PARAMETERIZATION DEVICE AND COMPUTER-READABLE RECORDING MEDIUM

Abstract

A parameterization device according to the present disclosure is provided with a simulation unit that simulates an operation of the control target in which the value of a prescribed control parameter is fixed, based on a control target model that models the operation of each unit of a control target; a first search unit that performs simulation processing while changing the value of the control parameter within a prescribed first range, and searches for a candidate set of values of the control parameter near the boundary of a prescribed restriction condition based on a first index value calculated from the simulation processing results; a candidate application unit that sets the candidate set of values of the control parameter for the control target, checks the operation of the control target, and calculates a second index value based on the verification results;and a search range determining unit that determines a second range that is narrower than the first range based on the first index value and the second index value;

Description

TECHNICAL FIELD

[0001] The present invention relates to a parameterization device and a computer-readable recording medium. GENERAL STATE OF THE ART

[0002] One method for adjusting a control parameter specified in the control of an industrial machine is to use simulation. In this method, a predetermined first range for the control parameter is first determined, and the simulation is repeatedly performed while varying the value of the control parameter within the first range. Then, based on the simulation results, candidates for an optimal value of the control parameter are extracted. Next, a predetermined second range is determined near each extracted candidate for the value of the control parameter. The machine is then repeatedly operated while varying the control parameter within the second range. Based on the results of this operation, the optimal value of the control parameter is determined (see, for example, Patent Document 1, etc.). LITERATURE LISTPATENT DOCUMENT

[0003] Patent document 1: JP 2017 - 102 619 A SUMMARY OF THE INVENTIONPROBLEM THAT THE INVENTION INTENDED TO SOLVE

[0004] If the search range for a control parameter is narrow, there is a possibility that a suitable control parameter will not be obtained. However, if the search range for the control parameter is wide, a significant amount of time will be required to perform the simulation calculation and the operation using a machine. Especially if the control parameter is adjusted under actual machine operation, this places a significant burden on the operator.

[0005] For this reason, there is a need for a technology that allows appropriate narrowing of the search range for the control parameter. MEANS TO SOLVE THE PROBLEM

[0006] One aspect of the disclosure is a parameterization device that includes a control target model configured to model an operation of each unit provided to an industrial machine serving as a control target, a simulation unit configured to simulate, based on the control target model, an operation of the control target with a predetermined setting value of a control parameter, a first search unit configured to repeatedly perform the simulation process by the simulation unit while changing the value of the control parameter within a predetermined first range, and, based on a first index value calculated from a result of the simulation process, search for a candidate for a set of values of the control parameter that allow a first index value to be obtained near a boundary of a predetermined restriction condition,a candidate application unit that performs an operation check for the control target by setting the set of values of the control parameter serving as the candidate searched by the first search unit, and calculates a second index value based on a result of the operation check; and a search range determination unit configured to determine a second range serving as a range of values narrower than the first range based on the first index value and the second index value. BRIEF DESCRIPTION OF THE DRAWINGS Fig. 1 is a schematic hardware configuration diagram of a parameter setting device according to a first embodiment of the disclosure; Fig. 2 shows functions of the parameterization device according to the first embodiment of the disclosure as a schematic block diagram; Fig. 3 is a flowchart illustrating a schematic processing flow related to the preparation of a search; Fig. 4 is a flowchart illustrating a schematic flow of a first search process; Fig. 5 is a flowchart illustrating a schematic flow of a process for determining a second area; and Fig. Figure 6 is a flowchart illustrating a schematic flow of a second search. MODE(S) FOR CARRYING OUT THE INVENTION

[0007] With reference to the drawings, individual embodiments of the disclosure will be described below. First embodiment

[0008] Fig. 1 is a schematic hardware configuration diagram illustrating a main portion of a parameter setting device according to one embodiment of the disclosure. The parameter setting device 1 according to this embodiment can be implemented, for example, as a controller that controls an industrial machine based on a control program. Furthermore, the parameter setting device 1 can be implemented, for example, as a personal computer attached to the controller that controls the industrial machine, or as another computer such as a computer, a fog computer, or a cloud server connected to the controller via a wired / wireless network. This embodiment shows an example in which the parameter setting device 1 is implemented as a computer connected to a controller that controls an industrial machine 4 via a network 5.

[0009] A CPU 11 provided in the parameter setting device 1 according to this embodiment is a processor that controls the entire parameter setting device 1. The CPU 11 reads a system program stored in a ROM 12 via a bus 22 and controls the entire parameter setting device 1 according to the system program. A RAM 13 temporarily stores calculation data, display data, various externally input data, etc.

[0010] A non-volatile memory 14 includes, for example, a battery-backed memory (not shown), an SSD (solid-state drive), etc., and maintains its storage state even when the power supply of the parameter setting device 1 is turned off. The non-volatile memory 14 stores programs and data read from an external device 72 via an interface 15, programs and data input via an input device 71, programs and data received via the network 5 from the industrial machine 4 or other devices, etc. For example, the stored data may include data related to physical quantities such as a motor current, voltage, torque, position, speed, and acceleration of a drive unit detected by a sensor 8 attached to the industrial machine 4.The programs and data stored in the non-volatile memory 14 can be loaded into the RAM 13 during execution / use. In addition, various system programs such as well-known analysis programs are prewritten in the ROM 12.

[0011] The interface 15 is an interface for connecting the CPU 11 of the parameter setting device 1 to the external device 72, such as a USB device. For example, system programs, programs related to the operation of the industrial machine 4, setting data, etc., are read from the external device 72. Furthermore, programs, setting data, etc., created and edited in the parameter setting device 1 can be saved to an external storage device via the external device 72.

[0012] The interface 20 is an interface for connecting the CPU 11 of the parameter setting device 1 to the wired or wireless network 5. For example, the network 5 can perform communication using technologies such as serial communication such as RS-485, Ethernet (registered trademark) communication, optical communication, wireless LAN, Wi-Fi (registered trademark), and Bluetooth (registered trademark). The controller that controls the industrial machine 4, the fog computer 6, the cloud server 7, etc., are connected to the network 5 and mutually exchange data with the parameter setting device 1.

[0013] Various data read into the memory, data obtained as a result of program execution, etc., are output to and displayed on the display device 70 via the interface 17. Furthermore, the input device 71, which includes a keyboard, a pointing device, etc., transmits commands, data, etc., based on an operator's operation, to the CPU 11 via an interface 18.

[0014] Fig. Figure 2 shows functions of the parameterization device 1 according to the first embodiment of the disclosure as a schematic block diagram. The respective functions of the parameterization device 1 according to this embodiment are implemented by the CPU 11, with which the Fig. 1, executes a system program and controls activities of the respective units of the parameterization device 1.

[0015] The parameter setting device 1 of this embodiment includes a simulation unit 100, a first search unit 110, a candidate application unit 120, a search area determination unit 130, a second search unit 140, and an output unit 150. Furthermore, the RAM 13 or the non-volatile memory 14 of the parameter setting device 1 is provided with a model storage unit 210, which is an area in which a control target model modeling the operation of the industrial machine 4 serving as the control target is stored in advance. Furthermore, an evaluation program 220 used for a simulation process and for controlling the operation of the actual control target is stored in advance in the RAM 13 or the non-volatile memory 14 of the parameter setting device 1.

[0016] The simulation unit 100 executes a predetermined simulation process to simulate an operation of the control target based on the control target model stored in the model storage unit 210. The control target model stored in the model storage unit 210 models the operation of each unit of the industrial machine 4, including a drive unit such as a servo motor, a transmission unit such as a ball screw, and a movable unit such as a table. The control target model is expressed by a mathematical expression, a transfer function, a block diagram, etc., that reflects the characteristics of the industrial machine 4 serving as the control target. By preparing the control target model, it is possible to simulate the operation of the industrial machine 4 serving as the control target.

[0017] The simulation process executed by the simulation unit 100 virtually executes the operation of the industrial machine 4 when predetermined command information is output to the industrial machine 4 serving as the control target, through a calculation based on the control target model. As a result of the simulation process, virtual feedback information of the industrial machine 4 serving as the control target is generated. Examples of the virtual feedback information include virtual physical quantities related to the operation of the industrial machine 4, such as a position, a speed, an acceleration, and a torque of a motor for each operation cycle.

[0018] When performing the simulation process, the simulation unit 100 considers a given control parameter in the calculation associated with the control target model. The control parameter differs depending on the type of industrial machine 4 serving as the control target. For example, if the industrial machine 4 serving as the control target is a machine tool driven by servo motors, examples of the control parameter include setting values associated with each motor, such as the linear acceleration, linear jerk, corner speed difference, the acceleration / deceleration time constant after interpolation, the speed gain, the position loop gain, and the feedforward coefficient.Furthermore, in the case of an electrical discharge machining machine, the examples additionally include setting values related to the power supply, such as the electrical discharge machining pulse voltage and the electrical discharge machining current.

[0019] The first search unit 110 repeatedly performs the simulation process by the simulation unit 100 while changing the control parameter within a first range for the control parameter. Then, based on the result of the simulation process, the first search unit 110 searches, in an area of the set of control parameter values of the first range where a predetermined index value satisfies a predetermined constraint condition, a set of most suitable control parameter values and a set of control parameter values nearby as candidates for the set of control parameter values. The predetermined index value is an index used for constraints and evaluations related to the result of the operation of the control target. Examples of the index value include machining accuracy (machining error), machined surface quality (positional deviation, vibration), machining time (cycle time), etc.

[0020] The first range is a range of possible values for each control parameter in the simulation process. The first range can be set by the operator or can be determined according to a predetermined rule based on specifications of the industrial machine 4 serving as the control target, command information included in the evaluation program 220 used in the simulation, etc. The first range is a predetermined range within which an index value used to evaluate the result of the simulation process can be calculated. Since the first range is a search range in the simulation process by the simulation unit 100, there is no problem if the first range is set to a relatively wide range.For example, a range from a minimum value to a maximum value that can be set for each control parameter may be set as the first range, or a range of values that can be set based on command information may be set as the first range.

[0021] The first search unit 110 causes the simulation unit 100 to execute the simulation process based on predetermined command information contained in the evaluation program 220 while changing the value of each control parameter within the first range. As a result, virtual feedback information is obtained, and a predetermined index value is evaluated based on the obtained feedback information. The first search unit 110 performs this process using a machine learning-based search or a rule-based search such as reinforcement learning or Bayesian optimization, or a known algorithm such as a predetermined exhaustive search algorithm.When a suitable constraint condition and evaluation method have been determined, at least one set of at least one control parameter value near a boundary of the constraint condition is obtained as a result of the search by the first search unit 110. The first search unit 110 can store the result of the simulation process (the index value), the determination result, and the result of the evaluation of the constraint condition for the set of control parameter values that have undergone the evaluation.The first search unit 110 outputs a single set of the best control parameter values in the range where the constraint condition is satisfied, or two sets of control parameter values near the boundary of the constraint condition, a first set of control parameter values that satisfy the constraint condition, and a second set of control parameter values that do not satisfy the constraint condition, to the candidate application unit 120.

[0022] The candidate application unit 120 sets, for the industrial machine 4 serving as the control target, a set of control parameter values near the boundary of the constraint condition obtained through the search of the first search unit 110, and issues a command to perform an operation check based on command information included in the evaluation program 220. Then, feedback information related to the operation is obtained from the industrial machine 4 as a result of the operation. An index value is then calculated to evaluate the obtained feedback information.

[0023] The search range determining unit 130 determines, based on the operation result of the operation check performed by the candidate application unit 120 for the set of control parameter values near the boundary of the restriction condition searched by the first search unit 110 on the industrial machine 4 to be actually controlled, a second range obtained by correcting the first range.

[0024] If the set of control parameter values near the boundary of the constraint condition searched by the first search unit 110 is a single set, the search range determination unit 130 may determine a predetermined range based on the set of control parameter values as the second range. For example, the second range may be a range from a lower limit of the first range for each control parameter to a control parameter value near the boundary of the constraint condition. Furthermore, the second range may be a range from an upper limit of the first range for each control parameter to a control parameter value near the boundary of the constraint condition.If the result of the operation check on the industrial machine 4 to be actually controlled by the candidate application unit 120 does not satisfy the constraint condition, the second range may be determined based on a control parameter value near the boundary of the constraint condition in a direction such that the constraint condition is satisfied. Or, if the constraint condition is not satisfied, the second range may be determined based on a control parameter value near the boundary of the constraint condition in a direction such that the evaluation is improved.

[0025] When the set of control parameter values near the boundary of the restriction condition that the first search unit 110 has searched is two sets, the search range determining unit 130 may determine the second range based on a processing result obtained by performing a simulation process on each set of control parameter values near the boundary of the restriction condition and a result of the operation check performed on the industrial machine 4 to be actually controlled.For example, in a case where the constraint condition is satisfied according to the result of the operation verification performed on the industrial machine 4 to be actually controlled, regardless of the set of control parameter values used for operation, the search range determination unit 130 calculates, for the set of second control parameter values, a difference between the respective index values of the processing result of the simulation process and the result of the operation verification performed on the industrial machine 4 to be actually controlled as a modeling error. Next, a set of third control parameter values that do not satisfy the constraint condition is selected from the sets of control parameter values searched by the first search unit 110, taking the calculated modeling error into account.Then, a range between the selected set of third control parameter values and the set of second control parameter values can be determined as the second range.

[0026] If, as a result of the operation check performed on the industrial machine 4 to be actually controlled, the index value has satisfied the restriction condition in the case of operation with one set of control parameter values, but the index value has not satisfied the restriction condition in the case of operation with the other set of control parameter values, a range between the first set of control parameter values and the second set of control parameter values may be determined as a second range.

[0027] Furthermore, for example, in a case where the constraint condition is not met according to the result of the operation verification performed on the industrial machine 4 to be actually controlled, regardless of the set of control parameter values used for operation, the search range determination unit 130 calculates, for the set of first control parameter values, a difference between the respective index values of the processing result of the simulation process and the result of the operation verification performed on the industrial machine 4 to be actually controlled as a modeling error. Next, a set of third control parameter values that do not satisfy the constraint condition is selected from the sets of control parameter values searched by the first search unit 110, taking the calculated modeling error into account.Then, a range between the selected set of third control parameter values and the set of first control parameter values can be determined as the second range.

[0028] The second search unit 140 searches for a set of appropriate control parameters while changing the control parameters within the second range determined by the search range determination unit 130. The second search unit 140 according to this embodiment operates the industrial machine 4 to be actually controlled according to command information included in the evaluation program 220. Then, based on the result of the operation of the industrial machine 4 to be actually controlled, a set of the most appropriate control parameter values is searched for in an area of the set of control parameters of the second range where an index value satisfies the constraint condition.The second search unit 140 performs this process using a machine learning-based search or a rule-based search such as reinforcement learning or Bayesian optimization, or a known algorithm such as a predetermined complete search algorithm. The second search unit 140 operates the industrial machine 4 to be actually controlled and calculates an index value from its operation result. Then, the second search unit 140 determines whether the calculated index value satisfies the constraint condition and makes an evaluation using the index value. Operating the industrial machine 4 to establish a set of control parameter values takes the same time as the actual cycle time.However, since the second range determined by the search range determination unit 130 is sufficiently narrower than the first range, searching for it does not require a tremendous amount of time. The second search unit 140 searches for a set of the best control parameter values that satisfy at least one set of constraint conditions. The second search unit 140 outputs the searched set of control parameter values to the output unit 150.

[0029] The output unit 150 outputs the set of control parameter values searched by the second search unit 140 to a predetermined device, a predetermined apparatus, etc. For example, the output unit 150 may display the set of control parameter values on the display unit 70 or record the set of control parameter values in a predetermined area provided in the non-volatile memory 14. Furthermore, the set of control parameter values may be sent to the controller of the industrial machine 4 for setting or sent to a higher-level computer such as the fog computer 6 or the cloud server 7.

[0030] With reference to Fig. 3 to Fig. 6, a specific operation example of the parameter setting device 1 according to this embodiment having the above-mentioned structure will be described.

[0031] This operating example considers a case where industrial machine 4 is a machine tool where each shaft is driven by a servo motor. The control parameters to be sought are the linear acceleration [mm / s 2] and the corner speed difference [mm / s] of each shaft of the industrial machine 4 are set. In addition, a maximum value of a machining error and a cycle time are selected as an index value. A constraint condition is that the maximum value of the machining error is equal to or less than a predetermined target error, and the evaluation method is that a shorter cycle time is more favorable. It should be noted that the quality of the machined surface, etc., can be used as an index value, and in this case, a predetermined value for the quality of the machined surface can be provided as a constraint condition. There is a correlation between the machining error and the cycle time. If the machining error is to be reduced, the cycle time tends to become longer, and if the cycle time is to be shortened, the machining error will increase.If the machining error lies within a target error, for any set of control parameter values near its boundary, there exists a solution that minimizes the cycle time.

[0032] Fig. Figure 3 is a flowchart illustrating the schematic flow of processing related to search preparation.

[0033] First, following a command from the operator, the simulation unit 100 reads a model of the machine tool in which each shaft is driven using a servo motor from the model storage unit 210 (step SA01). Next, following a command from the operator, the first search unit 110 selects the linear acceleration and the corner speed difference as the control parameters to be searched (step SA02). Furthermore, the constraint condition of the machining error is set to a target error of 10 [µm] or less, and the evaluation method is set so that the shorter the cycle time, the higher the evaluation becomes (step SA03).

[0034] Next, the first search unit 110 sets a first range for each control parameter (step SA04). The first range is set to 10 to 10000 [mm / s] for the linear acceleration. 2], and the corner speed difference is set to 10 to 5000 [mm / s]. This setting can be made by a command from the operator. Furthermore, the controller of the industrial machine 4, which serves as the control target, can request a maximum and minimum value for each control parameter, and the setting can be made based on the response.

[0035] Fig. Figure 4 is a flowchart showing the schematic processing flow of the first search process.

[0036] When the above settings are completed and the operator issues a command to start the search, the first search unit 110 selects an initial value for each control parameter from the first range and sets the initial value for the simulation model read by the simulation unit 100 (step SB01). Next, the first search unit 110 sets the evaluation program 220 to be executed in the simulation process for the simulation unit 100 (step SB02). Then, the first search unit 110 commands the selected simulation model to execute the simulation process using the set control parameter value.

[0037] The simulation unit 100 executes the simulation process following the command from the first search unit 110 (step SB03). When the simulation process is completed, the first search unit 110 obtains a processing result from the simulation unit 100 (step SB04). The obtained processing result is a machining path and a cycle time, which are used to calculate the index value. The first search unit 110 calculates the index value based on the obtained processing result (step SB05). The machining error serving as an index value can be calculated as a maximum value of a difference between a path commanded by the command information and a machining path in virtual machining in the simulation process. Regarding the cycle time, a cycle time obtained as a processing result is used as an index value as it is.If the search for the first range is not completed at this time (No at step SB06), the first search unit 110 changes the control parameter value and then sets the control parameter value for the simulation model (step SB07). Then, the process proceeds to step SB03. On the other hand, if the search for the first range is completed at this time (YES at step SB06), a control parameter near the boundary of the constraint condition is selected as a candidate from among the searched control parameters (step SB08). The processes at steps SB03 to SB07 are performed as described above using a known search algorithm such as a machine learning-based search, a rule-based search, a predetermined complete search algorithm, or Bayesian optimization.

[0038] Here, it is assumed that the first search unit 110, as a result of the first search process, obtains a set of first control parameter values A that satisfy the constraint condition (linear acceleration = 2300 [mm / s 3 ], corner speed difference = 1100 [mm / s] with a machining error of 9 [µm] and a cycle time of 35.2 [s]) and a set of second control parameter values B that do not satisfy the constraint condition (linear acceleration = 2400 [mm / s 3 ], corner speed difference = 1200 [mm / s] with a machining error of 12 [µm] and a cycle time of 33.0 [s]) as a candidate for the control parameter.

[0039] Fig. 5 is a flowchart illustrating the schematic flow of the process for determining the second area.

[0040] When candidates of the set of control parameter values are selected, the candidate application unit 120 sets the selected candidate control parameter values for the industrial machine 4 to be actually controlled, performs an operation check based on command information included in the evaluation program 220, and obtains an operation result for performing the operation using each candidate of the set of control parameter values (step SC01). The obtained operation result is the machining path and cycle time, which are used to calculate the index value. The candidate application unit 120 calculates the index value based on the obtained operation result (step SC02).The machining error, which serves as an index value, can be calculated as the maximum difference between the path commanded by the command information and the actual machining path. Regarding the cycle time, the cycle time obtained as a processing result is used as the index value.

[0041] Next, the search range determination unit 130 determines the second search range obtained by correcting the first range based on the index value calculated by the candidate application unit 120 (step SC03). For example, it is assumed that the machining error serving as the index value as a result of the operation check when setting the set of first control parameter values A for the industrial machine 4 to be actually controlled was 12 [µm]. Furthermore, it is assumed that the machining error serving as the index value as a result of the operation check when setting the set of second control parameter values B for the industrial machine 4 to be actually controlled was 14 [µm]. Thus, the restriction condition is not satisfied for either the first set of first control parameter values or the second set of second control parameter values.In such a case, the search range determination unit 130 calculates the difference between the respective index values of the processing result of the simulation process and the result of the operation verification performed on the industrial machine 4 to be actually controlled for the set of first control parameter values A. When performing the simulation process with the set of first control parameter values A determined, the machining error was 9 [µm]. Furthermore, the machining error serving as the index value as the result of the operation verification in the case of the determination for the industrial machine 4 to be actually controlled was 12 [µm], and the difference between the two was 3 [µm]. This value is estimated as the modeling error that occurs when modeling the industrial machine that is the actual control target.Therefore, new candidates for the set of control parameter values are selected, taking into account the constraint condition and the modeling error. In this case, the target error set as the constraint condition is 10 [µm] and the modeling error is 3 [µm]. Therefore, if a set of control parameter values falls within a machining error equal to or less than 10 [µm] - 3 [µm] = 7 [µm] as a result of the simulation process, there is a high probability that the constraint condition will be met when the operation is performed with their setting for the industrial machine 4 to be actually controlled. Therefore, from sets of control parameter values with machining errors that fall below 7 [µm] as a result of the simulation process, a set with the shortest cycle time is selected as the set of third control parameter values C.Once the set of third control parameter values C has been selected, the candidate application unit 120 then performs an operation check for the set of third control parameter values C on the industrial machine 4 to be actually controlled. If an index value calculated from its check result satisfies the constraint condition, a range between the set of third control parameter values C and the set of first control parameter values A can be determined as the second range. On the other hand, if the constraint condition is not met, a new set of control parameter values with even smaller machining errors can be selected as the set of third control parameter values C, and the same process can be repeated. Assume that, through the above-described process flow for the set of third control parameter values C, for example, a set of control parameter values with a linear acceleration of 2000 [mm / s] can be obtained.2 ] and a corner speed difference = 900 [mm / s] (with a machining error of 7 [µm] and a cycle time of 36.0 [s]). In this case, the search range determination unit 130 determines the second range such that the range of linear acceleration is 2000 to 2300 [mm / s 2 ] and the range of corner speed difference is 900 to 1100 [mm / s].

[0042] Now, a case will be discussed where the constraint condition is satisfied for both the set of first control parameter values and the set of second control parameter values. For example, assume that the machining error serving as the index value as a result of the operation check when the set of first control parameter values A was specified for the industrial machine 4 to be actually controlled was 7 [µm]. Furthermore, assume that the machining error serving as the index value as a result of the operation check when the set of second control parameter values B was specified for the industrial machine 4 to be actually controlled was 9 [µm]. Thus, the constraint condition is satisfied for both the set of first control parameter values and the set of second control parameter values.In such a case, the search range determination unit 130 calculates the difference between the respective index values of the processing result of the simulation process and the result of the operation verification performed on the industrial machine 4 to be actually controlled for the set of second control parameter values B. When performing the simulation process with the set of second control parameter values B determined, the machining error was 12 [µm]. Furthermore, the machining error serving as the index value as the result of the operation verification in the case of the determination for the industrial machine 4 to be actually controlled was 9 [µm], and the difference between the two was 3 [µm]. This value is estimated as the modeling error that occurs when modeling the industrial machine that is the actual control target.Therefore, considering both the constraint condition and the modeling error, new candidate control parameter values are selected. In this case, the target error set as the constraint condition is 10 [µm], and the modeling error is 3 [µm]. Therefore, if a set of control parameter values exhibits a machining error equal to or greater than 10 [µm] + 3 [µm] = 13 [µm] as a result of the simulation process, it is highly unlikely that the machining condition will be met when the operation is performed on the industrial machine 4 to be actually controlled while they are set. Therefore, from the sets of control parameter values exhibiting a machining error equal to or greater than 13 [µm] as a result of the simulation process, a set with the shortest cycle time is selected as the set of third control parameter values C.Once the set of third control parameter values C has been selected, the candidate application unit 120 then performs an operation check on the set of third control parameter values C on the industrial machine 4 to be actually controlled. If an index value calculated from the check result thereof does not satisfy the constraint condition, a range between the set of third control parameter values C and the set of second control parameter values B may be determined as the second range. On the other hand, if the constraint condition is met, a new set of control parameter values with even larger processing errors may be selected as the set of third control parameter values C, and the same process may be repeated.

[0043] Fig. Figure 6 is a flowchart showing the schematic flow of the second search.

[0044] When the above process is completed and the second range is determined, the second search unit 140 selects an initial value for each control parameter from the second range and sets the initial value for the industrial machine 4 to be actually controlled (step SD01). Next, the second search unit 140 sets the evaluation program 220 to be executed for the industrial machine 4 to be actually controlled (step SD02). Then, the second search unit 140 commands the industrial machine 4 to be actually controlled to operate using the set control parameter.

[0045] In the industrial machine 4 to be actually controlled, an operation based on the command information included in the evaluation program 220 is performed (SD03). When the operation based on the command information is completed in the industrial machine 4 to be actually controlled, the second search unit 140 acquires an operation result from the industrial machine 4 to be actually controlled (step SD04). The acquired operation result is the machining path and the cycle time, which are used to calculate the index value. The second search unit 140 calculates the index value based on the acquired operation result (step SD05). The machining error serving as the index value can be calculated as the maximum value of a difference between a path commanded by the evaluation program 220 and an actual machining path.Regarding the cycle time, a cycle time obtained as a processing result is used as an index value as it is. If the search for the second range is not completed at this time (No at step SD06), the second search unit 140 changes the control parameter value and then sets the control parameter value for the industrial machine 4 to be actually controlled (step SD07). Then, the process proceeds to step SD03. On the other hand, if the search for the second range is completed at this time (YES at step SD07), the control parameter with the highest evaluation (the cycle time serving as the index value is the shortest) among the control parameters that satisfy the constraint condition (the machining error serving as the index value is equal to or less than the target error) is selected from the searched control parameters (step SD08).The processes in steps SD03 to SD07 are performed as described above using a known search algorithm such as machine learning-based search, rule-based search, predetermined exhaustive search algorithm, or Bayesian optimization.

[0046] Here, it is assumed that the second search unit 140, as a result of the second search process, obtains a set of control parameter values that satisfy the constraint condition (linear acceleration = 2250 [mm / s 3], corner speed difference = 1000 [mm / s] with a machining error of 10 [µm] and a cycle time of 35.9 [s]) as the control parameter. The output unit 150 displays the set of control parameter values selected by the second search unit 140 on the display device 70 and executes the setting by sending the set to the industrial machine 4 to be actually controlled (step SD09).

[0047] The parameter setting device 1 according to this embodiment having the above-mentioned structure narrows the range of control parameters to near the boundary of the constraint condition through a simulation process that can be processed at high speed. Since the narrowed range of control parameters is sufficiently narrow, it becomes possible, for example, to set the control parameters using the industrial machine 4 to be actually controlled. Even if the industrial machine 4 can set control parameters with high accuracy, it is difficult to set control parameters over a wide range because obtaining the operating result takes time.However, if a simulation process that can be performed at a high speed is used in advance, the adjustment range can be narrowed to a certain degree of safety, and therefore a shortening of the adjustment time can be expected using the industrial machine 4.

[0048] The present disclosure has been described in detail above, but is not limited to these embodiments. Therefore, various additions, substitutions, modifications, partial omissions, and so on can be made to these embodiments without departing from the gist of the disclosure or the spirit of the disclosure derived from the contents described in the claims and their equivalents. For example, the order of each operation and the order of each process in the above embodiments are merely examples and are not limited to these embodiments. The same applies when numerical values or mathematical formulas are used in the explanations of the above embodiments.

[0049] Supplementary notes will be described below. (Supplementary Note 1)

[0050] A parameterization device (1) according to one aspect of the disclosure comprises a control target model configured to model an operation of each unit provided with an industrial machine (4) serving as a control target; a simulation unit (100) configured to simulate, based on the control target model, an operation of the control target with a predetermined setting value of a control parameter; a first search unit (110) configured to repeatedly perform the simulation process by the simulation unit (100) while changing the value of the control parameter within a predetermined first range, and, based on a first index value calculated from a result of the simulation process, search for a candidate for a set of values of the control parameter that allow a first index value to be obtained near a boundary of a predetermined constraint condition; a candidate application unit (120) that performs an operation check for the control target by setting the set of values of the control parameter serving as the candidate searched by the first search unit (110), and calculates a second index value based on a result of the operation check; and a search range determining unit (130) configured to determine, based on the first index value and the second index value, a second range serving as a range of values narrower than the first range. (Supplementary Note 2)

[0051] A parameterization device (1) according to another aspect of the disclosure further comprises a second search unit (140) configured to search for the control parameter by repeatedly operating the control target while changing the value of the control parameter within the second range. (Supplementary Note 3)

[0052] In a parameterization device (1) according to another aspect of the disclosure, the first index value and the second index value are any of a machining accuracy, a quality of the machined surface and a machining time, and at least one of the first search unit (110) and the second search unit (140) provides the restriction condition related to the machining accuracy or the quality of the machined surface and searches the control parameter using a machine learning method such that the machining time is shortest under the restriction condition. (Supplementary Note 4)

[0053] A computer-readable recording medium according to one aspect of the disclosure stores a program that causes a computer, as a simulation unit (100) configured to simulate, based on a control target model configured to model at least one operation of each unit with which an industrial machine (4) serving as a control target is provided, an operation of the control target with a predetermined setting value of a control parameter; a first search unit (110) configured to repeatedly perform the simulation process by the simulation unit (100) while changing the value of the control parameter within a predetermined first range, and, based on a first index value calculated from a result of the simulation process, search for a candidate for a set of values of the control parameter that allow a first index value to be obtained near a boundary of a predetermined constraint condition; a candidate application unit (120) that performs an operation check for the control target by setting the set of values of the control parameter serving as the candidate searched by the first search unit (110), and calculates a second index value based on a result of the operation check; and a search range determining unit (130) configured to operate on the basis of the first index value and the second index value to determine a second range serving as a range of values narrower than the first range. EXPLANATION OF REFERENCE SYMBOLS 1 PARAMETERIZATION DEVICE 4 INDUSTRIAL MACHINE 5 NETWORK 6 FOG COMPUTERS 7 CLOUD SERVER 8 SENSOR 11 CPU 12 ROM 13 RAM 14 NON-VOLATILE MEMORY 15, 17, 18, 20 INTERFACE 22 BUS 70 DISPLAY DEVICE 71 INPUT DEVICE 72 EXTERNAL DEVICE 100 SIMULATION UNIT 110 FIRST SEARCH UNIT 120 CANDIDATE APPLICATION UNIT 130 SEARCH AREA DETERMINATION UNIT 140 SECOND SEARCH UNIT 150 dispensing units 210 MODEL STORAGE UNIT 220 EVALUATION PROGRAM QUOTES CONTAINED IN THE DESCRIPTION

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

[0000] JP 2017 - 102 619 A

[0003]

Claims

[1] Parameterization device, comprising a control target model configured to model an operation of each unit provided to an industrial machine serving as a control target; a simulation unit configured to simulate, based on the control target model, an operation of the control target with a predetermined setting value of a control parameter; a first search unit configured to repeatedly perform the simulation process by the simulation unit while changing the value of the control parameter within a predetermined first range, and to search, based on a first index value calculated from a result of the simulation process, for a candidate set of values of the control parameter that allow a first index value to be obtained near a boundary of a predetermined constraint condition; a candidate application unit that performs an operation check for the control target by setting the set of values of the control parameter serving as the candidate searched by the first search unit, and calculates a second index value based on a result of the operation check; and a search range determining unit configured to determine, based on the first index value and the second index value, a second range serving as a range of values narrower than the first range. [2] The parameter setting device according to claim 1, further comprising a second search unit configured to search for the control parameter by repeatedly operating the control target while changing the value of the control parameter within the second range. [3] Parameterization device according to claim 2, wherein the first index value and the second index value are any of a machining accuracy, a quality of the machined surface and a machining time, and at least one of the first search unit and the second search unit provides the restriction condition related to the machining accuracy or the quality of the machined surface and searches the control parameter using a machine learning method such that the machining time is shortest under the restriction condition. [4] Computer-readable recording medium that stores a program that causes a computer to act as a simulation unit configured to simulate an operation of the control target with a predetermined setting value of a control parameter based on a control target model configured to model at least one operation of each unit with which an industrial machine serving as a control target is provided; a first search unit configured to repeatedly perform the simulation operation by the simulation unit while changing the value of the control parameter within a predetermined first range, and to search, based on a first index value calculated from a result of the simulation process, for a candidate set of values of the control parameter that allow a first index value to be obtained near a boundary of a predetermined constraint condition; a candidate application unit that performs an operation check for the control target by setting the set of values of the control parameter serving as the candidate searched for by the first search unit, and calculates a second index value based on the operation check; and a search range determining unit configured to determine, on the basis of the first index value and the second index value, a second range serving as a range of values narrower than the first range, to work.

Images