Information processing system, program and manufacturing method for injection molding machine

Abstract

To provide information for restricting a difference in device operation due to a device difference, by deriving the device difference in a relationship between physical quantities of the devices as a characteristic of a control target, and realizing control corresponding to the characteristic of each of such devices.SOLUTION: Waveform data obtained by an operation of a control target device is acquired, and based on a relationship between variables included in the acquired waveform data, an input variable as a first variable, which is at least a part of the variables, and an actual value as a second variable which is at least another part of the variables are extracted. Then, an output value as a variable corresponding to the second variable is derived based on the input variable as the first variable; a characteristic of the control target device is obtained based on the derived output variable and the actual value as the second variable; and information used for control of the control target device is output based on the characteristic of the control target device and is sent to the control target device.SELECTED DRAWING: Figure 8

Description

[Technical field]

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

[0002] In controlling equipment, control gains such as PI (Proportional-Integral) control gains are used. The response of the controlled object is determined by the control gain and the characteristics of the controlled object. Therefore, the control gain can be calculated backwards once the characteristics of the controlled device and the desired response are determined.

[0003] Patent Document 1 discloses a control system including a status observation unit that observes information related to the machine as status data, a judgment data acquisition unit that acquires information related to processing as judgment data, a reward calculation unit that calculates a reward based on the judgment data and reward conditions, a learning unit that machine-learns adjustment of the machine's servo gain, a decision-making unit that determines adjustment actions for the machine's servo gain based on the machine learning results of the machine's servo gain adjustment and the status data, and a gain change unit that changes the machine's servo gain based on the determined servo gain adjustment action. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Patent No. 6457472 Summary of the Invention [Problem to be solved by the invention]

[0005] Although the physical quantities detected by devices have mutual relationships, there are physical quantities for which the relationships vary (machine differences) for each device. If such machine differences exist, the response to control will differ for each device even if control is performed with the same control gain.

[0006] The present invention aims to provide information for determining the characteristics of a controlled object in terms of the relationship between physical quantities of the equipment, realizing control according to the characteristics of each such equipment, and suppressing differences in the operation of the equipment due to differences between machines. [Means for solving the problem]

[0007] One aspect of the present invention is an information processing system comprising: an acquisition unit that acquires waveform data obtained by the operation of a controlled device; an analysis unit that extracts a first variable which is at least a portion of the variables and a second variable which is at least another portion of the variables based on the relationship between variables contained in the acquired waveform data, derives a variable corresponding to the second variable based on the first variable, and determines characteristics of the controlled device based on the derived variable and the second variable; and an output unit that outputs information used to control the controlled device based on the characteristics of the controlled device. Effect of the Invention

[0008] According to one aspect of the present invention, it is possible to determine the characteristics of the controlled object in terms of the relationship between the physical quantities of the equipment, realize control according to the characteristics of each such equipment, and provide information for suppressing differences in the operation of the equipment due to differences between machines. [Brief description of the drawings]

[0009] [Figure 1] 1 is a diagram showing a configuration of an injection molding machine to which the present embodiment is applied; [Diagram 2] FIG. 2 is a diagram illustrating a configuration of a control device. [Diagram 3] FIG. 1 illustrates a configuration of a data processing device. [Figure 4] FIG. 1 is a diagram illustrating a configuration of an information processing device. [Diagram 5] FIG. 2 is a diagram illustrating an example of a hardware configuration of a computer that realizes an information processing device. [Figure 6] 6A and 6B are diagrams showing an example of the adjustment of the machine difference, and FIG. 6B is a diagram showing the state after the machine difference has been adjusted. [Figure 7]FIG. 1 is a diagram illustrating a configuration of a linear multiple regression model. [Figure 8] FIG. 11 is a diagram illustrating an example of an analysis process performed by an analysis unit. [Figure 9] 5 is a flowchart showing a procedure for adjusting control information in accordance with device characteristics in an injection molding machine. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0010] 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 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.

[0011] The injection device 20 is configured to include a cylinder for heating the molding material, a screw that is rotatable in the cylinder and axially movable, a rotary motor for driving the screw in the rotational direction, and a motor for driving the screw in the axial direction. The molding material is, for example, a resin. The injection device 20 rotates the screw while advancing it in a direction (forward) from the injection device 20 toward the mold clamping device 30, thereby injecting the molding material that has been heated and turned into a liquid in the cylinder, and filling it into the mold of the mold clamping device 30 disposed in front of the injection device 20. The injection device 20 performs, for example, a metering process, a filling process, a pressure holding process, and the like in the manufacturing process of the molded product. The filling process and the pressure holding process are collectively referred to as the injection process.

[0012] The clamping device 30 is configured to include a mold, a clamping mechanism for clamping the mold, a motor for driving the clamping mechanism, and the like. The clamping device 30 closes the mold and receives the molding material injected from the injection device 20 into the inside of the mold. At this time, the clamping device 30 clamps the mold using the clamping mechanism so that the mold will 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 clamping device 30 opens the mold, making it possible to remove the produced molded product. The clamping device 30 performs, for example, a mold closing process, a pressure increase process, a mold clamping process, a pressure release process, a mold opening process, and the like in the manufacturing process of the molded product.

[0013] 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.

[0014] 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 obtains the characteristics of the injection molding machine 10 based on the acquired waveform data. These characteristics include factors that cause machine differences in the individual injection molding machines 10. The information processing device 400 outputs information for performing control to suppress machine differences in the individual injection molding machines 10 based on the information on the obtained characteristics of the injection molding machines 10, and provides the information to the control device 100. Details of the processing by the information processing device 400 and the information output will be described later.

[0015] <Configuration of the control device 100> FIG. 2 is a diagram showing the configuration of the control device 100. The control device 100 controls the operations of the injection device 20 and the mold clamping device 30. The control device 100 is realized by, for example, a computer. The control device 100 includes a control unit 110 and a storage unit 120. The control device 100 controls the injection device 20 and the mold clamping device 30 to repeatedly perform the processes related to the manufacture of the molded product, thereby repeatedly manufacturing the molded product. The processes related to the manufacture of the molded product include a metering process, a mold closing process, a pressure increase process, a mold clamping process, a filling process, a pressure holding process, a cooling process, a depressurization process, a mold opening process, and an ejection process. Hereinafter, these manufacturing processes may be collectively referred to as a "manufacturing process." In addition, a series of operations for obtaining a molded product, for example, an operation from the start of a metering process in the above manufacturing process to the start of the next metering process, is called a "shot," a "molding cycle," or the like. Note that the above-mentioned processes for manufacturing a molded product are merely examples. For example, the process may include other processes not included in the above as processes executed in one shot.

[0016] The control unit 110 controls the injection unit 20 and the 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 pressure hold time, measurement value, VP switching position, pressure hold pressure, injection speed (filling speed), screw rotation speed, screw back pressure, and clamping force. A plurality of combinations of these molding conditions are determined according to the molded product and the mold. The combination data of the molding conditions is hereinafter also referred to as a molding condition data set. The control information also includes control data such as voltage, current, pressure, speed, and acceleration for the driving unit such as the mechanism and the motor. The molding condition data set is prepared according to the type of the molded product and the mold, and is stored in the storage unit 120.

[0017] The control unit 110 controls the injection unit 20 and the clamping unit 30 using the above molding condition data set, and performs the process related to the production (shot) of a molded product, including each of the above processes. The control unit 110 reads out the molding condition data set corresponding to the molded product to be produced from the storage unit 120, for example, at the start of production of the molded product. The control unit 110 then controls the operation of the injection unit 20 and the 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 clamping unit 30 so that data obtained from the injection unit 20 and the clamping unit 30 in the production process matches the set values ​​of the molding condition data set.

[0018] The storage unit 120 holds control information used by the control unit 110 to control the injection unit 20 and the clamping unit 30. The molding condition data sets included in the control information are prepared in correspondence with the molded product and the mold to be manufactured. The storage unit 120 holds molding condition data sets for each molded product and each mold to be manufactured. Although not shown, the storage unit 120 also holds a program for the control unit 110 to control the injection unit 20 and the clamping unit 30. As will be described in detail later, the processor in the control device 100 reads and executes the program held in the storage unit 120, thereby realizing the function of the control unit 110.

[0019] <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 execute operations in the processes related to the manufacture of the above-mentioned molded products. 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.

[0020] The data acquisition unit 210 acquires data to be processed from the injection unit 20 and the clamping unit 30. Various sensors, detectors, etc. are attached to the injection unit 20 and the clamping unit 30. In addition, various measuring instruments may be connected to the injection unit 20 and the clamping unit 30. Data acquired using these sensors, detectors, measuring instruments, etc. (hereinafter referred to as "acquired data") is information that represents the molding results by the injection unit 20 and the 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 instruments, etc., and stores it in the memory unit 230.

[0021] 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, identifying a possible range of values, and identifying maximum and minimum values.

[0022] The storage unit 230 holds the acquired data acquired by the data acquisition unit 210. For example, binary, text, CSV (Comma Separated Values), INI, YAML (YAML Ain't Markup Language), JSON (JavaScript Object Notation), etc. may be used as the data format of the acquired data held in the storage unit 230. By making the data file in such a general-purpose data format, it becomes possible to exchange data files held in the storage unit 230 with other information processing devices, or to edit data files acquired from external devices. Although not shown, the storage unit 230 holds a program for the processing unit 220 to execute data processing. Although the details will be described later, the processor in the data processing device 200 reads and executes the program held in the storage unit 230, thereby realizing the function of the processing unit 220.

[0023] <Configuration of information processing device 400> 4 is a diagram showing a configuration of the information processing device 400. The information processing device 400 acquires waveform data obtained by the operation of the injection molding machine 10 to obtain characteristics of the injection molding machine 10, and outputs information used to control the injection molding machine 10 based on the information of the obtained characteristics. 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 analyzes the characteristics of the injection molding machine 10 using a machine learning model. The storage unit 430 holds the machine learning model 431 used for analysis by the analysis unit 421.

[0024] The communication unit 410 receives waveform data obtained by the operation of the injection molding machine 10 from the control device 100 and the data processing device 200. The data to be received may be various data obtained as waveform data during the operation of the injection molding machine 10. Specifically, for example, data such as voltage and current supplied to various mechanisms, and speed, acceleration, and pressure during the operation of various mechanisms may be included. The communication unit 410 also transmits information used for controlling the injection molding machine 10 obtained by processing of the processing unit 420 to the control device 100. The communication unit is an example of an acquisition unit.

[0025] The processing unit 420 performs a process of obtaining the characteristics of the injection molding machine 10 using the waveform data received by the communication unit 410. The processing unit 420 extracts input variables to be input to the machine learning model and actual values ​​to be used for verification from the acquired waveform data, and inputs them to the analysis unit 421. The input variables are an example of a first variable, and the actual values ​​are an example of a second variable. Here, the input variables and the actual values ​​are variables having a mutual relationship. That is, when the value of the input variable changes, the value of the actual value also changes accordingly. In addition, the processing unit 420 outputs information for controlling the injection molding machine 10 based on the analysis result by the analysis unit 421, and causes the communication unit 410 to transmit the information to the control device 100. The processing unit 420 is an example of an output unit.

[0026] The analysis unit 421 inputs the input variables out of the input input variables and performance values ​​to the machine learning model 431, and derives a variable corresponding to the performance value (hereinafter referred to as an "output value"). The analysis unit 421 is an example of a machine learning device. Next, the analysis unit 421 compares the performance value with the output value, and calculates an error. Then, the analysis unit 421 adjusts the machine learning model 431 so that the error of the output value relative to the performance value becomes smaller. The process by the analysis unit 421 and the machine learning model 431 will be described in detail later.

[0027] The storage unit 430 holds the waveform data received by the communication unit 410, information obtained by processing by the processing unit 420, a machine learning model 431 used by the analysis unit 421 of the processing unit 420, etc. The data format of the data file held in the storage unit 430 may be, for example, CSV, XML (Extensible Markup Language), JSON, etc.

[0028] <Hardware configuration of information processing device 400> FIG. 5 is a diagram showing an example of a hardware configuration of a computer that realizes an information processing device 400. The computer shown in FIG. 5 includes a processor 401, which is a calculation means, and a main memory 402 and an auxiliary memory 403, which are storage means. As the processor 401, for example, a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), an ASIC (Application Specific Integrated Circuit), an FPGA (Field-Programmable Gate Array), or other various calculation circuits can be used. The processor 401 reads a program stored in the auxiliary memory 403 into the main memory 402 and executes it. As the main memory 402, for example, a RAM (Random Access Memory) is used. As the auxiliary memory 403, for example, a magnetic disk device, an SSD (Solid State Drive), or the like is used.

[0029] The computer may also be configured to include a display device 404 for displaying an image, and an input device 405 as an input means for performing an input operation by a computer user. 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 an input operation by touching the operation screen displayed on the display device 404 with a finger or a pen-type device. Note that the configuration of the computer shown in FIG. 5 is merely an example, and the computer used in this embodiment is not limited to the configuration example of FIG. 5. For example, the computer may be configured to include a non-volatile memory such as a flash memory or a ROM (Read Only Memory) as a storage device.

[0030] 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.

[0031] <Instrumental differences between controlled devices> Fig. 6 is a diagram showing a model of the adjustment of the machine difference, Fig. 6(A) is a diagram showing an example of the machine difference, and Fig. 6(B) is a diagram showing the state after the machine difference is adjusted. Fig. 6(A) and (B) are waveform diagrams showing the speed on the vertical axis and the time on the horizontal axis in the case where the operating speed of the controlled device changes over time. In Fig. 6(A) and (B), the dashed lines are waveform diagrams showing the control information, and the solid lines are waveform diagrams showing the performance data.

[0032] Even if the machines, such as the injection molding machine 10, are the same model, they usually have some machine differences, which causes differences in operation. For example, consider a case where the speed is controlled as shown in FIG. 6 by changing the motor current value. In this case, even if the motor current value can be controlled to be in a desired state, if there is a machine difference, the speed obtained in each machine will vary as shown in FIG. 6(A). Even if the speed and position are detected by a sensor, fed back, and the current value is controlled to finally converge to the desired speed, the time lag and overshoot that occur until the desired speed is reached will differ depending on the machine difference. In the example shown in FIG. 6(A), the speed changes (solid lines) of three machines controlled according to one control information (dashed lines) are shown. In the example shown in FIG. 6(A), the three machines show different speed changes while being controlled by the same control information.

[0033] In this embodiment, such machine differences are treated as characteristics of each device, and the motor current value is controlled to suppress the machine differences, thereby realizing speed control with machine differences suppressed. In the example shown in Fig. 6(B), the speed changes of the three devices are shown according to the same control information (dashed lines) as in the example shown in Fig. 6(A). In the example shown in Fig. 6(B), the machine differences of the three devices are suppressed, and they show the same speed changes due to control based on the same control information.

[0034] Here, the relationship between the current value and the speed has been described as an example, but the application of this embodiment is not limited to the above example. Some physical quantities detected by a sensor or the like in an apparatus have a relationship with each other. This embodiment can be applied to physical quantities having such a relationship, and the relationship varies depending on the apparatus. For example, the relationship between current and voltage, and the relationship between speed and acceleration can be mentioned. In the relationship between current and voltage, since there is a machine difference in electrical resistance, even if the same amount of current flows, the voltage value obtained by the apparatus may be different. In addition, in the relationship between speed and acceleration, since there is a machine difference in the inertia of the member to be operated in the apparatus, even if it is operated at the same speed, the acceleration may differ depending on the apparatus. By applying this embodiment to various physical quantities in these controlled apparatuses, it is possible to realize control that suppresses the machine difference between each apparatus and causes the same operation.

[0035] The information processing device 400 analyzes waveform data of physical quantities having mutual relationships as described with reference to Figs. 6(A) and (B) and identifies the characteristics of each injection molding machine 10, which is a device to be controlled. Then, information for performing control according to the characteristics of each injection molding machine 10 is generated and provided to the control device 100. As a means for analyzing the waveform data, the processing unit 420 of the information processing device 400 uses a machine learning model 431. As the machine learning model 431, for example, a linear multiple regression model can be used.

[0036] In addition to the linear multiple regression model, it is also possible to use a linear regression model or other mathematical models as a means for analyzing waveform data. However, by using a linear multiple regression model, it is easier to build a learning model compared to other means. This is because waveform data has multiple variables, and it is possible to collect correct answer data regarding input and output, and the data that can become multiple input variables of the waveform data is data that can be expressed by four arithmetic operations (including data expressed by approximate calculation formulas). For this reason, it can be said that analysis of waveform data is compatible with the characteristics of supervised machine learning for linear multiple regression models. As a result, the operation of operating a machine using a test device to obtain supervised data, learning to build a machine learning model, and determining parameters through calculations using the built machine learning model can be performed in an extremely short time compared to manually adjusting various parameters such as voltage, current, and speed.

[0037] FIG. 7 is a diagram showing the configuration of a linear multiple regression model. The linear multiple regression model used in the machine learning model 431 receives multiple inputs, performs analysis by multiple nodes representing multiple processing units, taking into account the correlation between the inputs, and obtains a single output. In the model shown in FIG. 7, x1 to x3 are input variables, and y1 is an output. w1 to w4 written in each node of the intermediate layer represent weight values ​​set in each node. That is, in the model shown in FIG. 7, when input variables x1 to x3 are given, output y1 is obtained through processing using weight values ​​w1 to w4 in each node. Then, by changing weight values ​​w1 to w4 of each node, different output y1 is obtained for the same input variables x1 to x3. Note that the number of input variables and nodes shown in FIG. 7 is merely an example and is not limited to the number shown.

[0038] When the linear multiple regression model shown in FIG. 7 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. For example, physical constants are set to the weight values ​​w1 to w4 of each node. The type of physical constant set to 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 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.

[0039] FIG. 8 is a diagram showing an example of analysis processing by the analysis unit 421. The analysis unit 421 analyzes waveform data acquired from the injection molding machine 10, which is a controlled device, by supervised learning using the machine learning model 431 (linear multiple regression model) as described with reference to FIG. 7, and identifies the characteristics of the device. The format of the waveform data is not particularly limited. For example, it may be data in which values ​​are listed in CSV or the like, or it may be a waveform diagram. Here, as an example, the machine learning model 431 is a model that obtains voltage and acceleration from the current performance and speed performance of a motor. Note that in FIG. 8, the intermediate layer of the machine learning model 431 is summarized and described as one node.

[0040] The analysis unit 421 extracts the d-axis current, the q-axis current, and the speed as the input variable X from the waveform data acquired from the injection molding machine 10, and inputs them to the machine learning model 431. The analysis unit 421 also extracts the actual values ​​(Y(actual)) of the d-axis voltage, the q-axis voltage, and the acceleration from the input waveform data. These actual values ​​correspond to the output contents calculated by the machine learning model 431 based on the input variables of the d-axis current, the q-axis current, and the speed.

[0041] On the other hand, the machine learning model 431 derives a d-axis voltage, a q-axis voltage, and an acceleration as an output (Y) based on the input d-axis current, q-axis current, and speed. Here, the d-axis voltage, the q-axis voltage, and the acceleration are each calculated based on the d-axis current, the q-axis current, and the speed, respectively.

[0042] Next, the analysis unit 421 compares the actual values ​​(Y(actual)) of the d-axis voltage, q-axis voltage, and acceleration extracted from the waveform data with the output (Y) of the d-axis voltage, q-axis voltage, and acceleration obtained using the machine learning model 431, and calculates an error. Then, the weight value W of each node in the intermediate layer is corrected so that this error is minimized, 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. Then, if a 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 is obtained. The difference in this characteristic in the injection molding machine 10, which is the controlled device, is an example of a machine difference between each injection molding machine 10.

[0043] In the above description, the analysis unit 421 corrects the weight value W so that the error between the output (Y) of the d-axis voltage, the q-axis voltage, and the acceleration and the actual value (Y(actual)) of the d-axis voltage, the q-axis voltage, and the acceleration is minimized, but this is merely an example. For example, instead of the above processing, the analysis unit 421 may correct the weight value W so that this error becomes smaller than a predetermined threshold. In this case, an analysis using the machine learning model 431 in which the weight value W is corrected can obtain the output (Y) of the d-axis voltage, the q-axis voltage, and the acceleration that is close to the actual value (Y(actual)) of the d-axis voltage, the q-axis voltage, and the acceleration.

[0044] In the example of the analysis process shown in FIG. 8, an example was described in which the actual values ​​(Y(actual)) of the d-axis voltage, q-axis voltage, and acceleration extracted from the waveform data were compared with the output (Y) of the d-axis voltage, q-axis voltage, and acceleration obtained using the machine learning model 431 to calculate the error, but these variables are not limited to the above example, and the comparison and error calculation may be performed using another variable having a causal relationship. For example, instead of the actual value and output of the acceleration, a value obtained using a time derivative of the speed or an approximate calculation formula may be used. Also, instead of the actual value and output of the voltage, a duty (ON-OFF ratio) value of the inverter may be used. Also, as the speed at the input, instead of speed data directly obtained by a sensor or the like, a speed value calculated from the difference in position data of the encoder may be used. Also, instead of the actual current, a voltage value output from a current detector may be used as an input.

[0045] <Adjusting the characteristics of the controlled device> The processing unit 420 of the information processing device 400 generates information (hereinafter referred to as "characteristic adjustment information") for performing control to suppress the machine difference between the injection molding machine 10 and other injection molding machines, based on the information on the characteristics of the injection molding machine 10 obtained as described above. As an example of such characteristic adjustment information, the processing unit 420 may generate a gain for correcting the control information used by the control device 100 to control the injection unit 20 and the mold clamping unit 30. The gain is a coefficient multiplied by a value used as the control information to compensate for the deviation based on the characteristics of the injection molding machine 10. The control device 100 corrects the control information using the gain acquired from the information processing device 400, and controls the injection unit 20 and the mold clamping unit 30. In this way, it is not necessary to change the design of the control information itself held by the control unit 110 of the control device 100 based on the characteristics (weight value W) of the injection molding machine 10 analyzed by the analysis unit 421, and it is only necessary to correct the control information already held by the control unit 110, so that it is possible to suppress an increase in the scale of design change.

[0046] On the other hand, the processing unit 420 may generate control information used by the control device 100 to control the injection device 20 and the mold clamping device 30 based on the characteristics (weight value W) of the injection molding machine 10 analyzed by the analysis unit 421 as the characteristic adjustment information. The control device 100 replaces the control information held by the control unit 110 with the control information acquired from the information processing device 400, and controls the injection device 20 and the mold clamping device 30. The processing unit 420 may also transmit the information on the characteristics (weight value W) of the injection molding machine 10 analyzed by the analysis unit 421 as it is to the control device 100 as the characteristic adjustment information. In this case, the control device 100 generates a gain based on the information on the characteristics of the injection molding machine 10 acquired from the information processing device 400 to correct the control information, or generates control information reflecting the characteristics.

[0047] 9 is a flowchart showing a procedure for adjusting control information according to the characteristics of the equipment in the injection molding machine 10. First, in the injection molding machine 10, the control device 100 operates the injection device 20 and the mold clamping device 30 (S101), and the data processing device 200 acquires sensor information detected in association with the operation of the injection device 20 and the mold clamping device 30 (S102). Then, the control device 100 and the data processing device 200 transmit waveform data obtained by the operation of the injection device 20 and the mold clamping device 30 to the information processing device 400 (S103).

[0048] The information processing device 400 analyzes the waveform data received from the control device 100 and the data processing device 200 to obtain the characteristics of the injection molding machine 10 (S104), and transmits characteristic adjustment information based on the obtained characteristics to the control device 100 of the injection molding machine 10 (S105). When the control device 100 receives the characteristic adjustment information from the information processing device 400 (S106), it adjusts the control information for controlling the injection device 20 and the mold clamping device 30 based on the received characteristic adjustment information (S107). After this, the control device 100 of the injection molding machine 10 controls the injection device 20 and the mold clamping device 30 using the control information adjusted to reflect the unique characteristics of each device. Then, the control by the control device 100 is changed and control according to the characteristics of the device is performed, thereby suppressing the machine difference in control of the device with other devices.

[0049] Although the embodiment of the present invention has been described above, the technical scope of the present invention is not limited to the above embodiment. For example, in the above embodiment, the waveform data is analyzed in the information processing device 400 connected to the injection molding machine 10, and the characteristic adjustment information is generated. However, the waveform data may be analyzed in the data processing device 200 of the injection molding machine 10, and the characteristic adjustment information may be generated.

[0050] In the above embodiment, the suppression of differences between devices has been described, but the present embodiment can also be applied to cases where the characteristics of the same device change based on differences in the operating environment, etc. For example, the characteristics of the injection molding machine 10 change due to changes in the type of resin used as the molding material, changes in the mold, changes in the outside air temperature, etc. Therefore, a configuration may be adopted in which waveform data is acquired in response to these environmental changes and fluctuations, the characteristics of the device in each environment are identified, and control is performed in accordance with these characteristics.

[0051] Furthermore, when generating gains in control as equipment adjustment information, this embodiment can be widely applied to gains whose design methods are established in control engineering, such as proportional gains and integral gains in PI control of current, speed, pressure, etc., noise filter coefficients, feedforward gains, etc. In addition, various 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]

[0052] 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... machine learning model

Claims

1. An acquisition unit that acquires waveform data obtained by an operation of a controlled device; an analysis unit that extracts first variables that are at least a portion of the variables and second variables that are at least a portion of the variables based on a relationship between variables included in the acquired waveform data, derives variables corresponding to the second variables based on the first variables, and determines characteristics of the controlled device based on the derived variables and the second variables; an output unit that outputs information used to control the controlled device based on the characteristics of the controlled device; An information processing system comprising:

2. 2. The information processing system according to claim 1, wherein the analysis unit uses a linear multiple regression model that inputs a plurality of the first variables and obtains one output through a plurality of processes in an intermediate layer, and derives the variable corresponding to the second variable as the output.

3. The information processing system according to claim 2, characterized in that the analysis unit modifies weight values ​​set for the multiple processes in the intermediate layer so as to reduce an error between the derived variable and the second variable, and the modified weight values ​​are used as information representing the characteristics of the controlled device.

4. The information processing system according to claim 3 , wherein the information output by the output unit is information on a gain in controlling the controlled device, the information being generated based on the weight value after correction.

5. Computer, A means for acquiring waveform data obtained by the operation of a controlled device; a means for extracting a first variable which is at least a part of the variables and a second variable which is at least another part of the variables based on a relationship between variables included in the acquired waveform data, deriving a variable corresponding to the second variable based on the first variable, and determining a characteristic of the controlled device based on the derived variable and the second variable; As a means for outputting information used for controlling the controlled device based on the characteristics of the controlled device, A program characterized by:

6. A step of operating the injection molding machine to obtain waveform data; extracting first variables which are at least a part of the variables and second variables which are at least another part of the variables based on relationships between variables included in the acquired waveform data, deriving variables corresponding to the second variables based on the first variables, and determining characteristics of the injection molding machine based on the derived variables and the second variables; adjusting control information of the injection molding machine based on characteristics of the injection molding machine; A method for manufacturing an injection molding machine, comprising:

Images