Information processing system, injection molding machine, and program

Abstract

To reduce time and effort required for changing a simulation model according to a structure, a use mode or the like of an apparatus, with respect to a model used for simulation related to control of the apparatus.SOLUTION: A first mechanical operation 506 of performing an estimation related to an operation of a first movable part using a simulation model of the first movable part based on a command for controlling the operation of the control target device, the first movable part being a movable part of the control target device that is not affected by the usage mode in the operation, and a second mechanical operation 507 of receiving an estimation result of the first mechanical operation 506 and performing an estimation related to an operation of a second movable part using a simulation model of the second movable part, the second movable part being a movable part of the control target device that is affected by the usage mode in the operation.SELECTED DRAWING: Figure 6

Description

[Technical Field]

[0001] The present invention relates to an information processing system, an injection molding machine, and a program. [Background technology]

[0002] In controlling equipment, simulations are performed and control information is adjusted based on the results of the simulations.

[0003] Patent Document 1 discloses that in an injection molding system, a PID (Proportional-Integral-Differential) controller is adjusted to control the injection pressure of an injection molding machine based on the error between the injection pressure detected by a sensor and the pressure set point indicated by a control model.

[0004] Patent Document 2 discloses that, with regard to a device constituting an injection molding machine, a control system for the device is designed by linearizing a mathematical model that models an actual device and performing a simulation. [Prior art documents] [Patent documents]

[0005] [Patent Document 1] Special Publication No. 2020-533197 [Patent Document 2] Japanese Patent Application Publication No. 6-8296 Summary of the Invention [Problem to be solved by the invention]

[0006] When simulating the control of equipment, it is sometimes necessary to use different simulation models depending on the equipment's structure, usage, etc. However, changing the model used in the simulation depending on the structure and usage conditions of various equipment is time-consuming.

[0007] The present invention aims to reduce the effort required to change a simulation model used in a simulation relating to the control of a device in accordance with the structure, usage, etc. of the device. [Means for solving the problem]

[0008] One aspect of the present invention is an information processing system characterized by comprising: a first estimation unit that, based on an instruction to control the operation of a controlled device, makes an estimation regarding the operation of a first movable part, which is a movable part of the controlled device whose operation is not affected by the usage manner, using a simulation model of the first movable part; and a second estimation unit that receives the estimation result of the first estimation unit and makes an estimation regarding the operation of a second movable part, which is a movable part of the controlled device whose operation is affected by the usage manner, using a simulation model of the second movable part. [Effects of the Invention]

[0009] According to one aspect of the present invention, it is possible to reduce the effort required to change a simulation model used in a simulation relating to the control of a device in accordance with the structure, usage, etc. of the device. [Brief explanation of the drawings]

[0010] [Figure 1] 1 is a diagram showing the configuration of an injection molding machine to which the present embodiment is applied; [Figure 2] FIG. 2 is a diagram illustrating a configuration of a control device. [Figure 3] FIG. 1 is a diagram illustrating a configuration of a data processing device. [Figure 4] FIG. 1 is a diagram illustrating a configuration of an information processing device. [Figure 5] FIG. 1 is a diagram illustrating an example of a hardware configuration of a computer that realizes an information processing device. [Figure 6] FIG. 2 is a diagram illustrating an example of the configuration of a simulation model used for analysis by an analysis unit of a processing unit of an information processing device. [Figure 7]FIG. 10 is a diagram for comparing output waveforms of simulation models. [Figure 8] FIG. 10 is a diagram illustrating another example of the configuration of a simulation model used for analysis by the analysis unit of the processing unit of the information processing device. [Figure 9] FIG. 10 is a diagram illustrating an example of the configuration of a linear multiple regression model. [Figure 10] FIG. 1 is a diagram illustrating a method for deriving a machine learning model. DETAILED DESCRIPTION OF THE INVENTION

[0011] Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings. <Device configuration> 1 is a diagram showing the configuration of an injection molding machine to which this embodiment is applied. The injection molding machine 10 includes an injection unit 20, a mold clamping unit 30, a control device 100, and a data processing device 200. The injection molding machine 10 is an example of a device to be controlled. An information processing device 400 is connected to the control device 100 and the data processing device 200.

[0012] The injection device 20 is configured with a cylinder that heats the molding material, a screw that is rotatable within the cylinder and can move back and forth in the axial direction, a rotary motor that drives the screw in the rotational direction, and a motor that drives the screw in the axial direction. The molding material is, for example, a resin. The injection device 20 injects the molding material that has been heated and turned into a liquid form within the cylinder by rotating the screw and advancing it in a direction (forward) from the injection device 20 toward the clamping device 30, and fills the mold of the clamping device 30 located in front of the injection device 20. The injection device 20 performs, for example, a metering process, a filling process, and a pressure holding process in the manufacturing process of a molded product. The filling process and pressure holding process are collectively referred to as the injection process.

[0013] The mold clamping device 30 is configured to include a mold, a clamping mechanism for clamping the mold, a motor for driving this clamping mechanism, etc. The mold clamping device 30 closes the mold and receives the molding material injected from the injection device 20 into the mold. At this time, the mold clamping device 30 clamps the mold using the clamping mechanism so that the mold does not open when the molding material is filled (mold clamping). A molded product is produced when the molding material filled in the mold solidifies. Thereafter, the mold clamping device 30 opens the mold, allowing the produced molded product to be removed. The mold clamping device 30 performs processes in the manufacturing process of molded products, such as a mold closing process, a pressure increase process, a mold clamping process, a pressure release process, and a mold opening process.

[0014] The control device 100 is a device that controls the operations of the injection device 20 and the mold clamping device 30. The data processing device 200 is a device that processes data obtained as the injection device 20 and the mold clamping device 30 operate.

[0015] The information processing device 400 acquires waveform data obtained by the operation of the injection molding machine 10 from the control device 100 and the data processing device 200, and determines the characteristics of the injection molding machine 10 based on the acquired waveform data. The information processing device 400 outputs information for controlling each injection molding machine 10 based on the information on the determined characteristics of the injection molding machine 10, and provides this information to the control device 100. Details of the processing by the information processing device 400 and the information output will be described later.

[0016] <Configuration of the control device 100> FIG. 2 illustrates the configuration of the control device 100. The control device 100 controls the operation of the injection device 20 and the mold clamping device 30. The control device 100 is implemented, for example, by a computer. The control device 100 includes a control unit 110 and a memory unit 120. The control device 100 controls the injection device 20 and the mold clamping device 30 to repeatedly perform processes related to the production of molded products, thereby repeatedly producing molded products. The processes related to the production of molded products include a metering process, mold closing process, pressurization process, mold clamping process, filling process, pressure holding process, cooling process, depressurization process, mold opening process, and ejection process. Hereinafter, these manufacturing processes may be collectively referred to as the "manufacturing process." Furthermore, a series of operations for obtaining a molded product, such as the operations from the start of a metering process in the above manufacturing process to the start of the next metering process, is referred to as a "shot," a "molding cycle," or the like. Note that the above-described processes for producing molded products are merely examples. For example, other processes not included in the above may be included as processes executed in one shot.

[0017] The control unit 110 controls the injection unit 20 and the mold clamping unit 30 based on the control information. The control information is a condition set by the user and is generated based on information input by the user using an input device (not shown). The control information includes molding conditions such as resin temperature, mold temperature (cylinder temperature), injection dwell time, measurement value, VP switching position, dwell pressure, injection speed (filling speed), screw rotation speed, screw back pressure, and mold clamping force. Multiple combinations of these molding conditions are determined depending on the molded product and mold. This combination data of molding conditions is also referred to as a molding condition data set below. The control information also includes control data such as voltage, current, pressure, speed, and acceleration for driving units such as mechanisms and motors. The molding condition data set is prepared depending on the type of molded product and mold, and is stored in the storage unit 120. The molding conditions are an example of operating conditions.

[0018] The control unit 110 controls the injection unit 20 and the mold clamping unit 30 using the above molding condition data set, and performs the process for manufacturing (shotting) a molded product, including each of the above steps. The control unit 110 reads out the molding condition data set corresponding to the molded product to be manufactured from the storage unit 120, for example, at the start of manufacturing the molded product. The control unit 110 then controls the operation of the injection unit 20 and the mold clamping unit 30 based on control information including the read molding condition data set. Specifically, the control unit 110 controls the injection unit 20 and the mold clamping unit 30 so that the data obtained from the injection unit 20 and the mold clamping unit 30 during the manufacturing process matches the set values ​​of the molding condition data set.

[0019] The storage unit 120 stores control information used by the control unit 110 to control the injection unit 20 and the mold clamping unit 30. The molding condition data sets included in the control information are prepared in association with the molded product and mold to be manufactured. The storage unit 120 stores molding condition data sets for each molded product and mold to be manufactured. In addition, although not shown, the storage unit 120 stores a program for the control unit 110 to control the injection unit 20 and the mold clamping unit 30.

[0020] <Configuration of data processing device 200> 3 is a diagram showing the configuration of the data processing device 200. The data processing device 200 acquires and processes data obtained as the injection device 20 and the mold clamping device 30 perform the operations in the processes related to the manufacturing of the above-mentioned molded product. The data processing device 200 is realized by, for example, a computer. The data processing device 200 includes a data acquisition unit 210, a processing unit 220, and a storage unit 230.

[0021] The data acquisition unit 210 acquires data to be processed from the injection unit 20 and the mold clamping unit 30. Various sensors, detectors, etc. are attached to the injection unit 20 and the mold clamping unit 30. Various measuring devices may also be connected to the injection unit 20 and the mold clamping unit 30. Data acquired using these sensors, detectors, measuring devices, etc. (hereinafter referred to as "acquired data") is information that represents the molding results obtained by the injection unit 20 and the mold clamping unit 30, and is used for quality control of molded products. The data acquisition unit 210 receives the acquired data transmitted from the sensors, detectors, measuring devices, etc., and stores it in the memory unit 230.

[0022] The processing unit 220 processes the acquired data stored in the storage unit 230. Specifically, the processing unit 220 performs processes such as extracting a representative value of the acquired data in each process and generating time-series data by chronologically serializing the acquired data in each process. In extracting the representative value, the processing unit 220 performs statistical processes on the acquired data such as calculating an average value, specifying a range of possible values, and specifying maximum and minimum values.

[0023] The storage unit 230 stores the acquired data acquired by the data acquisition unit 210. The data format of the acquired data stored in the storage unit 230 may be, for example, binary, text, CSV (Comma Separated Values), INI, YAML (YAML Ain't Markup Language), JSON (JavaScript Object Notation), or the like. By storing the data in a data file in one of these general-purpose data formats, it becomes possible to exchange data files stored in the storage unit 230 with other information processing devices, or to edit data files acquired from external devices. Furthermore, although not shown, the storage unit 230 stores a program for the processing unit 220 to execute data processing.

[0024] <Configuration of information processing device 400> FIG. 4 is a diagram showing the configuration of an information processing device 400. The information processing device 400 executes a simulation of the operation of the injection molding machine 10 using a model of the injection molding machine 10. The information processing device 400 then generates and outputs control information for the injection molding machine 10 based on the results of the simulation. The information processing device 400 is realized by, for example, a computer. The information processing device 400 includes a communication unit 410, a processing unit 420, and a storage unit 430. The processing unit 420 has an analysis unit 421 that executes a simulation using a machine learning model or the like to analyze the characteristics of the injection molding machine 10. The storage unit 430 stores a simulation model 431 used in the analysis by the analysis unit 421.

[0025] The communication unit 410 performs data communication between the control device 100 and the data processing device 200. Specifically, the communication unit 410 transmits control information for the injection molding machine 10 generated by processing by the processing unit 420 to the control device 100. The communication unit 410 is also used to obtain information used for simulation and analysis from the control device 100 or the data processing device 200. For example, the communication unit 410 may obtain control information for the injection unit 20 and the mold clamping unit 30 used for processing by the processing unit 420 from the control device 100. The data to be received may be various data obtained as waveform data during operation of the injection molding machine 10. Specifically, examples of the data include data on voltages and currents supplied to various mechanisms, and data on speeds, accelerations, and pressures during operation of the various mechanisms.

[0026] The processing unit 420 performs processing to determine the characteristics of the injection molding machine 10 using the control information of the injection unit 20 and the mold clamping unit 30. The control information of the injection unit 20 and the mold clamping unit 30 may be acquired by receiving it from the injection unit 20 and the mold clamping unit 30 via the communication unit 410, or control information separately prepared for the simulation may be used.

[0027] The analysis unit 421 processes the control information of the injection unit 20 and the mold clamping unit 30 and generates input variables to be input to the simulation model 431. Then, the analysis unit 421 inputs the generated input variables to the simulation model 431 and outputs variables corresponding to actual values ​​(hereinafter referred to as "output values"). Details of the processing by the analysis unit 421 and the simulation model 431 will be described later.

[0028] The storage unit 430 stores control information of the injection unit 20 and the mold clamping unit 30 used in the simulation, information obtained by processing by the processing unit 420, a simulation model 431 used by the analysis unit 421 of the processing unit 420, etc. The data format of the data file stored in the storage unit 430 may be, for example, CSV, XML (Extensible Markup Language), JSON, etc.

[0029] <Hardware configuration of information processing device 400> FIG. 5 is a diagram illustrating an example of the hardware configuration of a computer that realizes an information processing device 400. The computer illustrated in FIG. 5 includes a processor 401, which is a computing means, and a main memory 402 and an auxiliary memory 403, which are storage means. The processor 401 may be, for example, a central processing unit (CPU), a graphics processing unit (GPU), an application specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or any other type of computing circuit. The processor 401 loads a program stored in the auxiliary memory 403 into the main memory 402 and executes it. The main memory 402 may be, for example, a random access memory (RAM). The auxiliary memory 403 may be, for example, a magnetic disk device or a solid state drive (SSD).

[0030] The computer may also be configured to include a display device 404 for displaying images and an input device 405 as input means for allowing a computer user to perform input operations. Examples of the input device 405 include a keyboard, a mouse, and a touch panel. When a touch panel integrated with the display device 404 is used as the input device 405, the user performs input operations by touching the operation screen displayed on the display device 404 with a finger or a pen-type device. Note that the computer configuration shown in FIG. 5 is merely an example, and the computer used in this embodiment is not limited to the example configuration shown in FIG. 5. For example, the computer may be configured to include a nonvolatile memory such as a flash memory or a ROM (Read Only Memory) as a storage device.

[0031] 5, the communication unit 410 is realized by, for example, the processor 401 that reads and executes a program and a communication interface (not shown). The function of the processing unit 420 is realized by, for example, the processor 401 reading and executing a program. The storage unit 430 is realized by, for example, the auxiliary storage device 403.

[0032] <Analysis by analysis unit 421> 6 is a diagram showing an example of the configuration of a simulation model 431 used for analysis by the analysis unit 421 of the processing unit 420 of the information processing device 400. The analysis unit 421 accepts molding conditions included in the control information and performs various simulations using each model. The analysis unit 421 performs simulations targeting the operations of the injection unit 20 and the mold clamping unit 30 that constitute the injection molding machine 10. The analysis unit 421 may also perform simulations related to control by the control device 100 of the injection molding machine 10. The simulation performed by the analysis unit 421 may be configured, for example, by simulation models 431 such as command generation 501, pattern generation 502, speed control 504, current control 505, first machine operation 506, and second machine operation 507, as shown in FIG.

[0033] Command generation 501 and pattern generation 502 are simulation models that generate commands for operating injection molding machine 10 based on molding conditions for controlling injection molding machine 10. In the actual injection molding machine 10, the control device 100 generates commands for controlling the operations of injection unit 20 and mold clamping unit 30 based on the molding conditions. The calculation models used in command generation 501 and pattern generation 502 are the same as the calculation models used to generate commands in this control device 100. Analysis unit 421 that performs simulations using command generation 501 and pattern generation 502 is an example of a command generation unit.

[0034] The analysis unit 421 first generates a command for operating the injection molding machine 10 using a simulation model in command generation 501. In command generation 501, molding conditions for injection molding are converted into a command for operating the injection molding machine 10. This command is an instruction specifying the speed, pressure, etc., in the operation of the injection molding machine 10. The command generated by command generation 501 corresponds to the operation settings of the injection molding machine 10 made by the user.

[0035] Next, the analysis unit 421 converts the commands generated by command generation 501 into commands that can be followed by an actual device (injection molding machine 10) using a simulation model of pattern generation 502. Due to physical constraints of the actual device, it is difficult for the actual device to operate according to the commands corresponding to the molding conditions. Therefore, in pattern generation 502, the commands generated by command generation 501 are converted into commands whose content can be followed by the actual device. Specifically, for example, in a scene where the operating speed changes in the command generated by command generation 501, the command is converted so that the speed changes after a certain delay due to acceleration motion, rather than immediately switching to a different speed at the timing of the speed change.

[0036] The speed control 504 and the current control 505 are simulation models that generate information indicating the control content of the motor, which is the drive source of the injection molding machine 10. The speed control 504 and the current control 505 output pattern information that indicates the motor control pattern when the motor of the injection molding machine 10 is operated in accordance with the command generated by the pattern generation 502. The pattern information is generated, for example, as waveform data. The format of the waveform data is not particularly limited. For example, it may be data in which values ​​are listed in CSV format or the like, or a waveform diagram. The analysis unit 421 that performs a simulation using the speed control 504 and the current control 505 is an example of a pattern information generation unit.

[0037] The analysis unit 421 first simulates the operating speed of the motor using a simulation model for speed control 504 to generate pattern information of current changes (current commands). This pattern information is generated, for example, as waveform data representing the relationship between the passage of time and the current. Next, the analysis unit 421 simulates the current supplied to the motor using a simulation model for current control 505 to generate pattern information of voltage changes (voltage commands). In current control 505, the voltage supplied to the motor is specified to achieve the control of the operating speed of the motor generated by speed control 504. This pattern information is output, for example, as waveform data representing the relationship between the passage of time and the voltage supplied to the motor.

[0038] First machine motion 506 and second machine motion 507 are simulation models of the motion of injection molding machine 10. First machine motion 506 is a simulation model of the motion of the motor that is the drive source of injection molding machine 10. Second machine motion 507 is a simulation model of the motion of a moving part in injection molding machine 10 that operates upon receiving the driving force of the motor. The motor that is the subject of the simulation using first machine motion 506 is an example of a first moving part. Furthermore, the moving part that is the subject of the simulation using second machine motion 507 is an example of a second moving part.

[0039] The first machine action 506 and the second machine action 507 are realized, for example, as a machine learning model. For example, a linear multiple regression model is used as the machine learning model. For the first machine action 506 and the second machine action 507, operation information representing the results of the operation of the machines that constitute the actual injection molding machine 10 is output. In the example shown in FIG. 6, operation information regarding the operation speed of the injection molding machine 10 is generated. The analysis unit 421 that performs a simulation using the first machine action 506 is an example of a first estimation unit. Furthermore, the analysis unit 421 that performs a simulation using the second machine action 507 is an example of a second estimation unit.

[0040] The analysis unit 421 first executes a simulation of the motor operation using a simulation model of the first mechanical operation 506. The analysis unit 421 extracts input variables from the waveform data output from the current control 505 and inputs them to the first mechanical operation 506. In the first mechanical operation 506, a simulation of the motor operation is executed to calculate output variables (estimated values) corresponding to the input variables. The input variables are variables related to the torque of the motor. For example, the input variables include the d-axis current, the q-axis current, and the speed. As the output variables, information that can be used to calculate the torque of the motor in the second mechanical operation 507 is selected. For example, an estimated value of the motor torque itself or an estimated value of the current supplied to the motor can be used.

[0041] Next, the analysis unit 421 simulates the operation of the moving parts of the injection molding machine 10 using a simulation model of the second machine operation 507. The analysis unit 421 inputs the estimated values ​​output from the first machine operation 506 as input variables to the second machine operation 507. The second machine operation 507 simulates the operation of the moving parts of the injection molding machine 10 and calculates output variables (estimated values) corresponding to the input estimated values. Various information related to the operation of the moving parts targeted for simulation is selected as the output variables. Examples of the output variables include estimated values ​​of the operating speed, acceleration, and position of the moving parts, and an estimated value of the current supplied to the injection molding machine 10. Alternatively, instead of estimated values ​​such as the operating speed and current, information (parameters) that can be used to calculate these estimated values ​​may be output. The simulation model of the second machine operation 507 includes information such as the weight of the mold, the viscosity of the molding material (resin), and whether the system is belt-driven or driven by a direct drive motor (DD motor).

[0042] FIG. 7 is a diagram comparing the output waveforms of the simulation models. Here, waveform data showing the relationship between the motor operating speed and time is compared for each output of command generation 501, pattern generation 502, and second machine operation 507. In FIG. 7, each waveform data is represented by a waveform diagram showing the relationship between speed and time. In FIG. 7, the waveform data output from command generation 501 is represented by waveform diagram 510 with a dashed line. The waveform data output from pattern generation 502 is represented by waveform diagram 520 with a thin solid line. The waveform data output from second machine operation 507 is represented by waveform diagram 530 with a thick solid line.

[0043] As described above, the waveform data (waveform diagram 510) output from command generator 501 shows a sudden change in speed at a certain point. This is an operation based on the molding conditions set by the user, but in an actual device, it is difficult to operate the motor as shown in waveform diagram 510 due to the influence of inertia, output control, etc. The waveform data (waveform diagram 520) output from pattern generator 502 follows the speed change shown in waveform diagram 510, with a certain delay due to acceleration motion, at the timing when the speed of waveform diagram 510 changes.

[0044] The waveform data (waveform diagram 530) output from the second machine operation 507 further shows the speed change that reflects the inertia and operating characteristics of the motor and the moving parts of the injection molding machine 10. In Fig. 7, waveform diagram 530 shows that the speed changes in a curved manner with an even greater delay than waveform diagram 520.

[0045] <Adjusting the simulation model> 6, the output value of the first mechanical operation 506 (an estimated value of the current supplied to the motor) is fed back to the current control 505. The analysis unit 421 compares the output value related to the current of the first mechanical operation 506 with the output value (current command) of the speed control 504 input to the current control 505 to calculate an error. Then, the analysis unit 421 adjusts the physical quantities (parameters) included in the simulation model of the first mechanical operation 506 so that the error of the output value of the current control 505 relative to the value calculated through a linear multiple regression model for the output value of the first mechanical operation 506 is minimized.

[0046] Furthermore, the output value of the second machine operation 507 (an estimated value of the operation of the movable part of the injection molding machine 10) is fed back to the speed control 504. The analysis unit 421 compares the output value related to the speed of the second machine operation 507 with the output value (speed command) of the pattern generation 502 input to the speed control 504 to calculate an error. Then, the analysis unit 421 adjusts the physical quantities (parameters) included in the simulation model of the second machine operation 507 so that the error of the output value of the first machine operation 506 relative to the value calculated through a linear multiple regression model for the output value of the second machine operation 507 is minimized.

[0047] <Configuration of simulation models> The configuration of the simulation model group will be further described. In the example shown in Fig. 6, command generation 501, pattern generation 502, speed control 504, current control 505, first machine operation 506, and second machine operation 507 are shown as simulation models used for analysis by analysis unit 421. That is, in the above configuration example, first machine operation 506, which is a simulation model for the operation of the motor, and second machine operation 507, which is a simulation model for the operation of the moving parts of injection molding machine 10, are provided as simulation models for the operation of injection molding machine 10.

[0048] Here, the operating characteristics of the motor that is the target of the simulation of the first machine operation 506 do not change when the injection molding machine 10 is used. In other words, the motor is a moving part of the injection molding machine 10 that is not affected by the manner of use. Therefore, the operating characteristics of the motor can be specified before shipping the injection molding machine 10. On the other hand, the operating characteristics of various moving parts of the injection molding machine 10 other than the motor may change significantly depending on the manner of use of the injection molding machine 10. Specifically, this can be the case when the inertia changes due to a change in the mold, or when the applied pressure changes due to different molding conditions or molding materials.

[0049] Therefore, in this embodiment, a first machine operation 506, which is a simulation model for the operation of the motor, and a second machine operation 507, which is a simulation model for the operation of the moving parts of the injection molding machine 10, are configured separately. By making the first machine operation 506 independent, it is possible to derive a simulation model for the first machine operation 506 before shipping the injection molding machine 10. Furthermore, for injection molding machines 10 that use the same motor, it is possible to apply the first machine operation 506 based on a common simulation model.

[0050] On the other hand, by separating the simulation model for the motor operation from the second machine operation 507, it is possible to derive a simulation model only for the operation of the moving parts excluding the motor, depending on the mode of use of the injection molding machine 10. Furthermore, to derive a simulation model, it is necessary to actually operate the injection molding machine 10 to obtain control information and information on operating characteristics, and then adjust the simulation model based on the obtained information. However, injection molding machines 10 generally do not have sensors for obtaining information on operating characteristics such as motor torque. Therefore, when deriving a simulation model depending on the mode of use of the injection molding machine 10 after shipment, it is easier to perform the derivation process if the simulation model for the motor part is separated.

[0051] Note that the first mechanical operation 506 is not essential to the simulation model used for analysis by the analysis unit 421. If the simulation using the first mechanical operation 506 is omitted, the current control 505, which outputs a voltage command to be input to the first mechanical operation 506, is also omitted. That is, an input variable extracted from the waveform data output from the speed control 504 may be directly input to the second mechanical operation 507. Even with this configuration, the operating speed of the moving part of the injection molding machine 10 can be estimated based on the output of the second mechanical operation 507. However, in this case, since the estimation of the operating characteristics of the motor by the first mechanical operation 506 is not reflected, the accuracy of the output estimated value is lower than when the first mechanical operation 506 is provided.

[0052] Similarly, pattern generation 502 and current control 505 are not essential. If pattern generation 502 is not provided, input variables extracted from the output of command generation 501 are input to the simulation model subsequent to pattern generation 502. If current control 505 is not provided, input variables extracted from the output of the simulation model subsequent to current control 505 are input to the simulation model subsequent to first machine operation 506. In either case, since the estimation by the omitted simulation model is not reflected, the accuracy of the estimated value output from second machine operation 507 is lower than when these simulation models are provided.

[0053] In the configuration example shown in Fig. 6, commands for operating the injection molding machine 10 are generated (simulated) using command generation 501 and pattern generation 502. Alternatively, commands for actually controlling the operations of the injection unit 20 and mold clamping unit 30 may be generated using the control device 100 of the injection molding machine 10. The generated commands are transmitted from the control device 100 to the information processing device 400. Then, the analysis unit 421 of the information processing device 400 generates pattern information by speed control 504 and current control 505 based on the acquired commands. The same applies to a modified example shown in Fig. 8, which will be described later.

[0054] <Application to the control device 100> After each simulation model has been adjusted as described above, the user executes a simulation using this simulation model in the information processing device 400. Then, the user generates control information for realizing a desired operation in accordance with the characteristics of the injection molding machine 10 based on the estimated values ​​obtained by the simulation in the information processing device 400, and sends the control information to the control device 100. The control device 100 controls the operation of the injection device 20 and the mold clamping device 30 based on the control information obtained from the information processing device 400, and carries out the process for manufacturing a molded product.

[0055] <Modification> FIG. 8 is a diagram showing another example of the configuration of a simulation model used for analysis by the analysis unit 421 of the processing unit 420 of the information processing device 400. The simulation model in the example shown in FIG. 8 may be configured by simulation models such as command generation 501, pattern generation 502, pressure control 503, speed control 504, current control 505, first mechanical operation 506, and second mechanical operation 507. The example configuration shown in FIG. 8 is different from the example configuration shown in FIG. 6 in that pressure control 503 is added. Pressure control 503 is provided between pattern generation 502 and speed control 504. That is, the output of pattern generation 502 is input to pressure control 503, and the output of pressure control 503 is input to speed control 504. The simulation models of command generation 501, pattern generation 502, speed control 504, current control 505, first mechanical operation 506, and second mechanical operation 507 are the same as the simulation models shown in FIG. 6.

[0056] In the configuration shown in FIG. 8, pressure control 503 is a simulation model that generates information indicating the control details of the moving parts of injection molding machine 10. Pressure control 503 outputs pattern information that indicates the pressure control details when injection molding machine 10 is operated in accordance with the commands generated by pattern generation 502. The pattern information is generated, for example, as waveform data. The format of the waveform data is not particularly limited, and it may be data in which values ​​are listed in CSV format or the like, or a waveform diagram. Analysis unit 421 that performs a simulation using pressure control 503 is an example of a pattern information generation unit.

[0057] 8, the analysis unit 421 generates pattern information of the moving parts that are the target of the simulation in the injection molding machine 10, using a simulation model of the pressure control 503. This pattern information is generated, for example, as waveform data that represents the relationship between the passage of time and changes in pressure. The analysis unit 421 then generates speed pattern information using the speed control 504.

[0058] 8, when pressure control 503 is provided, the output value of second mechanical operation 507 is fed back to pressure control 503. The analysis unit 421 compares the output value related to the pressure of second mechanical operation 507 with the output value of pressure control 503 to calculate an error. Then, the analysis unit 421 adjusts the simulation model of speed control 504 so that the error of the output value of pressure control 503 relative to the output value of second mechanical operation 507 is minimized.

[0059] In the example described above with reference to Fig. 6, the operating speed and current of the movable parts of the injection molding machine 10 are estimated, and in the modified example described with reference to Fig. 8, a simulation for estimating pressure is also described. In addition, by selecting waveform data that can be acquired from the output of a sensor or the like from the injection molding machine 10, it is possible to obtain estimated values ​​for the force acting on the movable parts, such as the mold clamping force, the acceleration of the movable parts, the position of the movable parts (displacement, rotation angle, etc.), the position of the platen, and the like.

[0060] <Example of how to derive a machine learning model> Next, a specific example of a method for deriving a machine learning model used as a simulation model for the first machine operation 506 and the second machine operation 507 will be described. As an example, a derivation example of a simulation model for the operation of a motor used in the first machine operation 506 will be described. First, a linear multiple regression model, which is an example of a machine learning model, will be described, and then a method for deriving the machine learning model will be described.

[0061] FIG. 9 is a diagram illustrating an example of the configuration of a linear multiple regression model. The illustrated linear multiple regression model receives multiple inputs, performs analysis by using multiple nodes representing multiple processing units, taking into account the correlation between the inputs, and obtains a single output. In the model illustrated in FIG. 9, x1 to x3 are input variables, and y1 is the output. w1 to w4 written in each node of the hidden layer represent weights set for each node. That is, in the model illustrated in FIG. 9, when input variables x1 to x3 are given, output y1 is obtained through processing using weights w1 to w4 at each node. Then, by changing the weights w1 to w4 at each node, a different output y1 can be obtained for the same input variables x1 to x3. Note that the number of input variables and nodes illustrated in FIG. 9 is merely an example and is not limited to the illustrated number.

[0062] When the linear multiple regression model shown in Fig. 9 is applied to the relationship between current and voltage, for example, actual currents are input to the input variables x1 to x3, and for example, a voltage command is obtained as the output y1. Then, for example, physical constants are set as the weight values ​​w1 to w4 of each node. The type of physical constant set for the weight values ​​w1 to w4 is selected according to the physical quantity to be analyzed. For example, when the actual current of a motor is used as the input and the voltage command is used as the output, physical constants such as the motor's resistance value (R), d-axis inductance (Ld), q-axis inductance (Lq), back electromotive force constant (Ke), torque constant (Kt), viscous friction (Dm), inertia (J), etc. can be assigned to each node to set the weight values.

[0063] FIG. 10 is a diagram showing a method for deriving a machine learning model. The simulation model of the first machine operation 506 is derived by analyzing waveform data acquired from the injection molding machine 10, which is the equipment to be controlled, through supervised learning using a linear multiple regression model, such as that described with reference to FIG. 9. As an example, the simulation model here is a model that obtains voltage and acceleration from the actual current and speed of the motor. Note that in FIG. 10, the intermediate layer in the model is summarized and depicted as a single node.

[0064] First, the d-axis current, q-axis current, and speed are extracted as input variables X from the waveform data acquired from the injection molding machine 10 and input to the simulation model. Also, actual values ​​(Y(actual)) of the d-axis voltage, q-axis voltage, and acceleration are extracted from the waveform data. These actual values ​​correspond to the output contents calculated by the simulation model based on the input variables d-axis current, q-axis current, and speed.

[0065] On the other hand, the simulation model obtains the d-axis voltage, q-axis voltage, and acceleration as outputs (Y) based on the input d-axis current, q-axis current, and speed. Here, the d-axis voltage, q-axis voltage, and acceleration are each calculated based on the d-axis current, q-axis current, and speed, respectively.

[0066] Next, the actual values ​​(Y(actual)) of the d-axis voltage, q-axis voltage, and acceleration extracted from the waveform data are compared with the output (Y) of the d-axis voltage, q-axis voltage, and acceleration obtained using the simulation model, and an error is calculated. Then, the weight value W of each node in the hidden layer is modified to minimize this error, in other words, so that the output (Y) of the d-axis voltage, q-axis voltage, and acceleration matches the actual values ​​(Y(actual)) of the d-axis voltage, q-axis voltage, and acceleration. Once the weight value W that minimizes the error between the output (Y) of the d-axis voltage, q-axis voltage, and acceleration and the actual values ​​(Y(actual)) of the d-axis voltage, q-axis voltage, and acceleration is obtained, this weight value W represents the characteristics of the motor of the injection molding machine 10 from which the input waveform data was obtained.

[0067] In the above example, an example of derivation of a simulation model of the operation of the motor used in the first machine operation 506 was described. The same procedure is followed for deriving a simulation model of the operation of the moving part used in the second machine operation 507. When deriving the simulation model of the second machine operation 507, input variables and output variables are set according to the operation of the moving part to be simulated. As mentioned above, the simulation model of the moving part that is the target of the simulation of the second machine operation 507 may need to be changed if the usage mode of the injection molding machine 10 is changed. Therefore, when the usage mode of the injection molding machine 10 is changed, the injection molding machine 10 is operated to obtain physical quantities related to the operation of the moving part in the new usage mode, input variables and output variables are set, a simulation is performed, and the simulation model is adjusted.

[0068] Although the embodiments of the present invention have been described above, the technical scope of the present invention is not limited to the above embodiments. For example, in the above embodiments, the waveform data is analyzed in the information processing device 400 connected to the injection molding machine 10, and control information is generated. However, the waveform data may be analyzed in the control device 100 or data processing device 200 of the injection molding machine 10, and control information may be generated. In other words, the functions of the information processing device 400 may be implemented in the injection molding machine 10. Various other modifications and alternative configurations that do not depart from the scope of the technical concept of the present invention are included in the present invention. [Explanation of symbols]

[0069] 10... injection molding machine, 20... injection device, 30... mold clamping device, 100... control device, 200... data processing device, 400... information processing device, 410... communication unit, 420... processing unit, 421... analysis unit, 430... storage unit, 431... simulation model, 501... command generation, 502... pattern generation, 503... pressure control, 504... speed control, 505... current control, 506... first machine operation, 507... second machine operation

Claims

1. a first estimation unit that estimates an operation of a first movable part, which is a part of a movable part of the control-target device that is not affected in operation by a usage mode, using a simulation model of the first movable part based on a command to control an operation of the control-target device; a second estimation unit that receives an estimation result from the first estimation unit and estimates an operation of a second moving part, which is a moving part of the controlled device whose operation is affected by a usage mode, using a simulation model of the second moving part; An information processing system comprising:

2. The information processing system according to claim 1 , wherein the first estimating unit estimates an operation of a motor that is a drive source of the controlled device as the first moving part.

3. a command generation unit that receives information about an operating condition of the control target device and generates the command based on the received information; The information processing system according to claim 1 , wherein the first estimation unit receives the command generated by the command generation unit and performs estimation regarding the operation of the first movable part.

4. a pattern information generating unit that generates pattern information related to the operation of the control target device based on the command, the first estimation unit receives the pattern information generated by the pattern information generation unit and performs estimation regarding the operation of the first movable part; 2. The information processing system according to claim 1, wherein the pattern information generating unit modifies a calculation model for generating the pattern information based on an estimation result of at least one of the first estimating unit and the second estimating unit.

5. an injection device and a mold clamping device that perform the injection molding process; a control device that controls the operations of the injection device and the mold clamping device, The control device An information processing system according to any one of claims 1 to 4; a control unit that controls operations of the injection unit and the mold clamping unit based on control information that reflects the estimation result by the information processing system; An injection molding machine comprising:

6. Computer, a first estimation means for estimating an operation of a first movable part, which is a part of a movable part of the control target device whose operation is not affected by a usage mode, using a simulation model of the first movable part based on a command for controlling the operation of the control target device; second estimation means for receiving an estimation result from the first estimation means and performing estimation regarding an operation of a second movable part, which is a part of the movable parts of the controlled device whose operation is affected by a usage mode, using a simulation model of the second movable part; A program characterized by causing the program to function.

Images