the sum of the values ​​obtained by multiplying the value of the settling time evaluation index data and the value of the vibration evaluation index data by a predetermined weighting coefficient.

[0129] Figure 8 is an example of a display image generated by the generation unit 16. Figure 8 is an example of an image (hereinafter also referred to as the "status display image") that the control parameter optimization system 1 displays to the user using the control parameter optimization system 1 while the system 1 is executing the first control parameter optimization process described later, showing the status of the evaluation index data values ​​in the first control parameter optimization process.

[0130] In the graph in Figure 8, the horizontal axis represents the number of times the information processing device 10 sequentially outputs a control parameter, and the vertical axis represents the value of the evaluation index data corresponding to each of the control parameters sequentially output by the information processing device 10. In addition, the solid line in the graph in Figure 8 shows the trend of the minimum value of the evaluation index data corresponding to the control parameter output by the information processing device 10.

[0131] As shown in Figure 8, an icon labeled "Pause" (hereinafter also referred to as the "Pause icon") and an icon labeled "Resume" (hereinafter also referred to as the "Resume icon") are placed in the upper right corner of the status display image.

[0132] The interruption icon allows the user to interrupt the first control parameter optimization process by clicking it, for example, when the user determines that, as a result of viewing the situation display image, the value of the evaluation index data corresponding to the control parameter output by the information processing device 10 has become sufficiently small and therefore it is no longer necessary to continue the first control parameter optimization process, or when, for example, it is the end of the workday at the factory where the device 20 is installed.

[0133] The resume icon is an icon that allows the user to continue the first control parameter optimization process by clicking it, for example, when the user determines, after viewing the status display image, that the value of the evaluation index data corresponding to the control parameter output by the information processing device 10 has not become sufficiently small, and therefore the first control parameter optimization process needs to be continued, or when, for example, the factory where the device 20 is installed starts its business hours.

[0134] <Operation> The following describes the operation performed by the control parameter optimization system 1 with the above configuration.

[0135] The control parameter optimization system 1 performs a first control parameter optimization process to adjust the control parameters stored in the memory unit 21 to appropriate values. The first control parameter optimization process is started, for example, when a user of the control parameter optimization system 1 performs an operation on the information processing device 10 to start the first control parameter optimization process.

[0136] Figure 9 is a sequence diagram of the first control parameter optimization process, and Figure 10 is a flowchart of the first control parameter optimization process.

[0137] As shown in Figures 9 and 10, when the first control parameter optimization process is started, the information processing device 10 starts a predetermined program for executing the first control parameter optimization process (step S10).

[0138] When a predetermined program is started, the output unit 12 outputs the initial values ​​of the control parameters to the storage unit 21 (step S15). At this time, the output unit 12 may output, for example, initial values ​​of the control parameters consisting of predetermined values, for example, initial values ​​of the control parameters consisting of values ​​specified by the user, or for example, initial values ​​of the control parameters consisting of values ​​calculated by a calculation method specified by the user.

[0139] When control parameters are output from the output unit 12, the storage unit 21 stores the control parameters output from the output unit 12 (step S20). Then, the control unit 22 generates a command to move the position of the object to be driven 24 to a predetermined target position based on the control parameters stored in the storage unit 21 and outputs it to the drive unit 23. As a result, the control unit 22 controls the drive unit 23 (step S25). Then, the drive unit 23 drives the object to be driven 24 based on the command output from the control unit 22 (step S30).

[0140] When the object to be driven 24 is driven by the drive unit 23, the sensor 30 measures the position of the object to be driven 24 in a time series (step S35) and outputs measurement data representing the position of the object to be driven 24 to the input unit 11. The input unit 11 then acquires the time series measurement data output from the sensor 30 (step S40).

[0141] When the input unit 11 acquires measurement data, the control unit 13 generates evaluation index data indicating the vibration of the driven object 24 after the settling time based on the measurement data (step S45). The control unit 13 then checks whether the generation of the evaluation index data satisfies predetermined conditions (step S50). Here, predetermined conditions include, for example, the condition that the number of times the evaluation index data has been updated (i.e., the number of times it has been generated) has reached a predetermined number, or the condition that a predetermined time has elapsed since the start of adjustment of the control parameters. Here, the predetermined number and predetermined time may be predetermined, or they may be specified by the user using the control parameter optimization system 1.

[0142] In the process of step S50, if the generation of evaluation index data does not meet the predetermined conditions (step S50: No), the control unit 13 outputs the generated evaluation index data to the machine learning model 14. The machine learning model 14 then learns the relationship between the evaluation index data and the corresponding control parameters (step S55) and outputs the control parameter that is predicted to produce the smallest value of the evaluation index data. The control unit 13 then updates the control parameter previously output by the output unit 12 with the control parameter newly output from the machine learning model 14 (step S60). The output unit 12 then transmits the control parameter newly updated by the control unit 13 to the storage unit 21 (step S65).

[0143] Once the processing in step S65 is completed, the control parameter optimization system 1 proceeds to the processing in step S20 and repeats the processing from step S20 onward.

[0144] In the process of step S50, if the generated evaluation index data satisfies predetermined conditions (step S50: Yes), the control parameter optimization system 1 terminates its first control parameter optimization process.

[0145] <Consideration> As described above, the control parameter optimization system 1 with the above configuration optimizes the control parameters by repeatedly generating control parameters until the generation of evaluation index data satisfies predetermined conditions, by executing the first control parameter optimization process.

[0146] Therefore, the control parameter optimization system 1 allows for the optimization of control parameters without the need for skilled technicians and in a relatively short amount of time.

[0147] (Embodiment 2) The following describes a control parameter optimization system according to Embodiment 2, which is configured with some changes from the control parameter optimization system 1 according to Embodiment 1.

[0148] The control parameter optimization system 1 was an example of a system in which a sensor 30 measures the position of the object to be driven 24 over time and outputs measurement data, and an information processing device 10 acquires the measurement data output from the sensor 30.

[0149] In contrast, the control parameter optimization system according to Embodiment 2 is an example of a system in which a sensor with a processing device according to Embodiment 2 measures the position of the object to be driven 24 and outputs evaluation index data, and an information processing device according to Embodiment 2 acquires the evaluation index data output from the sensor with a processing device according to Embodiment 2.

[0150] Here, regarding the control parameter optimization system according to Embodiment 2, components similar to those in Control Parameter Optimization System 1 have already been described, so the same reference numerals are used and their detailed explanations are omitted. The explanation will focus on the differences from Control Parameter Optimization System 1.

[0151] Figure 11 is a schematic diagram showing an overview of the control parameter optimization system 1A according to Embodiment 2.

[0152] Figure 12 is a block diagram showing the configuration of the control parameter optimization system 1A.

[0153] As shown in Figure 11, the control parameter optimization system 1A is configured in a way that the information processing device 10 is changed to an information processing device 10A and the sensor 30 is changed to a sensor with a processing device 30A, compared to the control parameter optimization system 1 according to Embodiment 1. Furthermore, as shown in Figure 12, the information processing device 10A is configured in a way that the input unit 11 is changed to an input unit 11A and the control unit 13 is changed to a control unit 13A compared to the information processing device 10. In addition, the acquisition unit 19 is changed to an acquisition unit 19A and the information processing unit 18 is changed to an information processing unit 18A.

[0154] The sensor with processing unit 30A measures the position of the driven object 24 in a time series. The sensor with processing unit 30A then generates measurement data representing the position of the driven object 24. Furthermore, based on the generated measurement data, the sensor with processing unit 30A generates evaluation index data indicating the vibration of the driven object 24 after a settling time, and outputs the generated evaluation index data to the information processing unit 10A.

[0155] The sensor with processing unit 30A is realized, for example, in a computer device that includes a sensing device for measuring the position of the object to be driven 24, a processor, memory, and an input / output interface, by the processor executing a program stored in memory. Such a computer device is, for example, a personal computer (PC).

[0156] Alternatively, the sensor with processing device 30A may include, for example, an image processing device. In this case, the sensor with processing device 30A may measure the position of the object to be driven 24 by performing image processing on an image of the object to be driven 24 using the image processing device.

[0157] The input unit 11A acquires evaluation index data output from the sensor 30A with a processing unit.

[0158] The control unit 13A updates the control parameters based on the evaluation index data acquired by the input unit 11A, using a machine learning model 14 that learns the relationship between the evaluation index data and the control parameters.

[0159] <Operation> The following describes the operation performed by the control parameter optimization system 1A with the above configuration.

[0160] The control parameter optimization system 1A performs a second control parameter optimization process, which is a modified version of the first control parameter optimization process, instead of the first control parameter optimization process according to Embodiment 1.

[0161] Figure 13 is a sequence diagram of the second control parameter optimization process, and Figure 14 is a flowchart of the second control parameter optimization process.

[0162] As shown in Figures 13 and 14, the second control parameter optimization process includes the processes from step S110 to step S165.

[0163] Of these processes, the processes from step S110 to step S130, and the processes from step S150 to step S165 are the same as the processes from step S10 to step S30 and the processes from step S50 to step S65 in the first control parameter optimization process, respectively.

[0164] Therefore, this explanation will focus on the processes from step S135 to step S145.

[0165] When the processing in step S130 is completed, the sensor with processing unit 30A measures the position of the object to be driven 24 (step S135) and generates measurement data representing the position of the object to be driven 24 after the time at which it reaches an acceptable position where it can be evaluated that the object to be driven 24 has reached a predetermined target position. Then, based on the generated measurement data, the sensor with processing unit 30A generates evaluation index data indicating the vibration of the object to be driven 24 after the settling time (step S140) and outputs the generated evaluation index data to the input unit 11A. The input unit 11A then acquires the evaluation index data output from the sensor with processing unit 30A (step S145).

[0166] Once the process in step S145 is completed, the control parameter optimization system 1A proceeds to the process in step S150.

[0167] In the process of step S150, if the generation of evaluation index data satisfies predetermined conditions (step S150: Yes), the control parameter optimization system 1A terminates its second control parameter optimization process.

[0168] <Consideration> As described above, the control parameter optimization system 1A with the above configuration optimizes the control parameters by repeatedly generating control parameters until the generation of evaluation index data satisfies predetermined conditions, similar to the control parameter optimization system 1 according to Embodiment 1, by executing a second control parameter optimization process.

[0169] Therefore, the control parameter optimization system 1A, like the control parameter optimization system 1, can optimize control parameters without the need for skilled technicians and in a relatively short amount of time.

[0170] (Embodiment 3) The following describes a control parameter optimization system according to Embodiment 3, which is configured with some changes from the control parameter optimization system 1 according to Embodiment 1.

[0171] The control parameter optimization system according to Embodiment 3 is an example of a system that can provide the user with useful information in determining whether or not the environment related to the device 20 has changed during the period in which the control parameters are being optimized.

[0172] Here, regarding the control parameter optimization system according to Embodiment 3, components similar to those in Control Parameter Optimization System 1 have already been described, so they are given the same reference numerals and their detailed descriptions are omitted. The explanation will focus on the differences from Control Parameter Optimization System 1.

[0173] Figure 15 is a schematic diagram showing an overview of the control parameter optimization system 1B according to Embodiment 3.

[0174] Figure 16 is a block diagram showing the configuration of the control parameter optimization system 1B.

[0175] As shown in Figure 15, the control parameter optimization system 1B is configured in which the information processing device 10 is replaced with the information processing device 10B from the control parameter optimization system 1 according to Embodiment 1. Furthermore, as shown in Figure 16, the information processing device 10B is configured in which the control unit 13 is replaced with the control unit 13B from the information processing device 10, and the generation unit 16 is replaced with the generation unit 16B. In addition, the acquisition unit 19 is replaced with the acquisition unit 19B, and the information processing unit 18 is replaced with the information processing unit 18B.

[0176] The control unit 13B performs the same operations as the control unit 13, and also performs the following operations.

[0177] The control unit 13B, when it causes the device 20 to perform a first operation using a first control parameter at a first time and acquires first measurement data, and when it causes the device 20 to perform a first operation using the first control parameter at a second time later than the first time and acquires second measurement data, calculates the degree of environmental change, which indicates the possibility that the environment related to the device 20 has changed between the first time and the second time, based on the first measurement data and the second measurement data.

[0178] Here, the control unit 13B is described as causing the device 20 to perform the first operation using the first control parameters at a second time point. However, it is not necessarily required to use the first control parameters if the device 20 can be made to perform the first operation at a second time point. For example, the control unit 13B may cause the device 20 to perform the first operation at a second time point using control parameters similar to the first control parameters. Here, similar control parameters refer to control parameters within a range that produce the same result after the operation is performed. The same result means that the difference between the target evaluation value and the worst evaluation value when similar control parameters are used is 10% or less of the difference between the target evaluation value and the worst evaluation value when the first control parameters are used.

[0179] The control unit 13B may, for example, calculate the degree of environmental change using a Bayesian predictive distribution.

[0180] More specifically, the control unit 13B calculates one or more evaluation index data based on evaluation indices related to the operation of the device 20 from each of the one or more measurement data, including the first measurement data, acquired before the first time point, and calculates a Bayesian predictive distribution based on the one or more calculated evaluation index data. At the same time, the control unit 13B calculates comparative evaluation index data from the second measurement data. The control unit 13B may also calculate the probability of how likely the comparative evaluation index data is to occur based on the Bayesian predictive distribution, as the degree of environmental change.

[0181] Here, the evaluation index data is explained as being the settling time. However, the evaluation index data is not necessarily limited to the settling time, as long as it is a value based on an evaluation index related to the operation of the device 20. For example, it could be the total area, the degree of variation, or the effective value.

[0182] In this case, the probability calculated by the control unit 13B decreases as the number of parameters to be optimized increases, in other words, as the dimensionality of the optimization search space increases. Therefore, it is desirable for the control unit 13B to calculate the above probability corrected according to the dimensionality of the parameters to be optimized.

[0183] Alternatively, the control unit 13B may, for example, calculate the predicted measurement data that is most likely to be obtained when the device 20 performs the first operation, based on the calculated Bayesian predictive distribution, and then calculate the degree of environmental change based on the difference between the calculated predicted measurement data and the second measurement data actually obtained, such that the larger the difference, the larger the value.

[0184] Alternatively, the control unit 13B may calculate the degree of environmental change based on the difference between the first measurement data acquired at the first time and the second measurement data acquired at the second time, without using a Bayesian optimization algorithm, such that the larger the difference, the larger the value.

[0185] The control unit 13B may further cause the device 20 to perform the first operation at each of the one or more time points after the second time point to acquire one or more measurement data points, and calculate the degree of environmental change based on the first measurement data point, the second measurement data point, and one or more other measurement data points.

[0186] In this case, the control unit 13B may acquire operation count information indicating the number of times the device 20 will be instructed to perform the first operation after the second time input to the operation reception unit 15, and at each of the one or more time intervals indicated by the acquired operation count information, it may instruct the device 20 to perform the first operation and acquire one or more measurement data points.

[0187] In this case, the control unit 13B may calculate first evaluation index data based on an evaluation index related to the operation of the device 20 based on first measurement data, calculate second evaluation index data based on an evaluation index based on second measurement data, and calculate one or more evaluation index data based on an evaluation index based on one or more measurement data.

[0188] The control unit 13B may further cause the device 20 to perform a first operation or an additional operation which is a third operation different from the first operation at a third time before the second time, to acquire third measurement data related to the movement of the device 20, and cause the device 20 to perform an additional operation at a fourth time after the second time, to acquire fourth measurement data related to the movement of the device 20, and calculate the degree of environmental change based on the third and fourth measurement data in addition to the first and second measurement data.

[0189] When the control unit 13B calculates the degree of environmental change, it determines whether or not to display an image on the display unit 17 based on the first measurement data and the second measurement data, based on the calculated degree of environmental change.

[0190] The control unit 13B may, for example, determine whether to display the display image on the display unit 17 if the calculated environmental change rate satisfies predetermined conditions, and determine whether to not display the display image on the display unit 17 if the predetermined conditions are not met.

[0191] Here, the predetermined condition may be, for example, a condition that the degree of environmental change is greater than a predetermined threshold.

[0192] The control unit 13B may further identify a recommended optimization algorithm suitable for the algorithm used to optimize the control parameters, based on the progress of the optimization of the control parameters.

[0193] Bayesian optimization algorithms optimize control parameters using all acquired data, so if the environment related to the device 20 changes, there is a relatively high possibility that the optimization of control parameters will not be performed correctly. On the other hand, evolutionary strategy algorithms (CMA-ES) and genetic algorithms (GA) optimize control parameters by giving emphasis to the most recently acquired data.

[0194] Therefore, the control unit 13B may, for example, calculate the Bayesian optimization algorithm as the recommended optimization algorithm when the calculated degree of environmental change is relatively low, and calculate the evolutionary strategy algorithm (CMA-ES) or the genetic algorithm (GA) as the recommended optimization algorithm when the calculated degree of environmental change is relatively high.

[0195] When the control unit 13B determines that the display image should be displayed on the display unit 17, the generation unit 16B generates a display image based on the first measurement data and the second measurement data, and displays the generated display image on the display unit 17.

[0196] In this case, the generation unit 16B may generate a display image that includes a first measurement image related to the first measurement data and a second measurement image related to the second measurement data, and display the generated display image on the display unit 17.

[0197] Here, if the control unit 13B calculates first evaluation index data based on evaluation indicators related to the operation of the device 20 based on first measurement data, and calculates second evaluation index data based on evaluation indicators related to the operation of the device 20 based on second measurement data, the generation unit 16B may generate a display image including a first measurement image showing the first evaluation index data and a second measurement image showing the second evaluation index data, and display the generated display image on the display unit 17.

[0198] Figure 17 is an example of a display image generated by the generation unit 16B when the first and second evaluation index data calculated by the control unit 13B are settling time, the optimization of control parameters is interrupted at an interruption time between the first and second time points during the period when the information processing device 10B is optimizing the control parameters in the device 20, and the optimization of the interrupted parameters is resumed at a restart time between the interruption time and the second time point.

[0199] In the example in Figure 17, the first evaluation index data corresponds to "xxx" in the description "Settling time before interruption: xxx [ms]", the second evaluation index data corresponds to "yyy" in the description "Settling time after restart: yyy [ms]", the first measurement image corresponds to the image consisting of the string "Settling time before interruption: xxx [ms]", and the second measurement image corresponds to the image consisting of the string "Settling time after restart: yyy [ms]".

[0200] In this case, if the first measurement data and the second measurement data are in time series, the generation unit 16B may generate a display image that includes a first measurement image showing the time series waveform of the first measurement data and a second measurement image showing the time series waveform of the second measurement data, and display the generated display image on the display unit 17.

[0201] Figure 18 is an example of a display image when the generation unit 16B generates a display image that shows a first measurement image showing the time-series waveform of the first measurement data and a second measurement image showing the time-series waveform of the second measurement data side by side.

[0202] In the example in Figure 18, the first measurement image corresponds to the image showing the waveform below the text "Position deviation waveform before interruption," and the second measurement image corresponds to the image showing the waveform below the text "Position deviation waveform after resumption."

[0203] In this case, the generation unit 16B may generate a display image by superimposing a first measurement image showing the time-series waveform of the first measurement data and a second measurement image showing the time-series waveform of the second measurement data, and display the generated display image on the display unit 17.

[0204] Figure 19 is an example of a display image when the generation unit 16B generates a display image that superimposes a first measurement image showing the time-series waveform of the first measurement data and a second measurement image showing the time-series waveform of the second measurement data.

[0205] In the example in Figure 19, the first measurement image corresponds to an image showing a waveform indicated by a solid line, and the second measurement image corresponds to an image showing a waveform indicated by a dashed line.

[0206] Furthermore, the generation unit 16B may also generate a display image based on the one or more measurement data obtained when the control unit 13B causes the device 20 to perform the first operation at each of the one or more time points after the second time point.

[0207] Furthermore, the generation unit 16B may, when the control unit 13B causes the device 20 to perform the first operation at each of the one or more time points after the second time point to acquire one or more measurement data points, calculate first evaluation index data based on the first measurement data, calculate second evaluation index data based on the second measurement data, and calculate one or more evaluation index data based on one or more measurement data points, generate a display image including an image related to one or more difference measurement data points corresponding to each of the one or more difference evaluation index data points among the second evaluation index data and the one or more evaluation index data points that have a difference greater than the second threshold between the first evaluation index data and the second threshold, and display the generated display image on the display unit 17.

[0208] Figure 20 shows an example of a display image when the generation unit 16B generates a display image by superimposing a first measurement image showing the time-series waveform of the first measurement data and one or more measurement images showing the time-series waveforms of measurement data with one or more differences.

[0209] In the example in Figure 20, the first measurement image corresponds to an image showing a waveform indicated by a solid line, and one or more measurement images correspond to images showing waveforms indicated by dashed lines.

[0210] Furthermore, if the control unit 13B has the device 20 perform one or more first operations before the second time point to acquire one or more measurement data (hereinafter also referred to as "one or more additional measurement data"), and has calculated first evaluation index data based on the first measurement data, the generation unit 16B may generate a display image that further superimposes one or more additional measurement images showing the waveforms of these one or more additional measurement data.

[0211] Figure 21 is an example of a display image when the generation unit 16B generates a display image that further superimposes a first measurement image showing the time-series waveform of the first measurement data, one or more measurement images showing the time-series waveform of one or more difference measurement data, and one or more additional measurement images showing the waveform of one or more additional measurement data.

[0212] In the example in Figure 21, the first measurement image and one or more additional measurement images correspond to images showing waveforms indicated by solid lines, while one or more measurement images correspond to images showing waveforms indicated by dashed lines.

[0213] In this case, the generation unit 16B may acquire the second threshold value input to the operation reception unit 15.

[0214] Furthermore, if the input unit 11 acquires at least one of the first operational status information relating to the first temperature, first humidity, and operating status of an external device in the environment where the device 20 is installed at a first time, and at least one of the second operational status information relating to the second temperature, second humidity, and operating status of an external device in the environment where the device 20 is installed at a second time, the generation unit 16B may generate a display image including an image showing at least one of the first operational status information relating to the first temperature, first humidity, and operating status of an external device in the environment where the device 20 is installed at a first time, and an image showing at least one of the second operational status information relating to the second temperature, second humidity, and operating status of an external device in the environment where the device 20 is installed at a second time, and display the generated display image on the display unit 17.

[0215] Here, the external device may be, for example, a peripheral device of device 20. Peripheral devices include, for example, a printer, a hard disk, etc., attached to device 20.

[0216] Figure 22 is an example of a display image when the generation unit 16B generates a display image that includes an image showing at least one of the following at a first time: a first temperature, a first humidity, and first operational status information relating to the operating status of an external device in the environment in which the device 20 is installed, and an image showing at least one of the following at a second time: a second temperature, a second humidity, and second operational status information relating to the operating status of an external device in the environment in which the device 20 is installed.

[0217] Furthermore, the generation unit 16B may generate a display image including an image showing the time difference between the interruption time and the restart time if, during the period in which the information processing device 10B is optimizing the control parameters in the device 20, the optimization of the control parameters is interrupted at an interruption time that is later than the first time and earlier than the second time, and the optimization of the interrupted parameters is resumed at a restart time that is later than the interruption time and earlier than the second time, and display the generated display image on the display unit 17.

[0218] Figure 23 is an example of a display image when the generation unit 16B generates a display image that includes an image showing the time difference between the interruption time and the restart time.

[0219] Furthermore, the generation unit 16B may, if the control unit 13B has the device 20 perform an additional operation, which is either a first operation or a third operation different from the first operation, at a third time before the second time, to acquire third measurement data relating to the movement of the device 20, and if the device 20 performs an additional operation at a fourth time after the second time, to acquire fourth measurement data relating to the movement of the device 20, generate a display image based on the third and fourth measurement data in addition to the first and second measurement data, and display the generated display image on the display unit 17.

[0220] Alternatively, the generation unit 16B may generate a display image including an image showing the degree of environmental change when the control unit 13B calculates the degree of environmental change, and display the generated display image on the display unit 17.

[0221] Figure 24 shows an example of a display image when the generation unit 16B generates a display image that includes an image showing the degree of environmental change.

[0222] The example in Figure 24 is an example of a display image that corresponds to the case where the degree of environmental change calculated by the control unit 13B is 50%.

[0223] Furthermore, when the control unit 13B calculates the degree of environmental change, and the degree of environmental change is greater than a predetermined threshold (first threshold), the generation unit 16B may generate a display image that includes at least one of the following images: an image related to an inquiry about whether to review the installation status of the device 20, an image related to an inquiry about whether to continue optimizing the control parameters, an image related to an inquiry about whether to restart the optimization from the beginning, and an image related to an inquiry about whether to change the algorithm used for optimization, and display the generated display image on the display unit 17.

[0224] Figures 25A to 25C are examples of display images when the generation unit 16B generates a display image that includes at least one of the following images: an image related to an inquiry about whether to review the installation status of the device 20, an image related to an inquiry about whether to continue optimizing the control parameters, an image related to an inquiry about whether to restart the optimization from the beginning, and an image related to an inquiry about whether to change the algorithm used for optimization.

[0225] Alternatively, the generation unit 16B may generate a display image including an image showing the identified recommended optimization algorithm when the control unit 13B has identified a recommended optimization algorithm, and display the generated display image on the display unit 17.

[0226] Figure 26 is an example of a display image when the generation unit 16B generates a display image that includes an image showing the recommended optimization algorithm.

[0227] The example in Figure 26 is an example of a display image that corresponds to the case where the recommended optimization algorithm identified by the control unit 13B is the Evolutionary Strategy Algorithm (CMA-ES).

[0228] <Operation> The following describes the operation performed by the control parameter optimization system 1B with the above configuration.

[0229] The control parameter optimization system 1B performs the third to ninth control parameter optimization processes instead of the first control parameter optimization process according to Embodiment 1.

[0230] Figure 27 is a flowchart of the third control parameter optimization process.

[0231] As shown in Figure 27, the third control parameter optimization process includes the processes from step S310 to step S395.

[0232] Of these processes, the processes from step S310 to step S350, and the processes from step S355 to step S365 are the same as the processes from step S10 to step S50, and the processes from step S55 to step S65 in the first control parameter optimization process, respectively.

[0233] Therefore, this explanation will focus on the processes from step S370 to step S395.

[0234] In the process of step S350, if the process proceeds to step S350:No, the control unit 13B checks whether a predetermined amount of time (for example, 1 day) has elapsed since the time when the process proceeded to step S370:Yes in the previous step S370, in a loop process that returns from the process of step S320 through the process of step S350:No to the process of step S320 (step S370).

[0235] Here, if the control unit 13B has not proceeded to step S370:Yes even once in the above loop processing, it checks whether a predetermined time has elapsed since the time when step S370 was first performed.

[0236] In the process of step S370, if the predetermined time has not elapsed (step S370: No), the control unit 13B checks whether an operation to interrupt the third control parameter optimization process has been made to the information processing device 10B (step S375).

[0237] Here, the operation to interrupt the third control parameter optimization process may be, for example, clicking the interruption icon in the display image shown in Figure 8.

[0238] If, during the process in step S375, an operation is performed that interrupts the third control parameter optimization process (step S375:Yes), the generation unit 16B waits until an operation is made to restart the interrupted third control parameter optimization process to the information processing device 10B. Once the operation to restart the interrupted third control parameter optimization process is made (step S385:Yes), the generation unit 16B generates a display image that includes an image showing the time difference between the interruption time when the process proceeded to step S375:Yes and the restart time when the process proceeded to step S385:Yes, and displays the generated display image on the display unit 17 (step S390).

[0239] Here, the operation to resume the interrupted third control parameter optimization process may be, for example, clicking the resume icon in the display image shown in Figure 8.

[0240] In the process of step S390, the display image generated by the generation unit 16B is, for example, the display image shown in Figure 23.

[0241] When the process in step S390 is completed, or when a predetermined time has elapsed during the process in step S370 (step S370: Yes), the control parameter optimization system 1B performs the first restart process (step S395).

[0242] Figure 28 is a flowchart of the first restart process performed by the control parameter optimization system 1B.

[0243] As shown in Figure 28, when the first restart process is started, the control unit 13B, if it proceeds to step S395 via step S390 in the third control parameter optimization process, selects a first control parameter corresponding to relatively good evaluation index data from the evaluation index data generated in the third control parameter optimization process before the interruption. If it proceeds to step S395 via step S370:Yes, it selects a first control parameter corresponding to relatively good evaluation index data from the evaluation index data generated in the third control parameter optimization process before the predetermined time had elapsed (step S405).

[0244] Here, the control unit 13B may, for example, select the shortest settling time as a relatively good evaluation index data if the evaluation index data is the settling time.

[0245] When the first control parameter is selected, the control unit 13B acquires the first control parameter and the first evaluation index data corresponding to the first evaluation index data (step S410). Then, the output unit 12 transmits the first control parameter to the storage unit 21 (step S415). Here, the output unit 12 may transmit a control parameter similar to the first control parameter to the storage unit 21 instead of the first control parameter. Hereafter, the first control parameter and the control parameter similar to the first control parameter will simply be referred to as the first control parameter.

[0246] When the first control parameter is output from the output unit 12, the storage unit 21 stores the first control parameter output from the output unit 12 (step S420). Then, the control unit 22 generates a command to move the position of the object to be driven 24 to a predetermined target position based on the first control parameter stored in the storage unit 21 and outputs it to the drive unit 23. As a result, the control unit 22 controls the drive unit 23 (step S425). Then, the drive unit 23 drives the object to be driven 24 based on the command output from the control unit 22 (step S430).

[0247] When the object to be driven 24 is driven by the drive unit 23, the sensor 30 measures the position of the object to be driven 24 in a time series (step S435) and outputs second measurement data representing the position of the object to be driven 24 to the input unit 11. The input unit 11 then acquires the second measurement data in a time series output from the sensor 30 (step S440).

[0248] When the input unit 11 acquires the second measurement data, the control unit 13B generates second evaluation index data indicating the vibration of the driven object 24 after the settling time, based on the second measurement data (step S445).

[0249] When the second evaluation index data is generated, the control unit 13B calculates the degree of environmental change, which indicates the possibility that the environment related to the device 20 has changed between the first time when the operation corresponding to the first measurement data was performed by the device 20 and the second time when the operation corresponding to the second measurement data was performed by the device 20, based on the first measurement data and the second measurement data (step S446).

[0250] Once the degree of environmental change is calculated, the control unit 13B determines whether or not to display an image based on the first measurement data and the second measurement data on the display unit 17 based on the calculated degree of environmental change (step S447).

[0251] If, in the above determination, it is determined that the display image should be displayed on the display unit 17 (step S448: Yes), the generation unit 16B generates a display image including a first measurement image related to the first evaluation index data and a second measurement image related to the second evaluation index data, and displays the generated display image on the display unit 17 (step S450).

[0252] In the process of step S450, the display image generated by the generation unit 16B is, for example, one of the display images exemplified in Figures 17, 18, and 19.

[0253] In the above determination, the first restart processing ends its processing both when it is determined that a display image is not to be displayed on the display unit 17 (step S448: No) and when the processing of step S450 is completed.

[0254] Returning to FIG. 27 again, the description of the third control parameter optimization processing will be continued.

[0255] When the first restart processing (step S395) is completed, and when no operation to interrupt the third control parameter optimization processing has been performed in the processing of step S375 (step S375: No), the processing proceeds to step S355.

[0256] In the processing of step S350, when the generated evaluation index data satisfies a predetermined condition (step S350: Yes), the control parameter optimization system 1B ends the third control parameter optimization processing.

[0257] FIG. 29 is a flowchart of the fourth control parameter optimization processing.

[0258] As shown in FIG. 29, the fourth control parameter optimization processing includes the processing from step S510 to step S595.

[0259] Among these processings, the processing from step S510 to step S590 are respectively the same processing as the processing from step S310 to step S390 in the third control parameter optimization processing.

[0260] Therefore, the description here will focus on the processing of step S595.

[0261] When the processing of step S590 is completed, and when a predetermined time has elapsed in the processing of step S570 (step S570: Yes), the control parameter optimization system 1B performs a second restart processing (step S595).

[0262] Figure 30 is a flowchart of the second restart process performed by the control parameter optimization system 1B.

[0263] As shown in Figure 30, the second restart process includes the processes from step S605 to step S665.

[0264] Of these processes, the process in step S605 and the processes from step S615 to step S640 are the same as the processes in step S405 and the processes from step S415 to step S440 in the first restart process, respectively.

[0265] Therefore, this explanation will focus on the processing in step S610, and the processing from steps S645 to S665.

[0266] When the processing in step S605 is completed, the control unit 13B acquires a first control parameter corresponding to the first evaluation index data (step S610).

[0267] Once the processing in step S610 is complete, the process proceeds to step S615.

[0268] When the processing in step S640 is completed, the control unit 13B calculates the degree of environmental change, based on the first measurement data and the second measurement data, which indicates the possibility that the environment related to the device 20 has changed between the first time when the operation corresponding to the first measurement data was performed by the device 20 and the second time when the operation corresponding to the second measurement data was performed by the device 20 (step S645).

[0269] Once the degree of environmental change is calculated, the generation unit 16B checks whether the degree of environmental change is greater than the first threshold (step S650).

[0270] In the process of step S650, if the degree of environmental change is greater than the first threshold (step S650: Yes), the generation unit 16B generates a display image that includes at least one of the following images: an image related to the inquiry of whether or not to review the installation status of the device 20, an image related to the inquiry of whether or not to continue optimizing the control parameters, an image related to the inquiry of whether or not to restart the optimization from the beginning, and an image related to the inquiry of whether or not to change the algorithm used for optimization, and displays the generated display image on the display unit 17 (step S655).

[0271] In the process of step S655, the display image generated by the generation unit 16B is, for example, one of the display images exemplified in Figures 25A, 25B, and 25C.

[0272] When a display image is shown on the display unit 17, the control unit 13B checks for a response operation to the information processing device 10B performed by the user who has viewed the display image (step S660).

[0273] In the process of step S660, if the response operation performed by the user is an operation indicating C: to change the algorithm used for optimization (step S660:C), the control unit 13B changes the algorithm used for optimization to the algorithm indicated by the user (step S665).

[0274] The second restart process terminates if, in the process of step S650, the degree of environmental change is not greater than the first threshold (step S650: No); in the process of step S660, the response operation performed by the user is A: an operation indicating that the review of the installation of the device 20 has been completed or an instruction to continue optimizing the control parameters (step S660: A); in the process of step S660, the response operation performed by the user is B: an operation indicating that the optimization should be restarted from the beginning (step S660: B); or when the process of step S665 is completed.

[0275] Returning to FIG. 29 again, the description of the fourth control parameter optimization process will be continued.

[0276] If the second restart process (step S595) ends via the process of step S650:No or via the process of step S660:A, and if no operation to interrupt the fourth control parameter optimization process has been performed in the process of step S575 (step S575:No), the process proceeds to step S555.

[0277] If the second restart process (step S595) ends via the process of step S660:B or via the process of step S665, the process proceeds to step S515.

[0278] In the process of step S550, if the generated evaluation index data satisfies a predetermined condition (step S550:Yes), the control parameter optimization system 1B ends the fourth control parameter optimization process.

[0279] FIG. 31 is a flowchart of the fifth control parameter optimization process.

[0280] As shown in FIG. 31, the fifth control parameter optimization process includes the processes from step S710 to step S795.

[0281] Among these processes, the processes from step S710 to step S790 are respectively the same as the processes from step S310 to step S390 in the third control parameter optimization process.

[0282] Therefore, the description herein will focus on the process of step S795.

[0283] When the process of step S790 is completed, and when a predetermined time has elapsed in the process of step S770 (step S770:Yes), the control parameter optimization system 1B performs a third restart process (step S795).

[0284] Figure 32 is a flowchart of the third restart process performed by the control parameter optimization system 1B.

[0285] As shown in Figure 32, the third restart process includes the processes from step S800 to step S860, and the processes from step S815A to step S840A.

[0286] Of these processes, the processes from step S805 to step S845 are the same as the processes from step S405 to step S445 in the first restart process.

[0287] Furthermore, the processes from step S815A to step S835A are the same as the processes from step S815 to step S835, respectively.

[0288] Therefore, this explanation will focus on the processing in step S800, the processing from step S840A to step S845A, and the processing from step S850 to step S860.

[0289] When the third restart process begins, the control unit 13B acquires operation count information, which is input to the operation reception unit 15 and indicates the number of times the device 20 will be made to perform the first operation after the second time, and assigns the number indicated by the acquired operation count information to an integer n of 1 or more (step S800).

[0290] Once the processing in step S800 is complete, the process proceeds to step S805.

[0291] Once the processing in step S835A is complete, the input unit 11 acquires the time-series measurement data output from the sensor 30 (step S840A).

[0292] When the input unit 11 acquires measurement data, the control unit 13B generates evaluation index data indicating the vibration of the driven object 24 after the settling time, based on the measurement data (step S845A).

[0293] Once the evaluation index data is generated, the control unit 13B substitutes n-1 for n (step S850) and checks whether the resulting n is greater than 0 (step S855).

[0294] In step S855, if n is greater than 0 (step S855: Yes), proceed to step S815A.

[0295] In the process of step S855, if n is not greater than 0 (step S855: No), the control unit 13B calculates the degree of environmental change, based on the first measurement data and the second measurement data, which indicates the possibility that the environment related to the device 20 has changed between the first time when the operation corresponding to the first measurement data was performed by the device 20 and the second time when the operation corresponding to the second measurement data was performed by the device 20 (step S856).

[0296] Once the degree of environmental change is calculated, the control unit 13B determines whether or not to display an image based on the first measurement data and the second measurement data on the display unit 17 based on the calculated degree of environmental change (step S857).

[0297] If, in the above determination, it is determined that the display image should be displayed on the display unit 17 (step S858: Yes), the generation unit 16B generates a display image that includes a first measurement image related to the first evaluation index data, a second measurement image related to the second evaluation index data, and n measurement images related to n evaluation index data, and displays the generated display image on the display unit 17 (step S860).

[0298] In the process of step S860, the display image generated by the generation unit 16B is, for example, the display image exemplified in Figure 20.

[0299] In the above determination, if it is determined that the display image should not be displayed on the display unit 17 (step S858: No), or if the processing in step S860 is completed, the third restart process terminates.

[0300] Returning to Figure 31, let's continue the explanation of the fifth control parameter optimization process.

[0301] If the third restart process (step S795) is completed, or if no operation that interrupts the fifth control parameter optimization process is performed in step S775 (step S775: No), the process proceeds to step S755.

[0302] In the process of step S750, if the generated evaluation index data satisfies the predetermined conditions (step S750: Yes), the control parameter optimization system 1B terminates its fifth control parameter optimization process.

[0303] Figure 33 is a flowchart of the sixth control parameter optimization process.

[0304] As shown in Figure 33, the sixth control parameter optimization process includes the processes from step S910 to step S995. Of these processes, the processes from step S910 to step S990 are the same as the processes from step S310 to step S390 in the third control parameter optimization process.

[0305] Therefore, this explanation will focus on the process in step S995.

[0306] When the processing in step S990 is completed, or when a predetermined time has elapsed during the processing in step S970 (step S970: Yes), the control parameter optimization system 1B performs a fourth restart process (step S995).

[0307] Figure 34 is a flowchart of the fourth restart process performed by the control parameter optimization system 1B.

[0308] As shown in Figure 34, the fourth restart process includes the processes from step S1000 to step S1065, and the processes from step S1015A to step S1040A.

[0309] Of these processes, the process in step S1000 and the processes from step S1010 to step S1040 are applications of the processes in step S800 and steps S810 to step S840 in the third restart process, respectively, and the processes in step S1005 and steps S1050 to step S1065 are the same as the processes in step S610 and steps S650 to step S665 in the second restart process, respectively.

[0310] Furthermore, the processes from step S1015A to step S1035A are the same as the processes from step S1015 to step S1035, respectively.

[0311] Therefore, this explanation will focus on the processing in step S1040A, and the processing from steps S1041 to S1043.

[0312] Once the processing in step S1035A is complete, the input unit 11 acquires the time-series measurement data output from the sensor 30 (step S1040A).

[0313] When the input unit 11 acquires measurement data, the control unit 13B substitutes n-1 for n (step S1041) and checks whether the resulting n is greater than 0 (step S1042).

[0314] In step S1042, if n is greater than 0 (step S1042: Yes), proceed to step S1015A.

[0315] In the process of step S1042, if n is not greater than 0 (step S1042: No), the control unit 13B calculates the degree of environmental change, which indicates the possibility that the environment related to the device 20 has changed between the first time when the operation corresponding to the first measurement data was performed by the device 20 and the second time when the operation corresponding to the second measurement data was performed by the device 20, based on the first measurement data, the second measurement data, and the n measurement data (step S1043).

[0316] Once the processing in step S1043 is complete, the process proceeds to step S1050.

[0317] The fourth restart process terminates if, in the process of step S1050, the degree of environmental change is not greater than the first threshold (step S1050: No); in the process of step S1060, the response operation performed by the user is A: an operation indicating that the review of the installation of the device 20 has been completed or an instruction to continue optimizing the control parameters (step S1060: A); in the process of step S1060, the response operation performed by the user is B: an operation indicating that the optimization should be restarted from the beginning (step S1060: B); or when the process of step S1065 is completed.

[0318] Returning to Figure 33, we will continue the explanation of the sixth control parameter optimization process.

[0319] If the fourth restart process (step S995) is completed via the process in step S1050:No or via the process in step S1060:A, or if no operation is performed in the process in step S975 that interrupts the sixth control parameter optimization process (step S975:No), the process proceeds to step S955.

[0320] If the fourth restart process (step S995) is completed via the process in step S1060:B or via the process in step S1065, the process proceeds to step S915.

[0321] In the process of step S950, if the generated evaluation index data satisfies the predetermined conditions (step S950: Yes), the control parameter optimization system 1B terminates its sixth control parameter optimization process.

[0322] Figure 35 is a flowchart of the seventh control parameter optimization process.

[0323] As shown in Figure 35, the seventh control parameter optimization process includes the processes from step S1110 to step S1195. Of these processes, the processes from step S1110 to step S1190 are the same as the processes from step S310 to step S390 in the third control parameter optimization process.

[0324] Therefore, this explanation will focus on the process in step S1195.

[0325] When the process in step S1190 is completed, or when a predetermined time has elapsed during the process in step S1170 (step S1170: Yes), the control parameter optimization system 1B performs a fifth restart process (step S1195).

[0326] Figure 36 is a flowchart of the fifth restart process performed by the control parameter optimization system 1B.

[0327] As shown in Figure 36, the fifth restart process includes the processes from step S1205 to step S1250, and the processes from step S1215A to step S1245A.

[0328] Of these processes, the processes from step S1215 to step S1235 are the same as the processes from step S415 to step S435 in the first restart process.

[0329] Therefore, this explanation will focus on the processes from step S1205 to step S1210, from step S1240 to step S1250, and from step S1215A to step S1245A.

[0330] When the fifth restart process is initiated, the control unit 13B, if it proceeds to step S1195 via step S1190 in the seventh control parameter optimization process, selects the first and second control parameters corresponding to relatively good evaluation index data from the evaluation index data generated in the seventh control parameter optimization process before the interruption. If it proceeds to step S1195 via step S1170:Yes, it selects the first and second control parameters corresponding to relatively good evaluation index data from the evaluation index data generated in the seventh control parameter optimization process before the predetermined time had elapsed (step S1205).

[0331] Here, the control unit 13B may, for example, if the evaluation index data is the settling time, select the shortest settling time and the next shortest settling time as the first and second control parameters, respectively, as relatively good evaluation index data.

[0332] When the first control parameter and the second control parameter are selected, the control unit 13B acquires the first control parameter and the first evaluation index data corresponding to the first evaluation index data, as well as the second control parameter and the second evaluation index data corresponding to the second evaluation index data (step S1210).

[0333] Once the processing in step S1210 is complete, the process proceeds to step S1215.

[0334] When the processing in step S1235 is completed, the input unit 11 acquires the third time-series measurement data output from the sensor 30 (step S1240).

[0335] When the input unit 11 acquires the third measurement data, the control unit 13B generates a third evaluation index data indicating the vibration of the driven object 24 after the settling time, based on the third measurement data (step S1245). Then, the output unit 12 transmits the second control parameter to the storage unit 21 (step S1215A). Here, the output unit 12 may transmit a control parameter similar to the second control parameter to the storage unit 21 instead of the second control parameter. Hereafter, the second control parameter and the control parameter similar to the second control parameter will simply be referred to as the second control parameter.

[0336] When the second control parameter is output from the output unit 12, the storage unit 21 stores the second control parameter output from the output unit 12 (step S1220A). Then, the control unit 22 generates a command to move the position of the object to be driven 24 to a predetermined target position based on the second control parameter stored in the storage unit 21 and outputs it to the drive unit 23. As a result, the control unit 22 controls the drive unit 23 (step S1225A). Then, the drive unit 23 drives the object to be driven 24 based on the command output from the control unit 22 (step S1230A).

[0337] When the object to be driven 24 is driven by the drive unit 23, the sensor 30 measures the position of the object to be driven 24 in a time series (step S1235) and outputs a fourth measurement data representing the position of the object to be driven 24 to the input unit 11. The input unit 11 then acquires the fourth measurement data in a time series output from the sensor 30 (step S1240A).

[0338] When the input unit 11 acquires the fourth measurement data, the control unit 13B generates a fourth evaluation index data indicating the vibration of the driven object 24 after the settling time, based on the fourth measurement data (step S1245A).

[0339] When the fourth evaluation index data is generated, the control unit 13B calculates the degree of environmental change, which indicates the possibility that the environment related to the device 20 has changed, based on the first measurement data, the second measurement data, the third measurement data, and the fourth measurement data, between a first time, which is the later of the time when the operation corresponding to the first measurement data was performed by the device 20 and the time when the operation corresponding to the second measurement data was performed by the device 20, and a second time, which is the earlier of the time when the operation corresponding to the third measurement data was performed by the device 20 and the time when the operation corresponding to the fourth measurement data was performed by the device 20 (step S1246).

[0340] Once the degree of environmental change is calculated, the control unit 13B determines whether or not to display an image based on the first measurement data and the second measurement data on the display unit 17 based on the calculated degree of environmental change (step S1247).

[0341] If, in the above determination, it is determined that the display image should be displayed on the display unit 17 (step S1248: Yes), the generation unit 16B generates a display image that includes a first measurement image related to the first evaluation index data, a second measurement image related to the second evaluation index data, a third measurement image related to the third evaluation index data, and a fourth measurement image related to the fourth evaluation index data, and displays the generated display image on the display unit 17 (step S1250).

[0342] In the above determination, if it is determined that the display image should not be displayed on the display unit 17 (step S1248: No), or if the processing in step S1250 is completed, the fifth restart process terminates.

[0343] Returning to Figure 35, we will continue the explanation of the seventh control parameter optimization process.

[0344] If the fifth restart process (step S1195) is completed, or if no operation that interrupts the seventh control parameter optimization process is performed in the process of step S1175 (step S1175: No), the process proceeds to step S1155.

[0345] In the process of step S1150, if the generated evaluation index data satisfies the predetermined conditions (step S1150: Yes), the control parameter optimization system 1B terminates its seventh control parameter optimization process.

[0346] Figure 37 is a flowchart of the eighth control parameter optimization process.

[0347] As shown in Figure 37, the eighth control parameter optimization process includes the processes from step S1310 to step S1395. Of these processes, the processes from step S1310 to step S1390 are the same as the processes from step S310 to step S390 in the third control parameter optimization process.

[0348] Therefore, this explanation will focus on the process in step S1395.

[0349] When the process in step S1390 is completed, or when a predetermined time has elapsed during the process in step S1370 (step S1370: Yes), the control parameter optimization system 1B performs a sixth restart process (step S1395).

[0350] Figure 38 is a flowchart of the sixth restart process performed by the control parameter optimization system 1B.

[0351] As shown in Figure 38, the sixth restart process includes the processes from step S1405 to step S1465, and the processes from step S1415A to step S1440A.

[0352] Of these processes, the processes in step S1405, steps S1415 to S1440, and steps S1415A to S1440A are the same as the processes in step S1205, steps S1215 to S1240, and steps S1215A to S1240A in the fifth restart process, respectively.

[0353] Furthermore, the processes from step S1450 to step S1465 are the same as the processes from step S650 to step S665 in the second restart process.

[0354] Therefore, this explanation will focus on the processes in step S1410 and step S1445.

[0355] When the processing in step S1405 is completed, the control unit 13B acquires a first control parameter corresponding to the first evaluation index data and a second control parameter corresponding to the second evaluation index data (step S1410).

[0356] Once the processing in step S1410 is complete, the process proceeds to step S1415.

[0357] When the processing in step S1440A is completed, the control unit 13B calculates the degree of environmental change that indicates the possibility of a change in the environment related to the device 20, based on the first measurement data, the second measurement data, the third measurement data, and the fourth measurement data, between a first time, which is the later of the time when the operation corresponding to the first measurement data was performed by the device 20 and the time when the operation corresponding to the second measurement data was performed by the device 20, and a second time, which is the earlier of the time when the operation corresponding to the third measurement data was performed by the device 20 and the time when the operation corresponding to the fourth measurement data was performed by the device 20 (step S1445).

[0358] Once step S1445 is completed, the process proceeds to step S1450.

[0359] The sixth restart process terminates if, in the process of step S1450, the degree of environmental change is not greater than the first threshold (step S1450: No); in the process of step S1460, the response operation performed by the user is A: an operation indicating that the review of the installation of the device 20 has been completed or an instruction to continue optimizing the control parameters (step S1460: A); in the process of step S1460, the response operation performed by the user is B: an operation indicating that the optimization should be restarted from the beginning (step S1460: B); or when the process of step S1465 is completed.

[0360] Returning to Figure 37, let's continue the explanation of the eighth control parameter optimization process.

[0361] If the sixth restart process (step S1395) is completed via the process in step S1450:No or via the process in step S1460:A, and if no operation is performed in the process in step S1375 that interrupts the eighth control parameter optimization process (step S1375:No), the process proceeds to step S1355.

[0362] If the sixth restart process (step S1395) is completed via the process in step S1460:B or via the process in step S1465, the process proceeds to step S1315.

[0363] In the process of step S1350, if the generated evaluation index data satisfies predetermined conditions (step S1350: Yes), the control parameter optimization system 1B terminates its eighth control parameter optimization process.

[0364] Figure 39 is a flowchart of the ninth control parameter optimization process.

[0365] As shown in Figure 39, the ninth control parameter optimization process includes the processes from step S1510 to step S1595.

[0366] Of these processes, the processes from step S1510 to step S1540, and the processes from step S1545 to step S1590 are the same as the processes from step S310 to step S340, and the processes from step S345 to step S390 in the third control parameter optimization process, respectively.

[0367] Therefore, this explanation will focus on the processes in step S1542 and step S1595.

[0368] When the processing in step S1540 is completed, the input unit 11 acquires at least one of the following: a first temperature in the environment in which the device 20 is installed, a first humidity, and first operating status information relating to the operating status of an external device (step S1542).

[0369] Once the processing in step S1542 is complete, the process proceeds to step S1545.

[0370] When the process in step S1590 is completed, or when a predetermined time has elapsed during the process in step S1570 (step S1570: Yes), the control parameter optimization system 1B performs a seventh restart process (step S1595).

[0371] Figure 40 is a flowchart of the seventh restart process performed by the control parameter optimization system 1B.

[0372] As shown in Figure 40, when the seventh restart process is started, if the control unit 13B proceeds to step S1595 via the process of step S1590, it selects a first control parameter corresponding to relatively good evaluation index data from the evaluation index data generated in the ninth control parameter optimization process before the interruption. If the control unit 13B proceeds to step S1595 via the process of step S1570:Yes, it selects a first control parameter corresponding to relatively good evaluation index data from the evaluation index data generated in the ninth control parameter optimization process before the predetermined time had elapsed (step S1605).

[0373] Here, the control unit 13B may, for example, select the shortest settling time as a relatively good evaluation index data if the evaluation index data is the settling time.

[0374] When the first evaluation index data is selected, the generation unit 16B acquires at least one of the following, which corresponds to the first evaluation index data: the first temperature in the environment in which the device 20 is installed, the first humidity, and first operating status information relating to the operating status of external devices (step S1605).

[0375] The input unit 11 then acquires at least one of the following: a second temperature in the environment where the device 20 is installed at the present time, a second humidity, and second operating status information relating to the operating status of external devices (step S1615).

[0376] When at least one of the second temperature, second humidity, and second operating status information is acquired, the generation unit 16B generates a display image including an image showing at least one of the first temperature, first humidity, and first operating status information, and an image showing at least one of the second temperature, second humidity, and second operating status information, and displays the generated display image on the display unit 17 (step S1620).

[0377] In the process of step S1620, the display image generated by the generation unit 16B is, for example, the display image exemplified in Figure 22.

[0378] Once the processing in step S1620 is complete, the seventh restart process terminates.

[0379] Returning to Figure 39, let's continue the explanation of the ninth control parameter optimization process.

[0380] If the seventh restart process (step S1595) is completed, or if no operation is performed in step S1575 that interrupts the ninth control parameter optimization process (step S1575: No), the process proceeds to step S1555.

[0381] In the process of step S1550, if the generated evaluation index data satisfies the predetermined conditions (step S1550: Yes), the control parameter optimization system 1B terminates its ninth control parameter optimization process.

[0382] <Consideration> As described above, the control parameter optimization system 1B with the above configuration determines whether or not to display the display image on the display unit 17 based on the degree to which the environment related to the device 20 has changed between the first time and the second time during the period in which the control parameters are being optimized.

[0383] Therefore, users of the control parameter optimization system 1B can obtain useful information for determining whether or not there have been environmental changes related to the device 20 between the first time and the second time by visually checking the display unit 17.

[0384] (supplement) As described above, the technologies disclosed in this application have been explained based on Embodiments 1 to 3. However, this disclosure is not limited to these Embodiments 1 to 3. Without departing from the spirit of this disclosure, various modifications that a person skilled in the art could conceive of these embodiments or modifications, or forms constructed by combining components from different embodiments or modifications, may also be included within the scope of one or more aspects of this disclosure.

[0385] (1) In Embodiment 1, the information processing device 10 was described as if it were implemented by a single computer device. However, the information processing device 10 is not necessarily limited to being implemented by a single computer device, as long as it can perform similar functions. The information processing device 10 may be implemented by, for example, a plurality of computer devices that can communicate with each other.

[0386] (2) In Embodiment 1, the control parameter optimization system 1 was described as having the following configuration: (i) the sensor 30 measures physical quantities related to the movement of the object to be driven and outputs measurement data related to the movement of the object to be driven 24 to the information processing device 10, and (ii) the input unit 11 acquires the measurement data output from the sensor 30.

[0387] However, the above configuration of the control parameter optimization system 1 is just one example, and the control parameter optimization system 1 is not necessarily limited to the above configuration as long as the input unit 11 can acquire measurement data related to the movement of the driven object 24.

[0388] For example, if the drive unit 23 is a servo motor, the servo motor has a built-in sensor that detects the motor position (for example, if the servo motor is a rotary motor, the rotational position of the servo motor). The servo motor then outputs an encoded value indicating the position of the servo motor detected by the built-in sensor.

[0389] Generally, sensors that detect the position of a motor are also called encoders. Furthermore, servo motors typically have a built-in encoder.

[0390] Here, the position of the servo motor represented by this encoded value has a one-to-one correspondence with the position of the object to be driven 24. Therefore, the encoded value output by the drive unit 23, which is a servo motor, represents not only the position of the servo motor but also the position of the object to be driven 24. Thus, it can be said that the sensor built into the servo motor also detects the position of the object to be driven 24 and outputs an encoded value that represents the position of the object to be driven 24.

[0391] The input unit 11 may also acquire the encoded value output from the drive unit 23, which is a servo motor, as measurement data.

[0392] (3) The comprehensive or specific aspects of the Disclosure may be implemented as a system, apparatus, method, integrated circuit, program, or a non-temporary recording medium such as a computer-readable CD-ROM. Alternatively, they may be implemented in any combination of a system, apparatus, method, integrated circuit, program, and non-temporary recording medium. For example, the Disclosure may be implemented as a program causing a computer device to perform processing performed by the information processing apparatus 10, the information processing apparatus 10A, or the information processing apparatus 10B. [Industrial applicability]

[0393] This disclosure can be widely used in systems for optimizing control parameters, etc. [Explanation of Symbols]

[0394] 1, 1A, 1B Control Parameter Optimization System 10, 10A, 10B Information Processing Devices 11, 11A input section 12 Output section 13, 13A, 13B Control Unit 14 Machine Learning Models 15 Operation reception unit 16, 16B generation section 17 Display section 18, 18A, 18B Information Processing Unit 19, 19A, 19B Acquisition Department 20 equipment 21 Memory section 22 Control Unit 23 Drive unit 24 Driven object 30 sensors 30A Sensor with Processing Unit

Claims

1. An information processing method for optimizing control parameters in a device that performs an operation based on control parameters, The information processing unit, At a first time point, the device is made to perform a first operation to acquire first measurement data relating to the movement of the device. At a second time point, later than the first time point, the device is made to perform the first operation to obtain second measurement data relating to the movement of the device. Based on the first measurement data and the second measurement data, an environmental change degree is calculated, indicating the degree to which the environment related to the device has changed between the first time and the second time. Based on the environmental change degree, a decision is made as to whether or not to display an image based on the first measurement data and the second measurement data on the display unit. Information processing methods.

2. The aforementioned information processing unit, When it is determined that the aforementioned display image should be displayed on the display unit, The system generates a display image that includes an image showing the degree of environmental change, and displays the display image on the display unit. The information processing method according to claim 1.

3. The aforementioned information processing unit, By performing the first operation with similar control parameters, the first measurement data and the second measurement data are obtained. The information processing method according to claim 1.

4. The aforementioned information processing unit, When the degree of environmental change is greater than the first threshold, the system generates a display image that includes at least one of the following images: an image related to an inquiry about whether to review the installation status of the device, an image related to an inquiry about whether to continue optimizing the control parameters, an image related to an inquiry about whether to restart the optimization from the beginning, and an image related to an inquiry about whether to change the algorithm used for the optimization. The information processing method according to claim 2.

5. The aforementioned information processing unit, Furthermore, at each of the one or more time points after the second time point, the device is made to perform the first operation to acquire one or more measurement data related to the movement of the device. Based on the above one or more measurement data, the display image is generated. The information processing method according to claim 2.

6. The aforementioned information processing unit, Furthermore, the degree of environmental change is calculated based on the above one or more measurement data. The information processing method according to claim 5.

7. The aforementioned information processing unit, Furthermore, the operation count information, which indicates the number of times the device is instructed to perform the first operation after the second time, is acquired from the operation reception unit. At each of the one or more time intervals indicated by the operation count information, the device is made to perform the first operation, and measurement data relating to the operation of the device is obtained for each of the one or more time intervals indicated by the operation count information. The information processing method according to claim 5 or claim 6.

8. The information processing unit generates the display image which includes a first measurement image relating to the first measurement data and a second measurement image relating to the second measurement data. The information processing method according to claim 2.

9. The aforementioned information processing unit, Furthermore, based on the first measurement data, a first evaluation index data is calculated based on an evaluation index related to the operation of the device, and based on the second measurement data, a second evaluation index data is calculated based on the evaluation index. A first measurement image showing the first evaluation index data and a second measurement image showing the second evaluation index data are generated. The information processing method according to claim 8.

10. The first measurement data and the second measurement data are time-series data. The information processing unit generates the display image which includes a first measurement image showing the time-series waveform of the first measurement data and a second measurement image showing the time-series waveform of the second measurement data. The information processing method according to claim 8 or claim 9.

11. The information processing unit generates the display image by superimposing the first measurement image and the second measurement image. The information processing method according to claim 10.

12. The aforementioned information processing unit, Furthermore, based on the first measurement data, a first evaluation index data is calculated based on an evaluation index related to the operation of the device; based on the second measurement data, a second evaluation index data is calculated based on the evaluation index; and based on one or more measurement data, one or more evaluation index data is calculated based on the evaluation index. If, among the second evaluation index data and the one or more evaluation index data, there is one or more evaluation index data with a difference greater than the second threshold between it and the first evaluation index data, the display image is generated which includes an image relating to one or more measurement data with a difference corresponding to that one or more evaluation index data with a difference. The information processing method according to claim 5 or claim 6.

13. The information processing unit further acquires the second threshold value input to the operation reception unit. The information processing method according to claim 12.

14. The aforementioned information processing unit, Furthermore, at the first time, at least one of the following is acquired: a first temperature in the environment in which the device is installed, a first humidity, and first operating status information relating to the operating status of an external device. Furthermore, at the second time, at least one of the following is acquired: a second temperature in the environment in which the device is installed, a second humidity, and second operating status information relating to the operating status of the external device. The display image is generated, which includes an image showing at least one of the first temperature, the first humidity, and the operating status of the external device as indicated by the first operating status information, and an image showing at least one of the second temperature, the second humidity, and the operating status of the external device as indicated by the second operating status information. The information processing method according to claim 2.

15. If the information processing unit interrupts the process for optimizing the control parameters at a third time, which is after the first time and before the second time, and resumes the interrupted process at a fourth time, which is after the third time and before the second time, it generates the display image which includes an image showing the time difference between the third time and the fourth time. The information processing method according to claim 2.

16. The aforementioned information processing unit, Furthermore, at a fifth time that is after the first time but before the second time, the device is made to perform the first operation, or an additional operation which is a third operation different from the first operation, to acquire third measurement data related to the movement of the device. Furthermore, at a sixth time after the second time, the device is made to perform the additional operation to acquire a fourth measurement data relating to the movement of the device. Based on the third measurement data and the fourth measurement data, the display image is generated. The information processing method according to claim 2.

17. The aforementioned information processing unit, Furthermore, based on the third and fourth measurement data, the degree of environmental change, which indicates the degree to which the environment related to the device has changed between the fifth time and the second time, is calculated. The information processing method according to claim 16.

18. The aforementioned information processing unit, Furthermore, based on the progress of the optimization of the control parameters, a recommended optimization algorithm suitable for the algorithm used for the optimization is identified. The display image includes an image showing the recommended optimization algorithm. The information processing method according to claim 2.

19. An information processing device for optimizing control parameters in a device that performs an operation based on control parameters, At a first time point, the device is made to perform a first operation to acquire first measurement data relating to the movement of the device. An acquisition unit that causes the device to perform the first operation at a second time after the first time and acquires second measurement data relating to the movement of the device, The system includes a control unit that calculates an environmental change degree, which indicates the degree to which the environment related to the device has changed between the first time and the second time, based on the first measurement data and the second measurement data, and that determines whether or not to display a display image based on the first measurement data and the second measurement data on the display unit based on the environmental change degree. Information processing device.

20. A program that causes an information processing device to perform processing for optimizing the control parameters in a device that performs operation based on control parameters, The aforementioned process is, At a first time point, the device is made to perform a first operation to acquire first measurement data relating to the movement of the device. At a second time point, later than the first time point, the device is made to perform the first operation to obtain second measurement data relating to the movement of the device. This process involves calculating an environmental change degree, which indicates the degree to which the environment related to the device has changed between the first time and the second time, based on the first measurement data and the second measurement data; and determining whether or not to display an image based on the first measurement data and the second measurement data on the display unit, based on the environmental change degree. program.

Images