Parameter automatic adjustment device and parameter automatic adjustment method

Abstract

To provide a technique for efficiently and automatically searching for control parameters for equipment.SOLUTION: A parameter automatic adjustment device according to one aspect comprises: a plurality of equipment models obtained by modeling equipment; a control parameter setting unit which sets a plurality of first control parameters used in a first trial in the plurality of equipment models and second control parameters used in the first trial in the equipment; and a comparison unit which compares the model operation results in the first trial of the plurality of equipment models by the plurality of first control parameters with actual machine operation results in the first trial of the equipment by the second control parameters. The control parameter setting unit selects control parameters used in the second trial on the basis of the first comparison results between the model operation results in the first trial and the actual machine operation results in the first trial.SELECTED DRAWING: Figure 2

Description

[Technical Field]

[0001] The present disclosure relates to an automatic parameter adjustment device, an automatic parameter adjustment system, and an automatic parameter adjustment method. [Background technology]

[0002] Production equipment used in factories, such as component mounters and assembly robots, combines multiple servo-controlled motors to perform complex and sophisticated motion control. In such devices, the operation of the controlled object is controlled according to a large number of control parameters. To achieve the desired performance, users adjust the control parameters empirically.

[0003] The process of adjusting these control parameters becomes more difficult as the operating conditions become more diverse and complex, and the number of parameters increases, requiring a great deal of time and effort. Therefore, there is a growing demand for automating this adjustment process.

[0004] For this reason, a technique has been disclosed for modeling the production equipment to be controlled and extracting candidate parameters to be adjusted using a simulation. [Prior art documents] [Patent documents]

[0005] [Patent Document 1] Japanese Patent Application Laid-Open No. 2017-102619 Summary of the Invention [Problem to be solved by the invention]

[0006] However, when the number of control parameters reaches several tens or even several hundreds, the number of combinations becomes enormous, and it takes a very long time to sequentially perform parameter optimization by simulation and optimization by an actual device.

[0007] Furthermore, if the operating range of the actual equipment is limited to a narrower range than the candidate control parameters extracted by simulation, the equipment will not be robust against disturbances due to the installation environment of the actual equipment, and it may be difficult to converge to the optimal value. For example, modeling errors in the equipment model and evaluation errors in the actual equipment may make it difficult to find appropriate control parameters.

[0008] The present disclosure contributes to providing a technique for efficiently and automatically searching for control parameters for equipment. [Means for solving the problem]

[0009] One aspect of the present disclosure relates to an automatic parameter adjusting device including: a plurality of equipment models that model equipment; a control parameter setting unit that sets a plurality of first control parameters to be used in a first trial for the plurality of equipment models and sets a second control parameter to be used in the first trial for the equipment; and a comparison unit that compares model operation results in the first trial of the plurality of equipment models using the plurality of first control parameters with actual operation results of the equipment using the second control parameters, wherein the control parameter setting unit selects control parameters to be used in a second trial based on a first comparison result between the model operation results in the first trial and the actual operation results in the first trial. Another aspect of the present disclosure relates to a computer-implemented automatic parameter adjustment method, including setting a plurality of first control parameters to be used in a first trial for a plurality of equipment models that model equipment, and setting a second control parameter to be used in the first trial for the equipment; comparing model operation results for the plurality of equipment models in the first trial using the plurality of first control parameters with actual operation results for the equipment in the first trial using the second control parameters; and selecting control parameters to be used in a second trial based on a first comparison result between the model operation results for the first trial and the actual operation results for the first trial.

[0010] These comprehensive or specific aspects may be realized as a system, a method, an integrated circuit, a computer program, or a recording medium, or may be realized as any combination of a system, an apparatus, a method, an integrated circuit, a computer program, and a recording medium. [Effects of the Invention]

[0011] According to the above-described aspects of the present disclosure, a technique for efficiently and automatically searching for control parameters for equipment can be provided.

[0012] Further advantages and benefits of certain aspects of the present disclosure will become apparent from the specification and drawings. Such advantages and / or benefits may be provided by some embodiments and features described in the specification and drawings, respectively, but not necessarily all, to obtain one or more identical features. [Brief explanation of the drawings]

[0013] [Figure 1] FIG. 1 is a configuration diagram illustrating an example of an automatic parameter adjustment system according to an embodiment of the present disclosure. [Figure 2] FIG. 1 is a diagram illustrating a functional configuration of an automatic parameter adjustment device according to an embodiment of the present disclosure. [Figure 3] FIG. 1 is a diagram illustrating a hardware configuration of an automatic parameter adjustment device according to an embodiment of the present disclosure. [Figure 4] FIG. 2 is a diagram illustrating an example of a data configuration of an operating condition parameter according to an embodiment of the present disclosure. [Figure 5] FIG. 2 is a diagram illustrating an example of a data configuration of a control condition parameter according to an embodiment of the present disclosure. [Figure 6] FIG. 10 is a diagram illustrating an example of an operation sequence of the automatic parameter adjustment system according to an embodiment of the present disclosure. [Figure 7] 10 is a flowchart illustrating an example of an automatic parameter adjustment process according to an embodiment of the present disclosure. [Figure 8] FIG. 10 is a diagram illustrating an example of a parameter adjustment result display according to an embodiment of the present disclosure. [Figure 9] FIG. 10 is a diagram illustrating an example of a parameter adjustment result display according to an embodiment of the present disclosure. [Figure 10] FIG. 10 is a diagram illustrating an example of a parameter adjustment result display according to an embodiment of the present disclosure. DETAILED DESCRIPTION OF THE INVENTION

[0014] Hereinafter, embodiments of the present disclosure will be described in detail with reference to the drawings. Note that the embodiments described below are merely examples, and the present disclosure is not limited to the following embodiments.

[0015] Hereinafter, embodiments of the present disclosure will be described in detail with reference to the accompanying drawings. However, unnecessary detailed description may be omitted. For example, detailed description of well-known matters and redundant description of substantially identical configurations may be omitted. This is to avoid unnecessary redundancy in the following description and to facilitate understanding by those skilled in the art.

[0016] The accompanying drawings and the following description are provided to enable those skilled in the art to fully understand the present disclosure, and are not intended to limit the subject matter described in the claims.

[0017] First, an automatic parameter adjustment system according to an embodiment of the present disclosure will be described with reference to Fig. 1. Fig. 1 shows an example of an automatic parameter adjustment system according to an embodiment of the present disclosure.

[0018] 1, the automatic parameter adjustment system 100 includes a user interface (UI) unit 101, an automatic parameter adjustment device 102, equipment 103, and a sensor 104. The automatic parameter adjustment system 100 adjusts control parameters so that a predetermined operation of the equipment 103, such as a component mounter, satisfies predetermined performance (for example, position accuracy, settling time, vibration, noise, power consumption, etc.).

[0019] The UI unit 101 is realized by UI devices such as a display, keyboard, and mouse, and receives adjustment items (for example, operating conditions, desired performance, priority parameters, etc.) from a user and passes the received adjustment items to the automatic parameter adjustment device 102.

[0020] As will be described in more detail below, the automatic parameter adjusting device 102 determines a search range for control parameters for the equipment 103 based on the adjustment items received from the user, and outputs candidate control parameters.

[0021] The equipment 103 is a mounting machine such as a production facility, and performs a predetermined operation based on the control parameters set by the automatic parameter adjusting device 102 .

[0022] Sensor 104 detects the operation results (for example, performance values ​​related to the operation) of equipment 103 operating according to set control parameters, and passes the operation results to automatic parameter adjusting device 102 .

[0023] The automatic parameter adjusting device 102 then evaluates the set control parameters based on the performance values ​​acquired from the sensors, and determines the next control parameters to be set in the equipment 103 based on the evaluation results. In this way, the automatic parameter adjusting device 102 repeats the above-mentioned control parameter adjustment process to optimize the control parameters (this series of operations is called a trial). The automatic parameter adjusting device 102 also displays the adjustment status of the control parameters to the user via the UI unit 101.

[0024] In this way, the automatic parameter adjustment system 100 presents the control parameters that have achieved the desired performance to the user as adjustment results, and sets them in the equipment 103.

[0025] Note that the illustrated blocks may be implemented in a single device or in different devices. For example, the facility 103 may be implemented as a single device including the UI unit 101, the automatic parameter adjusting device 102, and the sensor 104. Alternatively, the automatic parameter adjusting device 102 may be realized on the cloud, and the UI unit 101 may be implemented on a user's local PC (Personal Computer), smartphone, tablet, or the like, with the respective blocks being connected via a communication network (not shown). Furthermore, a plurality of facilities 103 and / or sensors 104 may be installed.

[0026] Furthermore, the UI unit 101 and / or the automatic parameter adjusting device 102 may not only set adjustment items input by a user, but also operate the GUI (Graphical User Interface) of existing adjustment software for manually adjusting the parameters of the conventional equipment 103 using RPA (Robotic Process Automation) that automatically controls the software using image recognition or the like, thereby setting control parameters and obtaining operation results. This makes it possible to perform automatic parameter adjustment even for conventional equipment 103 that does not have a dedicated communication interface.

[0027] Next, the automatic parameter adjusting device 102 according to an embodiment of the present disclosure will be described with reference to Figures 2 and 3. Figure 2 shows an example of the functional configuration of the automatic parameter adjusting device 102 according to an embodiment of the present disclosure.

[0028] As shown in FIG. 2, automatic parameter adjusting device 102 includes a parallel search unit 201, an actual machine parameter search unit 202, a control parameter setting unit 203, an equipment model 204, a comparison unit 205, and a model update unit 206.

[0029] The parallel search unit 201 uses a plurality of equipment models 204 of the equipment 103 to perform an operation simulation of the equipment 103 and search for control parameters. Specifically, the parallel search unit 201 searches for a combination of control parameters that will achieve desired performance based on the constraints of the adjustment items set via the UI unit 101, and outputs candidate control parameters to the control parameter setting unit 203. For example, the selection of candidate control parameters may be performed based on the simulation results output from the equipment models 204.

[0030] The actual machine parameter search unit 202 causes the equipment 103 to perform a physical operation and searches for control parameters based on the results of the actual machine operation. Specifically, the actual machine parameter search unit 202 searches for a combination of control parameters that will achieve desired performance based on the constraints of the adjustment items set via the UI unit 101, and outputs candidate control parameters to the control parameter setting unit 203. For example, the selection of candidate control parameters may be performed based on the results of the actual machine operation detected by the sensor 104.

[0031] The control parameter setting unit 203 selects trial control parameters from the plurality of candidate parameters acquired from the parallel search unit 201 and the actual machine parameter search unit 202, and sets the selected control parameters for the equipment model 204 and the equipment 103. For example, the selection of the control parameters may be performed based on the output result of the comparison unit 205.

[0032] The multiple equipment models 204 are configured by modeling the operation of the equipment 103 and are capable of performing simulations. The same or different control parameters may be set for each equipment model 204. The multiple equipment models 204 may be the same or different. Various methods can be used to model the operation of the equipment 103. For example, the equipment model 204 may be based on a mathematical model using transfer functions and / or differential equations, a structural analysis model using a CAD model, a multiphysics model, a multibody dynamics model, etc. Performance indicators such as operating time, movement accuracy, and vibration can be simulated using the equipment model 204. Alternatively, the equipment model 204 may be based on a machine learning model that predicts and outputs the actual operation results of the equipment 103 based on input parameters. Alternatively, the equipment model 204 may be a hybrid model that combines these. Various known machine learning methods may be applied. For example, the equipment model 204 may be a hybrid model that combines these. Deep learning using a neural network that generates time series patterns by applying various known machine learning methods may also be used. Alternatively, multiple equipment models 204 may be prepared and simulations of these equipment models 204 may be executed in parallel, which allows multiple control parameters and / or constraints to be evaluated simultaneously, thereby reducing the search time for control parameters.

[0033] The comparison unit 205 compares the model operation results of the equipment model 204 with the actual operation results output from the sensor 104. Specifically, the comparison unit 205 compares the operation results of the equipment model 204 for the control parameters set by the control parameter setting unit 203 with the operation results of the equipment 103, and selects control parameters for the next trial and determines whether to update the equipment model 204. An output related to the selection of control parameters is notified to the control parameter setting unit 203, and an output related to the update of the equipment model is notified to the model update unit 206.

[0034] The model update unit 206 updates the equipment model 204 based on the output from the comparison unit 205. Specifically, the model update unit 206 adjusts the internal parameters of the equipment model 204 so that the operation with the same control parameters substantially matches that of the equipment 103. In this way, the model update unit 206 reflects the operation of the equipment model 204 in the actual installation environment of the equipment 103, individual differences, etc., and can improve the accuracy and efficiency of control parameter search.

[0035] For example, the status of each of these internal blocks may be output to the UI unit 101 as an adjustment status and notified to the user.

[0036] Note that various known algorithms can be used for parameter search, such as heuristic algorithms such as Bayesian optimization, genetic algorithms, and particle swarm optimization, mathematical programming, and various solution methods in combinatorial optimization.

[0037] Furthermore, information about the search space may be shared between the parallel search unit 201 and the actual machine parameter search unit 202. For example, current search range information, past search history, and the like may be exchanged.

[0038] Here, the automatic parameter adjusting device 102 is realized by any computing device such as a server or a personal computer, and may have a hardware configuration such as that shown in Fig. 3. For example, the automatic parameter adjusting device 102 includes a storage device 111, a processor 112, a user interface (UI) device 113, and a communication device 114, which are interconnected via a bus B.

[0039] The programs or instructions that implement the various functions and processes of the automatic parameter adjusting device 102, which will be described later, may be downloaded from an external device via a network or the like, or may be provided from a removable storage medium such as a CD-ROM (Compact Disk-Read Only Memory) or flash memory. The storage device 111 is implemented by a random access memory, flash memory, hard disk drive, or the like, and stores installed programs or instructions as well as files, data, and the like used to execute the programs or instructions. The storage device 111 may include a non-transitory storage medium.

[0040] The processor 112 may be realized by one or more central processing units (CPUs), graphics processing units (GPUs), processing circuitry, etc., each of which may be composed of one or more processor cores, and performs various functions and processes of the automatic parameter adjustment device 102 (described below) in accordance with programs, instructions, and data such as parameters used to execute the programs or instructions stored in the storage device 111. The user interface (UI) device 113 may be composed of input devices such as a keyboard, mouse, camera, and microphone, output devices such as a display, speaker, headset, and printer, and input / output devices such as a touch panel, and provides an interface between a user and the automatic parameter adjustment device 102. For example, a user operates a graphical user interface (GUI) displayed on a display or touch panel using a keyboard, mouse, etc. to operate the automatic parameter adjustment device 102. The communication device 114 is realized by various communication circuits that execute communication processes with external devices and communication networks such as the Internet and a local area network (LAN).

[0041] However, the above-described hardware configuration is merely an example, and the automatic parameter adjusting device 102 according to the present disclosure may be realized by any other appropriate hardware configuration.

[0042] Next, adjustment items according to an embodiment of the present disclosure will be described with reference to Figures 4 and 5. Figure 4 shows an example of the data configuration of adjustment items of the operating condition parameters 301 according to an embodiment of the present disclosure, and Figure 5 shows an example of the data configuration of adjustment items of the control condition parameters 302 according to an embodiment of the present disclosure. Note that the illustrated adjustment items are merely examples, and appropriate adjustment items may be set depending on the equipment 103 to be set.

[0043] 4 and 5, the adjustment items consist of M operating conditions, and parameters are set for each operating condition. The operating conditions here refer to operating patterns broken down into partial operations, such as arm operation and component mounting operation.

[0044] The operating condition parameters 301 define the desired operation of the equipment 103, and in the illustrated embodiment, are composed of C condition parameters and T target performance parameters. The condition parameters may be, for example, a movement direction, a movement distance, an acceleration time, an acceleration limit value, etc. The target performance parameters may be, for example, a positioning settling time, a position error, an amount of overshoot such as vibration, etc.

[0045] The control condition parameters 302 define the setting range of the control parameters of the equipment 103, and in the illustrated embodiment, are composed of P control parameters and T performance weight parameters. The control parameters may be, for example, numerical data such as the resonant frequency, time constant, and control gain of the control filter, or a set of settable ranges, setting units (steps), and discrete value sets for the equipment 103, such as categorical data such as filter configuration mode settings. The performance weight parameters may, for example, set how much weight to assign to each item of the target performance in the evaluation.

[0046] Control parameters selected from these input data are set for the equipment model 204 and the equipment 103, and a predetermined operation is executed based on the set control parameters. Then, the performance values ​​of the operation results are measured.

[0047] The evaluation parameter 303 is an evaluation value used in parameter search, and is a value obtained by weighting each output result when control parameters are set for M operating conditions with a performance weight parameter. For example, if target performance is satisfied under all operating conditions, the weights for all parameters are set equally. On the other hand, if operating conditions are prioritized or desired performance is prioritized for each operating condition, the evaluation value may be calculated by adjusting the weights. The evaluation value may also be a value obtained by converting the weighted output result using an evaluation value function. The evaluation value function may, for example, simply calculate the sum of the weighted output results, or may be a function that sums the results converted into the degree of achievement (proportion) of the output result relative to the target performance. In this case, depending on the setting of the evaluation function, the search algorithm may be set to search for control parameters that minimize or maximize the evaluation value.

[0048] Next, the operation of the automatic parameter adjustment system 100 according to an embodiment of the present disclosure will be described with reference to Fig. 6. Fig. 6 shows an example of an operation sequence of the automatic parameter adjustment system 100 according to an embodiment of the present disclosure.

[0049] As shown in FIG. 6, in step S401, the UI unit 101 transmits the adjustment items set by the user to the parallel search unit 201 and the actual machine parameter search unit 202.

[0050] In step S402, the parallel search unit 201 selects multiple candidate parameters A for the equipment model 204 from a search space set based on the adjustment items, and transmits the selected multiple candidate parameters A to the control parameter setting unit 203. For example, different combinations of candidate parameters may be provided simultaneously (in parallel) for each of the multiple equipment models 204 as the candidate parameters A.

[0051] In step S403, the actual machine parameter search unit 202 selects multiple candidate parameters B for the equipment 103 from a search space set based on the adjustment items, and transmits the selected multiple candidate parameters B to the control parameter setting unit 203. For example, a combination of different candidate parameters may be sequentially (series) provided to one equipment 103 as candidate parameters B.

[0052] In step S404, the control parameter setting unit 203 selects trial parameters to be set for each equipment model 204 from the candidate parameters A and B, and transmits the selected trial parameters to each equipment model 204. For example, different combinations of trial parameters may be provided simultaneously (in parallel) to each of the multiple equipment models 204 as the trial parameters.

[0053] In step S405, control parameter setting unit 203 selects trial parameters to be set in equipment 103 from candidate parameters A and B, and transmits the selected trial parameters to equipment 103. For example, a combination of different trial parameters may be sequentially (seriesly) provided to one piece of equipment 103 as the trial parameters.

[0054] In step S406, the sensor 104 acquires an actual operation result of the equipment 103 that has operated according to the set trial parameters. The actual operation result indicates the operation of the equipment 103 (e.g., arm movement, etc.), and may indicate, for example, a physical quantity of the equipment 103 detected and / or measured by the sensor 104.

[0055] In step S407, each equipment model 204 executes a simulation according to the set trial parameters, and transmits the results of each model operation to the parallel search unit 201 and the comparison unit 205.

[0056] In step S408 , the sensor 104 transmits the acquired actual machine operation results to the actual machine parameter searching unit 202 and the comparing unit 205 .

[0057] In step S409, the comparison unit 205 compares the model operation result with the actual machine operation result, and transmits parameter switching determination information based on the comparison result to the control parameter setting unit 203. For example, when there is a significant difference between the model evaluation value and the actual machine evaluation value, the parameter switching determination information may instruct the control parameter setting unit to select control parameters that reduce the difference between the model evaluation value and the actual machine evaluation value.

[0058] In step S410, the comparison unit 205 compares the model operation result with the actual machine operation result, and transmits model update determination information based on the comparison result to the model update unit 206. For example, if there is a significant discrepancy between the model evaluation value and the actual machine evaluation value, the model update determination information may instruct the model update unit 206 to update the internal parameters of the equipment model 204 so as to reduce the discrepancy between the model evaluation value and the actual machine evaluation value.

[0059] In step S411, the model update unit 206 transmits model update information to the equipment model 204 based on the model update determination information.

[0060] In step S412, the control parameter setting unit 203 transmits control parameter information to the UI unit 101 based on the candidate parameters A and B and the parameter switching determination information. For example, the control parameter information may indicate the current adjustment progress.

[0061] In step S413, the comparison unit 205 transmits comparison information based on the comparison between the model operation result and the actual machine operation result to the UI unit 101. For example, the comparison information may indicate the current adjustment progress.

[0062] The above-described steps S402 to S413 are repeated until control parameters that satisfy the target performance set by the user are obtained.

[0063] When the control parameters that satisfy the target performance are acquired, in step S414, the control parameter setting unit 203 transmits the adjustment results to the UI unit 101, and the parameter automatic adjustment process ends.

[0064] If the simulation using the equipment model 204 can be executed sufficiently faster than the operation of the actual machine, the parallel search (S402, S403, S404, S407) using the equipment model 204 may be executed multiple times while the actual machine is operating (S406 to S408). Also, multiple trial parameters may be input to the equipment 103 in step S405, and the equipment 103 may execute them sequentially to output multiple actual machine operation results.

[0065] Next, the operation of the automatic parameter adjusting device 102 according to an embodiment of the present disclosure will be described with reference to Fig. 7. Fig. 7 is a flowchart showing the operation of the automatic parameter adjusting device 102 according to an embodiment of the present disclosure.

[0066] As shown in FIG. 7, in step S501, automatic parameter adjusting device 102 receives adjustment items such as operating conditions, target performance, control parameter ranges, and performance evaluation weights from UI unit 101.

[0067] In step S502, the automatic parameter adjusting device 102 causes the parallel search unit 201 and the actual machine parameter search unit 202 to select candidate parameters from the parameter search space in accordance with the set adjustment items.

[0068] In step S503, the automatic parameter adjusting device 102 selects trial parameters from a plurality of candidate parameters.

[0069] In step S504, automatic parameter adjusting device 102 sets the selected trial parameters in equipment model 204 and equipment 103. A simulation of a predetermined operation and an operation of the actual equipment are executed in accordance with the set trial parameters.

[0070] In step S505, automatic parameter adjusting device 102 obtains an evaluation value of the operation result of the simulation of equipment model 204 and the operation result of actual equipment 103.

[0071] In step S506, the automatic parameter adjusting device 102 compares the model evaluation value obtained by the equipment model 204 with the actual equipment evaluation value obtained by the equipment 103. If the multiple model evaluation values ​​are higher than the actual equipment evaluation values ​​by a predetermined difference or more (S506: Y), as shown in FIG. 8, the automatic parameter adjusting device 102 proceeds to S509; otherwise (S506: N), the automatic parameter adjusting device 102 proceeds to S507.

[0072] In step S507, the automatic parameter adjusting device 102 compares the model evaluation value obtained by the equipment model 204 with the actual equipment evaluation value obtained by the equipment 103, and if the multiple model evaluation values ​​are lower than the actual equipment evaluation values ​​by a predetermined difference or more (S507: Y), as shown in FIG. 9, proceeds to S510; otherwise (S507: N), proceeds to S508.

[0073] In step S508, if the model evaluation value of equipment model 204 and the actual equipment evaluation value of equipment 103 are in a state of nearly agreement as shown in FIG. 10 , automatic parameter adjusting device 102 selects the next trial parameters based on the control parameters that yield the best value between the model evaluation value of equipment model 204 and the actual equipment evaluation value of equipment 103, and proceeds to S511.

[0074] In step S509, the automatic parameter adjusting device 102 updates the internal parameters of the equipment model 204 to lower the evaluation value of the equipment model 204 so that the model evaluation value of the equipment model 204 approaches the evaluation value of the actual equipment of the equipment 103. The automatic parameter adjusting device 102 also selects the next trial parameters based on the control parameters that have yielded the model evaluation value closest to the evaluation value of the actual equipment of the equipment 103, and proceeds to S511.

[0075] In step S510, the automatic parameter adjusting device 102 updates the internal parameters of the equipment model 204 to increase the evaluation value of the equipment model 204 so that the model evaluation value of the equipment model 204 approaches the evaluation value of the actual equipment of the equipment 103. The automatic parameter adjusting device 102 also selects the next trial parameters based on the control parameters for which the evaluation value of the actual equipment of the equipment 103 has been obtained, and proceeds to S511.

[0076] In step S511, the automatic parameter adjusting device 102 determines whether the actual machine evaluation value of the equipment 103 has reached the target performance, and if it has reached the target performance (S511: Y), the process proceeds to S512, and if it has not reached the target performance (S511: N), the process proceeds to S502. Note that in FIG. 7, S502 to S511 are trials.

[0077] In step S512, the automatic parameter adjusting device 102 outputs and displays the final adjusted result, and ends the adjustment operation.

[0078] Next, a user interface (UI) display according to an embodiment of the present disclosure will be described with reference to Figures 8 to 10. As described above, the UI unit 101 may include a display device capable of displaying to a user the adjustment process of the parameter adjustment processing in the automatic parameter adjustment system 10.

[0079] 8 shows an example of a parameter adjustment result display according to an embodiment of the present disclosure. As shown in Fig. 8, the UI unit 101 is configured with an adjustment progress graph 601, an operating condition parameter setting area 602, a control condition parameter setting area 603, an evaluation progress setting area 604, and a pointer 605 such as a cursor or touch interface.

[0080] The adjustment progress graph 601 illustrates the progress of evaluation values ​​during parameter adjustment. The adjustment progress graph 601 includes an indicator 6011 showing the direction of high or low performance, a selected vertical axis label 6012 (e.g., an evaluation value using an evaluation function, a specific performance value, etc.), a selected horizontal axis label 6013 (e.g., evaluation time t, number of trials, etc.), model evaluation values ​​6014 for multiple selected trial parameters, actual machine evaluation values ​​6015 for selected trial parameters, and a model update direction 6016.

[0081] When the user clicks or taps in the operating condition parameter setting area 602, the operating condition parameters 301 can be displayed and / or edited. As a graphical user interface (GUI), table editing, value selection using a slider, etc., can be used.

[0082] When the user clicks or taps in the control condition parameter setting area 603, the control condition parameters 302 can be displayed and / or edited. As a GUI, table editing, drop-down menus, value selection using sliders, etc. can be used. In addition, the performance weight parameters can be displayed as a heat map or the like to improve user visibility.

[0083] In the evaluation progress setting area 604, when the user clicks or taps, commands such as starting, pausing, and / or ending automatic adjustment can be issued, and the content to be displayed in the adjustment progress graph 601 can be selected. As a GUI, value selection using a drop-down menu, radio buttons, check boxes, etc. can be used.

[0084] As shown in the figure, if the model evaluation value 6014 is higher than the actual equipment evaluation value 6015 by a predetermined difference or more, the following may be possible: 1. The disturbance components of the equipment 103, etc. are not properly reflected in the equipment model 204, and in simulations, the model evaluation value 6014 tends to exhibit higher performance than the actual equipment evaluation value 6015, or 2. Trial parameters that have the potential to produce higher performance than the trial parameters set for the equipment 103 have been set for the equipment model 204. Therefore, it is possible to display that the equipment model 204 should be updated in a direction (6016) where the output of the equipment model 204 approaches the output of the equipment 103 by adjusting the disturbance components of the equipment model 204, etc. Furthermore, trial parameters that have the potential to produce high performance for the equipment 103 can be selected from the trial parameters of the equipment model 204 and used in the search for the next trial parameters.

[0085] The indicator 6011 indicates which direction the performance is higher depending on the selected vertical axis label 6012. For example, if the position error is selected as the vertical axis, it can be interpreted that the smaller the position error, the higher the performance. Therefore, the indicator 6011 is a downward arrow and the lower label is "High Performance." Alternatively, in the case of evaluation values ​​obtained by weighting multiple performance values ​​and applying them to an evaluation function, if the evaluation function returns a larger evaluation value the higher the performance, the indicator 6011 is an upward arrow and the upper label is "High Performance." This allows the user to easily recognize the quality of performance without misunderstanding the meaning of the graph. Furthermore, the indicator 6011 can be flipped upside down by clicking, and the graph can also be displayed upside down accordingly. This allows the evaluation values ​​and performance values ​​to be displayed according to the user's preferences.

[0086] Furthermore, when the pointer 605 is placed on, clicked on, or tapped on the line segment of the model evaluation value 6014, the actual device evaluation value 6015, and / or the model update direction 6016, the related control parameter values, etc. may be displayed in a pop-up or the like.

[0087] 9 shows an example of a parameter adjustment result display according to an embodiment of the present disclosure. In the example shown in FIG. 9, an example of a state in which a model evaluation value 6014 is lower than an actual device evaluation value 6015 is shown.

[0088] If the model evaluation value 6014 is lower than the actual equipment evaluation value 6015 by a predetermined difference or more, the following may be possible: 1. The sensitivity, etc. of the equipment 103 is not reflected in the equipment model 204, and in simulations, the model evaluation value 6014 tends to show lower performance than the actual equipment evaluation value 6015, or 2. The trial parameters set for the equipment 103 are showing higher performance than the trial parameters of the equipment model 204. Therefore, by adjusting the sensitivity, etc. of the equipment model 204, it is possible to display that the equipment model 204 is updated in a direction (6016) such that the output of the equipment model 204 approaches the output of the equipment 103. Furthermore, since trial parameters that have shown high performance have been set for the equipment 103, these can be continued and used in the search for the next trial parameters.

[0089] 10 shows an example of a parameter adjustment result display according to an embodiment of the present disclosure. In the example shown in Fig. 10, an example of a state in which a model evaluation value 6014 and an actual device evaluation value 6015 are almost identical is shown.

[0090] In this case, it can be considered that 1. the operation results of the equipment model 204 and the equipment 103 are nearly identical for the same control parameters, and 2. the multiple trial parameters set in the equipment model 204 include parameters that have the potential to produce better performance than the parameters set in the equipment 103. Therefore, the next trial parameter search can be performed based on the control parameters that yielded the best value out of the model evaluation value 6014 and the actual equipment evaluation value 6015. Furthermore, for trial parameters that yielded a model evaluation value 6014 that is lower than the actual equipment evaluation value 6015, pruning or setting a different search space may be performed to improve the efficiency of the parallel search by the equipment model 204.

[0091] According to the above-described embodiment of the present disclosure, when multiple evaluation values ​​of equipment model 204 of parameter automatic adjustment system 100 are higher than those of the actual equipment, the equipment model 204 is updated by adjusting the disturbance components, etc. of equipment model 204 so that the output of equipment model 204 approaches the output of the actual equipment. Furthermore, trial parameters that are likely to produce high performance for the equipment 103 are selected from the trial parameters of equipment model 204 and used in the search for the next trial parameters. On the other hand, when multiple evaluation values ​​of equipment model 204 are lower than those of the actual equipment, the equipment model 204 is updated by adjusting the sensitivity, etc. of equipment model 204 so that the output of equipment model 204 approaches the output of the actual equipment. Furthermore, the trial parameters set for the equipment 103 are continued and used in the search for the next trial parameters. When the model evaluation value and the actual equipment evaluation value approximately match, the next trial parameters can be searched for based on the control parameters that yielded the best value between the model evaluation value and the actual equipment evaluation value. Furthermore, for trial parameters for which a model evaluation value lower than the actual equipment evaluation value is obtained, pruning or setting a different search space can be performed to improve the efficiency of parallel search by the equipment model 204.

[0092] In this way, a search for multiple operating conditions can be efficiently performed through a parallel search using multiple equipment models 204. Modeling errors can be corrected while continuing the time-consuming parameter search performed while operating the actual equipment. If the modeling errors become smaller, the search range can be narrowed based on the parameter search results using the actual equipment, thereby reducing the adjustment time and presenting the adjustment process to the user.

[0093] In the above-described embodiments, the notation "... part" used for each component may be replaced with other notations such as "... circuitry," "... assembly," "... device," "... unit," or "... module."

[0094] Although the embodiments have been described above with reference to the drawings, the present disclosure is not limited to such examples. It is clear that a person skilled in the art can conceive of various modifications or alterations within the scope of the claims. It is understood that such modifications or alterations also fall within the technical scope of the present disclosure. Furthermore, the components in the embodiments may be combined in any manner without departing from the spirit of the present disclosure.

[0095] The present disclosure can be realized by software, hardware, or software linked to hardware. Each functional block used in the description of the above embodiments may be realized, in part or in whole, as an LSI, which is an integrated circuit, and each process described in the above embodiments may be controlled, in part or in whole, by a single LSI or a combination of LSIs. The LSI may be composed of individual chips, or may be composed of a single chip that includes some or all of the functional blocks. The LSI may have data input and output. Depending on the degree of integration, the LSI may be called an IC, system LSI, super LSI, or ultra LSI.

[0096] The integrated circuit method is not limited to LSI, and may be realized as a dedicated circuit, a general-purpose processor, or a dedicated processor. Also, a field programmable gate array (FPGA) that can be programmed after LSI manufacturing, or a reconfigurable processor that can reconfigure the connections and / or settings of circuit cells within the LSI, may be used. The present disclosure may be realized as digital processing or analog processing.

[0097] Furthermore, if an integrated circuit technology that can replace LSI emerges due to advances in semiconductor technology or other derivative technologies, it is natural that such technology may be used to integrate functional blocks. The application of biotechnology, etc. is also a possibility.

[0098] In addition, the following supplementary notes are provided in relation to the above description. (Appendix 1) a plurality of equipment models that model the equipment; a control parameter setting unit that sets a plurality of first control parameters to be used in a first trial for the plurality of equipment models and sets a second control parameter to be used in the first trial for the equipment; a comparison unit that compares model operation results in the first trial of the plurality of equipment models using the plurality of first control parameters with actual operation results in the first trial of the equipment using the second control parameters; and The control parameter setting unit selects control parameters to be used in a second trial based on a first comparison result between a model operation result in the first trial and an actual operation result in the first trial. (Appendix 2) 2. The automatic parameter adjusting device according to claim 1, further comprising a model updating unit that updates the plurality of equipment models based on a result of the first comparison. (Appendix 3) the comparison unit compares a plurality of model evaluation values ​​indicating model operation results in the first trial with an actual machine evaluation value indicating an actual machine operation result in the first trial; When the plurality of model evaluation values ​​are higher than the actual device evaluation value by a predetermined first difference or more, the model update unit updates the plurality of equipment models so that the plurality of model evaluation values ​​approach the actual equipment evaluation value; 3. The automatic parameter adjusting device according to claim 2, wherein the control parameter setting unit selects the control parameters to be used in the second trial based on the first control parameters corresponding to the model evaluation value that is closest to the actual machine evaluation value. (Appendix 4) When the plurality of model evaluation values ​​are lower than the actual device evaluation value by a predetermined second difference or more, the model update unit updates the plurality of equipment models so that the plurality of model evaluation values ​​approach the actual equipment evaluation value; 4. The automatic parameter adjusting device according to claim 3, wherein the control parameter setting unit selects a control parameter to be used in the second trial based on the second control parameter. (Appendix 5) the control parameter setting unit selects control parameters to be used in the second trial based on the best value of the model evaluation values ​​and the actual machine evaluation values ​​when the model evaluation values ​​are not higher than the actual machine evaluation values ​​by a predetermined first difference or more and the model evaluation values ​​are not lower than the actual machine evaluation values ​​by a predetermined second difference or more. (Appendix 6) An automatic parameter adjusting device according to any one of Supplementary Notes 1 to 5; a display device that displays the model operation result in the first trial and the actual machine operation result in the first trial; A parameter automatic adjustment system having the above. (Appendix 7) setting a plurality of first control parameters to be used in a first trial for a plurality of equipment models obtained by modeling the equipment, and setting a second control parameter to be used in the first trial for the equipment; comparing model operation results of the plurality of equipment models in the first trial using the plurality of first control parameters with actual operation results of the equipment in the first trial using the second control parameters; selecting control parameters to be used in a second trial based on a first comparison result between the model operation result in the first trial and the actual operation result in the first trial; A computer-implemented method for automatically adjusting parameters, comprising:

[0099] The disclosures of the specification, drawings and abstract contained in Japanese Patent Application No. 2021-184816, filed on November 12, 2021, are incorporated herein by reference in their entirety. [Industrial Applicability]

[0100] One aspect of the present disclosure is useful in an automatic parameter adjustment system. [Explanation of symbols]

[0101] 100 Parameter Auto-tuning System 101 User Interface (UI) Section 102 Parameter automatic adjustment section 103 Equipment 104 Sensors 201 Parallel search section 202 Actual Machine Parameter Search Section 203 Control parameter setting section 204 Equipment Model 205 Comparison Section 206 Model Update Department

Claims

1. The computer a first step of performing parallel simulations using different control parameters for a plurality of identical equipment models that model the entire equipment, and obtaining an evaluation value for each of the equipment models; a second step of updating the value of the control parameter based on the evaluation value; Run adjusting the control parameters by repeating the first step and the second step; method.

2. Setting initial control parameter values ​​based on the items set by the user; The method of claim 1.

3. Setting the adjusted control parameters in the equipment. The method of claim 1.

4. updating the control parameters to values ​​that provide desired performance based on adjustment items set by a user; The method of claim 1.

5. Searching for values ​​of the control parameters that satisfy the constraints of the adjustment items set by the user and maximize or minimize an evaluation value function that indicates the degree of achievement of the target performance; The method of claim 1.

6. displaying the evaluation value obtained in the first step to a user; The method of claim 1.

7. comparing model operation results of the plurality of equipment models according to the control parameters with actual operation results of the equipment operated according to the control parameters; The method of claim 3.

8. A processor and a memory are included, the processor: a first step of performing parallel simulations using different control parameters for a plurality of identical equipment models that model the entire equipment, and obtaining an evaluation value for each of the equipment models; a second step of updating the value of the control parameter based on the evaluation value; Run adjusting the control parameters by repeating the first step and the second step; Automatic parameter adjustment device.

9. On the computer, a first step of performing parallel simulations using different control parameters for a plurality of identical equipment models that model the entire equipment, and obtaining an evaluation value for each of the equipment models; a second step of updating the value of the control parameter based on the evaluation value; a step of adjusting the control parameters by repeating the first step and the second step; An information processing program that executes the above.

Images