Procedure creation support device, procedure creation support method, and procedure creation support program

Abstract

To support in determining operating conditions during non-steady-state operation of a plant.SOLUTION: A procedure creation support device includes a processing unit that executes: acquiring process data output during past non-steady operation of a plant; creating a trained model that uses process data-based feature values as an explanatory variables and is trained their relationship with a predetermined objective variable through regression analysis; performing a simulation using the trained model and expected values of the explanatory variables; outputting regression coefficients of the trained model, simulation results, and conditions that are predetermined constraints on the explanatory variables; modifying the trained model when an operation to modify the explanatory variables is received from a user, or performing a simulation using the modified expected values when an operation to modify the expected values is received from a user.SELECTED DRAWING: Figure 2

Description

[Technical field]

[0001] The present disclosure relates to a procedure creation support device, a procedure creation support method, and a procedure creation support program. [Background technology]

[0002] Conventionally, a system for optimizing plant operating conditions has been proposed (Patent Document 1). The measurement data recording unit in this system records the operating state data acquired by the operating state data acquisition unit and the operating index data obtained by the operating index data acquisition unit as a series of measurement data associated based on predetermined items in a measurement DB. In addition, the regression model creation unit creates a regression model by performing a predetermined multivariate analysis using operating state variables representing the operating state data side as explanatory variables and operating index variables representing the operating index data side as objective variables. In addition, the operation index variable optimization unit determines operating state variables that optimize the operation index variables based on the regression model. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2012-74007 A Summary of the Invention [Problem to be solved by the invention]

[0004] For example, in unsteady operation such as during start-up of a plant from the start of operation to steady operation, the causal relationships of the effects of the operating conditions on product quality and cost are complex, and it is not easy to find desirable operating conditions. Therefore, an object of the present disclosure is to provide a technology for supporting the determination of operating conditions in unsteady operation of a plant. [Means for solving the problem]

[0005] The procedure creation support device according to the present disclosure can be realized in the following manner. (Aspect 1) Obtaining process data output during past unsteady operation of a plant; Creating a trained model in which a relationship between a feature quantity based on the process data and a predetermined objective variable is trained by regression analysis using the feature quantity as an explanatory variable; Performing a simulation using the trained model and the expected values ​​of the explanatory variables; Outputting the regression coefficients of the trained model, the results of the simulation, and predetermined constraint conditions regarding the explanatory variables; When an operation to modify an explanatory variable is received from a user, the trained model is modified, or when an operation to modify an expected value is received from a user, a simulation is performed using the modified expected value. A procedure creation support device comprising a processing unit that executes the above. (Aspect 2) The processing unit outputs the regression coefficient of the trained model or the absolute value of the regression coefficient as an index of the magnitude of the effect of the explanatory variable multiplied by the regression coefficient in the trained model on the change in the objective variable. 2. A procedure creation support device according to claim 1. (Aspect 3) The constraints include being within the range of explanatory variables based on process data output during past non-stationary operations. 3. The procedure creation support device according to claim 1 or 2. (Aspect 4) When a sign of a regression coefficient is specified by a user, the trained model performs a regression analysis using a regularization term that increases a cost when the sign of the regression coefficient differs from that specified by the user, so as to minimize a cost function including the regularization term; The constraint condition includes causal information about the direction in which one explanatory variable should be increased or decreased in order to change the target variable to a value in the steady-state operation of the plant. 4. A procedure creation support device according to any one of aspects 1 to 3. (Aspect 5) Causal information includes multiple pieces of information that indicate the direction in which explanatory variables should be increased or decreased based on different perspectives. 5. A procedure creation support device according to claim 4.

[0006] The content of the means for solving the problem may be provided as an apparatus such as a computer or a system including multiple apparatuses, a method executed by a computer, or a program executed by a computer. A recording medium for storing the program may also be provided. Effect of the Invention

[0007] According to the disclosed technique, it is possible to provide a technique for supporting the determination of operating conditions during unsteady operation of a plant. [Brief description of the drawings]

[0008] [Figure 1] FIG. 1 is a diagram illustrating an example of a system. [Diagram 2] FIG. 2 is a block diagram illustrating an example of a configuration of an information processing device. [Diagram 3] FIG. 3 is a schematic diagram showing an example of a process carried out by equipment included in a plant. [Figure 4] FIG. 4 is a diagram for explaining an example of process data in a batch process. [Diagram 5] FIG. 5 is a diagram for explaining an example of process data in a continuous process. [Figure 6] FIG. 6 is a process flow diagram showing an example of a scenario creation support process executed by the information processing device. [Figure 7] FIG. 7 is a diagram for explaining an example of a schematic scenario. [Figure 8] FIG. 8 is a diagram showing an example of operating conditions. [Figure 9] FIG. 9 is a diagram illustrating an example of the feature amount. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0009] Hereinafter, an embodiment of a prediction device will be described with reference to the drawings.

[0010] <Embodiment> FIG. 1 is a diagram showing an example of a system according to the present embodiment. The system 100 includes an information processing device 1, a control station 2, and a plant 3. The system 100 is, for example, a distributed control system (DCS) and includes a plurality of control stations 2. That is, the control system of the plant 3 is divided into a plurality of sections, and each control section is distributedly controlled by the control station 2. The control station 2 is an existing facility in the DCS, and receives status signals output from sensors and the like included in the plant 3, and outputs control signals to the plant 3. Then, actuators such as valves and other devices included in the plant 3 are controlled based on the control signals. The system 100 also includes a plurality of plants 3. The plant 3 is, for example, a chemical plant, a production plant that produces products, or the like.

[0011] The information processing device 1 acquires a state signal (process data) of the plant 3 via the control station 2. The process data includes temperature, pressure, flow rate, etc. of the processing target, which is raw material, intermediate, product, waste liquid, drainage, etc., and set values ​​that determine the operating conditions of the equipment equipped in the plant 3. Then, the information processing device 1 creates a model for predicting the quality, etc. of the product based on at least a part of the acquired process data, and supports the determination of desirable operating conditions. For example, a regression model is created using process data that is a quality evaluation standard as the objective variable and feature quantities that are candidates for control targets during a specified operation as explanatory variables. Then, based on the created regression model, information for determining operations to be performed in the operation of the plant 3, desirable operating values, target values, etc. is output.

[0012] <Device configuration> FIG. 2 is a block diagram showing an example of the configuration of the information processing device 1. The information processing device 1 is a computer, and includes a communication interface (I / F) 11, a storage device 12, an input / output device 13, and a processing unit (processor) 14. The communication I / F 11 may be, for example, a network card or a communication module, and communicates with other computers based on a predetermined protocol. The storage device 12 may be a main storage device such as a random access memory (RAM) or a read only memory (ROM), and an auxiliary storage device (secondary storage device) such as a hard disk drive (HDD), a solid state drive (SSD), or a flash memory. The main storage device temporarily stores a program read by the processor 14 and information transmitted / received between the processor 14 and other computers, and secures a working area for the processor 14. The auxiliary storage device stores a program executed by the processor 14, information transmitted / received between the processor 14 and other computers, and the like. The input / output device 13 is, for example, a user interface such as an input device such as a keyboard or a mouse, an output device such as a monitor, or an input / output device such as a touch panel. The processor 14 is an arithmetic processing device such as a central processing unit (CPU), and executes a program. 13, functional blocks are shown within the processor 14. That is, the processor 14 functions as a process data acquisition unit 141, a scenario creation support unit 142, and a control support unit 143 by executing a predetermined program.

[0013] The process data acquisition unit 141 acquires process data from a sensor equipped in the plant 3 via, for example, the communication I / F 11 and the control station 2, and stores the process data in the storage device 12. The scenario creation support unit 142 creates a prediction model for predicting a predetermined objective variable based on the past operation record of the plant. The prediction model can support the creation of a scenario that represents the operating conditions at the start of operation of the plant 3. The control support unit 143 outputs information to an operator and controls devices equipped in the plant 3 based on the operation of the operator. At this time, the scenario creation support unit 142 may predict the above-mentioned objective variable using the process data and the prediction model acquired from the plant 3. In addition, the control support unit 143 automatically controls the operation of the plant 3 according to a predetermined scenario, and controls the operation according to a manual operation by a user, especially in non-steady operation.

[0014] The above-mentioned components are connected via a bus 15.

[0015] Moreover, each of the plants 3 outputs a plurality of process data. FIG. 3 is a schematic diagram showing an example of a process performed by the equipment of the plant 3. In this embodiment, the process may include a batch process 31 and a continuous process 32. In the batch process 31, the processing target is sequentially processed for each predetermined processing unit, and for example, processing such as receiving, holding, and discharging raw materials in each equipment is performed in sequence. In the continuous process 32, the processing target stored in a buffer tank or the like is continuously processed, and for example, processing such as receiving, holding, and discharging raw materials is performed in parallel. Moreover, the process may include a plurality of series 33 performing the same processing in parallel.

[0016] The devices that perform each process include, for example, a reactor, a distillation apparatus, a heat exchanger, a compressor, a pump, a tank, and the like, which are connected via piping. Sensors, valves, and the like are provided at predetermined positions in the devices and piping. The sensors may include thermometers, flow meters, pressure gauges, level gauges, concentration meters, and the like. The sensors monitor the operating status of each device and output status signals. The sensors provided in the plant 3 are each provided with a "tag," which is identification information for identifying each sensor. The information processing device 1 and the control station 2 manage input / output signals to each device based on the tag.

[0017] FIG. 4 is a diagram for explaining an example of process data in a batch process. The left column of FIG. 4 shows a part of the process of the batch process 31 shown in FIG. 3. Specifically, the plant 3 includes a shredder 301, a cyclone 302, a pretreatment 303, a precooler 304, and a reactor 305. These processes are classified into a pretreatment process, a precooling process, and a reaction process. The right column of FIG. 4 shows an example of process data acquired in each process. In the pretreatment process, time-series data is acquired from sensors with tags 001 and 002. In the precooling process, time-series data is acquired from sensors with tags 003 and 004. In the reaction process, time-series data is acquired from sensors with tags 005, 006, and 007. In addition, in the batch process, a processing object associated with a serial number (also called a "production number") is intermittently processed. That is, the serial number is identification information for identifying processing objects to be processed collectively in the batch process. As shown in FIG. 4, time-series data on the processing object associated with subsequent serial numbers is obtained over time.

[0018] FIG. 5 is a diagram for explaining an example of process data in a continuous process. The left column of FIG. 5 shows a part of the process of the continuous process 32 shown in FIG. 3. Specifically, the plant 3 includes a tank 311 and a pump 312. The right column of FIG. 5 shows an example of process data acquired in each process. In the continuous process 32, time-series data associated with a tag and not associated with a serial number is continuously acquired from a sensor. In the example of FIG. 5, time-series data is acquired from each sensor with tags 102 and 103. In the continuous process, the equipment continuously receives the processing target and continuously processes it. When a batch process and a continuous process are performed successively, the processing target in the batch process may be linked to the processing target in the continuous process. For example, the serial number in the batch process is associated with the process data in the continuous process based on the sampling interval of the sensor and the time the processing target is retained between the batch process and the continuous process.

[0019] 6 is a process flow diagram showing an example of a scenario creation support process for non-steady operation executed by the information processing device 1. As an example of non-steady operation, in this embodiment, a start-up process from the start of operation of the plant 3 to steady operation in which products are stably manufactured will be described. In the start-up process, the concentration of unreacted raw materials in the products manufactured in the plant 3 is controlled so as to satisfy a predetermined standard, and after the concentration of unreacted raw materials in the products satisfies the predetermined standard, the plant transitions to steady operation.

[0020] FIG. 7 is a diagram for explaining an example of a schematic scenario. A scenario is, for example, a procedure manual created by a user, and a program for controlling the plant 3 in accordance with the scenario may be created for at least some of the processes, or the scenario may be used for an operator to refer to during operation. The scenario in FIG. 7 includes processes such as setting a target value according to the measured value (concentration) of the treatment target, changing the operation value at a predetermined speed up to a predetermined target value, changing the target value or operation value according to the measured value, and waiting for a predetermined period of time. The framework of the scenario can be created based on the principles of the reaction process. However, particularly in unsteady operation, it is difficult to determine which measured value should be used for control in the first place, and it is also difficult to determine the process in FIG. 7. It is not easy to find desirable values ​​for the target value of feedback control (underlined) and the amount of change per unit time of the manipulated variable. The scenario creation support process shown in Fig. 6 presents useful information for scenario creation. Specifically, by using the regression model described above, the user can determine desirable values ​​of explanatory variables that bring the objective variable, which is, for example, the concentration of unreacted raw material in the product, closer to a value that satisfies a predetermined condition, or identify explanatory variables that have a large effect on the fluctuation of the objective variable based on the magnitude of the coefficient of the explanatory variable.

[0021] FIG. 8 is a diagram showing an example of an operating condition. Such an operating condition can be created in advance by a user based on the principles of the reaction process, the knowledge of the operator, and past operating results. The table in FIG. 8 includes the attributes of "No.", "feature amount," "optimum value," "estimated value," and "condition." In the "No." field, an identification number of the feature amount is registered. In the "feature amount" field, a definition of the feature amount that can affect the change in the objective variable, which is the concentration of the unreacted raw material in the product, is registered. The feature amount is a value that can be used as an explanatory variable in a regression model. Note that the feature amount may be a value that changes over time, such as process data in a predetermined period or a value corresponding to the process data. In addition, in the "optimum value" field, an optimal value is registered based on, for example, a principle regarding a chemical reaction. Note that, for a feature amount including a condition that is a trade-off with another feature amount, a value to be used in a simulation may be set within a range of values, ratios, etc. in past operating results from the viewpoint of reaction stability, etc. In the "estimated value" field, an assumed value that is a value to be used in a simulation is registered. That is, even if each feature value is an optimal value, when the combination of the multiple features is a new operating condition, it may be desirable to set an expected value within the range of past operating results or to gradually approach the optimal value. Therefore, a simulation using a regression model is performed using the expected value. In the "Condition" field, conditions that are constraints when performing control are registered. The conditions may include conditions that are trade-offs for multiple feature values. A trade-off refers to a relationship in which the direction in which one explanatory variable should be increased or decreased is not uniquely determined in relation to other explanatory variables in order to bring the objective variable, which is the concentration of unreacted raw materials in the product, closer to the value in the steady operation of the plant 3. The user sets the expected value taking the conditions into consideration. For example, if the theoretical optimal values ​​are that the feed flow rate of raw material 1 is minimum and the feed flow rate of raw material 3 is maximum, as shown in FIG. 8 (No. 1 and No. 3), a limit based on operating results may be set as a condition for the ratio of the feed flow rate of raw material 1 to the feed flow rate of raw material 3, and the expected value may be set according to the limit.As shown in FIG. 8 (No. 6) for the condition of the liquid level at the start of the reaction in the reactor 1, an upper limit may be set with some margin based on the operational record, and an assumed value that satisfies this may be set.

[0022] FIG. 9 is a diagram showing an example of the feature amount stored in the storage device 12. For the feature amount shown in FIG. 8, for example, a record of the table shown in FIG. 9 is prepared. The table in FIG. 9 includes each attribute of "feature amount", "sign constraint", "relationship with reaction influencing factor" ("temperature", "concentration", "residence time"), and "trade-off". In the "feature amount" field, information corresponding to the feature amount in FIG. 8 is registered. In the "sign constraint" field, information indicating the sign of the coefficient of each feature amount (explanatory variable) to be set in the regression equation is registered. Note that, when there is sufficient learning data, it is understood that the coefficient of the explanatory variable in the regression equation can be estimated (converged) with an appropriate sign according to the relationship between the objective variable and the explanatory variable. However, when there is little learning data, it may not be possible to obtain a coefficient with an appropriate sign. By performing regression analysis with imposed sign constraint, it is possible to create an appropriate regression equation even when there is little learning data. That is, the information processing device 1 performs regression analysis based on the information registered in the "sign constraint" field. Note that regression analysis with imposed sign constraint can be performed using a known method disclosed in, for example, International Publication No. 2021 / 157669. That is, when a sign constraint is specified, the regression model uses a regularization term that increases the cost when the sign of the regression coefficient is different from the sign specified in the sign constraint. A regression analysis is performed to minimize a cost function that includes the terms:

[0023] The "Relationship with reaction influencing factors" field stores a sign indicating whether the objective variable will increase or decrease when the feature is increased. "+" indicates an increase, and "-" indicates a decrease. Conversely, when the feature is decreased, "-" indicates that the objective variable will increase, and "+" indicates that the objective variable will decrease. The sign registered in the "Relationship with reaction influencing factors" is set by the user based on the principles of chemical reactions, decomposed into the perspectives of temperature, concentration, and residence time. If the same sign is registered for these three perspectives, it can be determined that the direction of increase or decrease of the objective variable in response to the increase or decrease in the feature represented by the record (i.e., the sign registered in the "sign constraint" field) is determined. The regression equation in regression analysis with sign constraints is expressed, for example, as the following equation (1).

number

number

[0024] The "trade-off" field stores information indicating the presence or absence of a problem that the preferred direction of change is not univocally determined in relation to other processes in the entire non-stationary process (there is a trade-off). For features with a trade-off, the user may modify the sign constraint information and recreate the regression model. The information held in the table of FIG. 9 can be determined in advance, for example, based on the principles shown in FIG. 8 or the knowledge of the operator. It is assumed that the definitions of features as shown in FIG. 9 are stored in advance in the storage device 12.

[0025] In the process of FIG. 6, first, the process data acquisition unit 141 of the information processing device 1 The process data output by the plant 3 in past operation is read out (S1 in FIG. 6). The process data to be read out is the process data during the unsteady operation described above. In particular, it is preferable to use the process data of a case in which the process proceeded without any abnormality or malfunction. The scenario creation support unit 142 of the information processing device 1 performs machine learning using the read out process data (S2 in FIG. 6). The machine learning may be a method using a regularization term such as linear regression, Ridgge regression, or Lasso regression, or a method similar thereto. A regression model may be created based on the above-mentioned sign constraint. The objective variable of the regression model is, for example, the concentration of unreacted raw materials in a product manufactured in the plant 3. The explanatory variables of the regression model are at least a part of the feature quantities shown in FIG. 8 and FIG. 9, and are set in advance by, for example, a user. The explanatory variables may be the process data itself, or may be any value obtained according to the process data, such as an integral value of a flow rate. The explanatory variables may be, for example, a target value or an operation value in the procedure of the expected unsteady operation, or a candidate of a measurement value, a waiting time, etc., which is a start condition (trigger) of the process, as shown in FIG. 7. The explanatory variable may also be an integral value of an operation value or a measurement value, such as the flow rate or the liquid level shown in Fig. 8. Based on a regression model with the integral value as the explanatory variable, the user can determine, for example, the speed at which the flow rate or the liquid level is changed in a non-steady operation procedure.

[0026] In addition, the scenario creation support unit 142 evaluates the trained model (FIG. 6: S3). The scenario creation support unit 142 uses, for example, a part of the process data acquired in S1 as verification data to calculate an evaluation index such as a coefficient of determination. The calculated evaluation index is output via the input / output device 13.

[0027] Further, the scenario creation support unit 142 outputs information for creating a scenario representing the operating conditions of each device of the plant 3 in non-steady operation based on the trained model (S4 in FIG. 6). The trained model is, for example, a regression equation in which the regression coefficient (partial regression coefficient) and the intercept are determined by regression analysis. A simulation is performed using the trained model and the optimal or assumed values ​​of the explanatory variables, and a preferable value of the explanatory variable for quickly reducing, for example, the concentration of the unreacted raw material in the product, which is the objective variable, to a desired threshold value or less can be obtained and output. In S4, the scenario creation support unit 142 may perform a prediction using the trained model, particularly with respect to a feature amount (explanatory variable) including a condition that is a trade-off, and present the result to the user. The simulation is performed, for example, based on the "assumed value" in FIG. 8. The user can set the assumed value according to the "condition" and "optimum value" shown in FIG. 8 and perform the simulation. For example, in order to change the objective variable, which is the concentration of the unreacted raw material in the product, to a value in steady operation of the plant 3, it is possible to predict what assumed value the explanatory variable should be by changing the assumed value and repeating the simulation. Based on the preferred assumed value obtained here, the user can determine the operation value, target value, etc. to be set in the scenario. The magnitude of the absolute value of the coefficient of the regression model can be said to represent the magnitude of the influence on the change in the objective variable. Therefore, if a value based on the regression coefficient such as the regression coefficient or its absolute value is output in S4, the user can select the explanatory variable to be changed in the operation procedure based on a comparison of the regression coefficients. The user may change the assumed value of the explanatory variable and recreate the regression model. The sign of the regression coefficient represents the correspondence between the control to increase or decrease the explanatory variable and the direction in which the objective variable changes (increase or decrease). If the regression coefficient or its sign is output in S4, the user can know this correspondence. Based on the results of the simulation, the user may also modify the sign constraint information and recreate the regression model, especially for the feature quantities with a trade-off "present" in FIG. 9.

[0028] Generally, when there is multicollinearity, the magnitude of the coefficient does not necessarily indicate the degree of influence on the objective variable. On the other hand, in the regression equation according to this embodiment, the prediction accuracy was equivalent when a combination of explanatory variables with a correlation coefficient of 0.9 or more was included and when one of the combinations was deleted. In other words, the sign of the regression coefficient does not satisfy the above-mentioned "sign constraint". " It is believed that by using a regularization term that increases the cost when the sign differs from that specified in ", it is possible to converge to more appropriate coefficients, thereby solving the problem of multicollinearity.

[0029] Furthermore, the scenario creation support unit 142 judges whether to modify the model (FIG. 6: S5). In this step, the scenario creation support unit 142 receives, for example, a user's operation via the input / output device 13, whether to change the explanatory variables or the sign constraints, and judges whether to modify the model based on the input. If it is judged that the model is to be modified (S5: YES), the scenario creation support unit 142 receives selection of explanatory variables to be used in the regression model and modification of the sign constraints (FIG. 6: S6), and returns to S1 to repeat the process.

[0030] <Effects> According to this embodiment, the scenario creation support unit 142 can support the user in creating a regression model based on the magnitude of the effect of the feature amount (explanatory variable) on the change in the objective variable. In addition, when the changes in multiple explanatory variables are in a trade-off relationship with each other and affect the results of the entire non-stationary process, it is possible to prioritize how the explanatory variables should be changed (i.e., increased or decreased) to improve the prediction accuracy of the regression model by performing regression analysis using process data related to past operation results. For example, in order to reduce unreacted raw materials in the product, for example, if the initial liquid level of the reactor, which is one of the feature amounts, is increased by increasing the initial charge amount of the solvent in the reactor, in principle, the raw material concentration in the reactor decreases and the reaction becomes difficult, while the reaction time becomes longer and the reaction becomes easy to carry out sufficiently. By using the learning model of this embodiment, it becomes possible to determine and present which causal relationship has priority overall. In addition, the user can create a preferred operation scenario for non-stationary operation based on the created regression model. The control support unit 143 controls the plant 3 based on a program for operating in accordance with the scenario. In non-stationary operation, the control support unit 143 may receive manual operation by the user via the input / output device 13.

[0031] <Modification> Each configuration and their combinations in each embodiment are merely examples, and addition, omission, substitution, and other modifications of the configurations are possible as appropriate within the scope of the present disclosure. The present disclosure is not limited by the embodiments, but is limited only by the scope of the claims. In addition, each aspect disclosed in this specification can be combined with any other feature disclosed in this specification.

[0032] Furthermore, at least some of the functions of the information processing device 1 may be distributed among multiple devices, or the same functions may be provided in parallel by multiple devices. For example, the device functioning as the scenario creation support unit 142 may be different from the device functioning as the control support unit 143. At least some of the functions of the information processing device 1 may be provided on a so-called cloud.

[0033] In the embodiment, the process at the start-up of the plant has been described, but the unsteady operation may be a process at the shutdown of the plant or a process for changing the production amount per unit time. In this case, the process can be performed according to a predetermined scenario.

[0034] As shown in FIG. 8, the characteristic quantities in the embodiment may be the definite integral of the charge flow rate, which is the flow rate at which the raw materials are transferred to a specified reactor, the start time of transfer between two reactors, the height of the liquid level in the reactor at the start of the reaction, the definite integral of the height of the liquid level in the specified reactor, the integral of the absolute temperature of the specified reactor, etc. However, the characteristic quantities are not limited to the examples shown in FIG. 8. For example, various values ​​based on process data may be used, such as the difference in the start time of charging the first raw material and the second raw material, the definite integral of the flow rate of the cooling water for the reactor, the integral of the absolute temperature of the cooling water for the reactor, etc. The objective variable may also be the concentration of the unreacted raw materials in FIG. 8 (i.e., the concentration of the unreacted raw materials after a specified time from the start of the reaction). For example, it may be the time until the concentration of unreacted raw materials reaches a predetermined standard, the concentration of impurities in other products, product property values, raw material usage, energy usage, out-of-system emissions, or other values.

[0035] The present disclosure also includes a method and a computer program for executing the above-mentioned processes, and a computer-readable recording medium having the program recorded thereon. The recording medium having the program recorded thereon enables the above-mentioned processes by causing a computer to execute the program.

[0036] Here, a computer-readable recording medium refers to a recording medium that stores information such as data and programs through electrical, magnetic, optical, mechanical, or chemical action and can be read by a computer. Among such recording media, those that can be removed from a computer include flexible disks, magneto-optical disks, optical disks, magnetic tapes, memory cards, etc. Furthermore, recording media that are fixed to a computer include HDDs, SSDs (Solid State Drives), ROMs, etc. [Explanation of symbols]

[0037] 100: System 1: Information processing equipment 2: Control station 3: Plant 11: Communication I / F 12:Storage device 13: Input / output device 14: Processing unit (processor) 141: Process data acquisition unit 142: Scenario Creation Support Department 143: Control Support Department

Claims

1. Obtaining process data output during past unsteady operation of a plant; creating a trained model in which a relationship between a feature quantity based on the process data and a predetermined objective variable is trained by a regression analysis using the feature quantity as an explanatory variable; Performing a simulation using the trained model and the assumed values ​​of the explanatory variables; outputting the regression coefficients of the trained model, the results of the simulation, and conditions that are predetermined constraints on the explanatory variables; When an operation to modify the explanatory variables is received from a user, the trained model is modified, or when an operation to modify the assumed values ​​is received from the user, the simulation is performed using the modified assumed values. A procedure creation support device comprising a processing unit that executes the above.

2. The processing unit outputs the regression coefficient of the trained model or a value based on the regression coefficient as an index of the magnitude of an effect of the explanatory variable multiplied by the regression coefficient in the trained model on a change in the objective variable. The procedure creation support device according to claim 1 .

3. When the user specifies the sign of the regression coefficient, the trained model performs a regression analysis using a regularization term that increases a cost when the sign of the regression coefficient differs from the sign specified by the user, so as to minimize a cost function including the regularization term; The constraint condition includes causal relationship information regarding a direction in which one of the explanatory variables should be increased or decreased in order to change the objective variable to a value in the steady operation of the plant. The procedure creation support device according to claim 2.

4. The causal relationship information includes a plurality of pieces of information that indicate directions in which the explanatory variables should be increased or decreased based on different perspectives. The procedure creation support device according to claim 3.

5. The constraint condition includes being within a range of explanatory variables based on process data output during the past non-steady operation. The procedure creation support device according to claim 1 .

6. Obtaining process data output during past unsteady operation of a plant; creating a trained model in which a relationship between a feature quantity based on the process data and a predetermined objective variable is trained by a regression analysis using the feature quantity as an explanatory variable; Performing a simulation using the trained model and the assumed values ​​of the explanatory variables; outputting the regression coefficients of the trained model, the results of the simulation, and conditions that are predetermined constraints on the explanatory variables; When an operation to modify the explanatory variables is received from a user, the trained model is modified, or when an operation to modify the assumed values ​​is received from the user, the simulation is performed using the modified assumed values. A procedure creation support method in which the above is executed by one or more computers.

7. Obtaining process data output during past unsteady operation of a plant; creating a trained model in which a relationship between a feature quantity based on the process data and a predetermined objective variable is trained by a regression analysis using the feature quantity as an explanatory variable; A simulation is performed using the trained model and the assumed values ​​of the explanatory variables. and, outputting the regression coefficients of the trained model, the results of the simulation, and conditions that are predetermined constraints on the explanatory variables; When an operation to modify the explanatory variables is received from a user, the trained model is modified, or when an operation to modify the assumed values ​​is received from the user, the simulation is performed using the modified assumed values. A program to assist in creating procedures for executing the above on a computer.

Images