Support method, support device, support program, and method for constructing development support system

Abstract

According to the present invention, a development support method of a model pertaining to operations of a plant facility is executed by a processor and includes: acquiring facility identification information about the plant facility or process identification information about processes executed with the plant facility; acquiring target output information about the model; and outputting a processing element list that includes processing elements to configure development steps of the model, on the basis of the facility identification information or the process identification information and the target output information.

Description

Support method, support device, support program, and method for constructing development support system

[0001] The present invention relates to a method for supporting the development of a model relating to the operation of plant equipment, a support device, a support program, and a method for constructing a development support system.

[0002] Various models are used to design, construct, operate, and manage plants. Models are developed for each plant, tailored to its type, size, location, etc.

[0003] Japanese Patent Application Laid-Open No. 2023-016369

[0004] The inventors, while involved in the design, construction, operation, management, etc. of many plants, have recognized that even if the types, scales, locations, etc. of plants differ, there are many commonalities in the work processes for developing models and the processing elements such as algorithms that constitute the models. They have then come up with a technology that makes it possible to actively utilize knowledge and resources gained from developing models in the past, thereby reducing the cost, time, labor, etc. required to develop a new model.

[0005] The present invention has been made in view of the above circumstances, and has as its object to provide a technique for supporting the development of a model relating to the operation of plant equipment.

[0006] In order to solve the above problem, a method according to one aspect of the present disclosure is a method for supporting the development of a model related to the operation of plant equipment, the method being executed by a processor and including the steps of acquiring equipment identification information of the plant equipment or process identification information of a process performed on the plant equipment, acquiring target output information of the model, and outputting a processing element list including processing elements that should constitute the development process of the model based on the equipment identification information or the process identification information and the target output information.

[0007] Another aspect of the present disclosure is a support device including: an information acquisition unit that acquires equipment identification information of plant equipment or process identification information of a process executed in the plant equipment, and target output information of a model related to operation of the plant equipment; and an output unit that outputs a processing element list including processing elements that should constitute a development process of the model, based on the equipment identification information or the process identification information and the target output information acquired by the information acquisition unit.

[0008] Yet another aspect of the present disclosure is a method for constructing a development support system for a second model related to the operation of plant equipment, the method being executed by a processor and including: acquiring equipment identification information of the plant equipment that is the subject of a developed first model or process identification information of a process executed in the plant equipment, and target output information of the first model; acquiring processing elements that constitute a development process of the developed first model; and storing the processing elements in association with the equipment identification information or the process identification information and / or the target output information.

[0009] Yet another aspect of the present invention is a support device for building a development support system for a second model related to the operation of a plant facility, the support device including: an information acquisition unit that acquires facility identification information of the plant facility that is the subject of a developed first model or process identification information of a process executed in the plant facility, and target output information of the first model, a processing element acquisition unit that acquires processing elements that constitute a development process of the developed first model, and a storage unit that stores the processing elements in association with the facility identification information or the process identification information and / or the target output information.

[0010] Any combination of the above components, and any transformation of the present invention into a method, device, system, recording medium, computer program, etc., are also valid aspects of the present invention.

[0011] According to the present invention, it is possible to provide a technique for supporting the development of a model relating to the operation of a plant facility.

[0012] FIG. 1 is a diagram schematically showing an example of a method for developing a model related to the operation of plant equipment. FIG. 2 is a diagram showing the configuration of a development support system according to an embodiment. FIG. 3 is a diagram showing the configuration of a construction support device according to an embodiment. FIG. 4 is a flowchart showing the steps of a support method according to an embodiment. FIG. 5 is a diagram showing an example of the data structure of a processing element storage unit. FIG. 6 is a diagram showing an example of the data structure of a processing element storage unit. FIG. 7 is a diagram showing the configuration of a development support device according to an embodiment. FIG. 8 is a flowchart showing the steps of a support method according to an embodiment. FIG. 9 is a diagram showing an example of a screen displayed on a display device of the development support device. FIG. 10 is a diagram showing an example of a screen displayed on a display device of the development support device.

[0013] Figure 1 shows a schematic diagram of an example of a method for developing a model related to the operation of a plant facility. This diagram shows the steps of a method for developing an AI (artificial intelligence) that optimizes the operation of the plant facility as an example of a model related to the operation of the plant facility.

[0014] In step (1), operational data collected and accumulated in existing plant facilities owned by a customer is stored in a database server.

[0015] In step (2), preprocessing is performed on the driving data stored in the database server. The preprocessing may include, for example, assigning the same tag to identical or similar driving data when different tags are assigned to the driving data, aligning the units of the driving data, adjusting the offset of the driving data, processing outliers in the driving data, normalizing the driving data, complementing missing driving data, and calculating other data representing physical properties, states, etc. from the driving data using a predetermined formula, algorithm, simulation, etc. The preprocessing may be performed by referring to a tag correspondence table that defines the correspondence between tags assigned to the driving data. The content of the preprocessing may be determined by a data scientist with specialized knowledge for organizing and analyzing data.

[0016] In step (3), the data scientist visualizes the preprocessed data with reference to design information such as a process flow diagram (PFD) and heat and material balance (H&MB). The data scientist visualizes the preprocessed data in a manner that matches the plant design information, such as a time series plot, a histogram, or a box plot. The visualized data may be referenced by a data scientist or a process engineer in a subsequent step, or may be provided to a customer. The visualized data may be used, for example, to understand the plant's operating status (product production volume, whether operation has been stopped, equipment efficiency, etc.), and to select operating data (data type, extraction period) and to confirm the validity of the preprocessing of the operating data.

[0017] In step (4), a process engineer with expertise in the design and operation of plant equipment constructs a process simulation to simulate the operation of the plant equipment based on design information such as a process flow diagram (PFD), heat and material balance (H&MB), equipment performance, etc. If an existing process simulator exists, this step (4) is omitted.

[0018] In step (5), the data scientist simulates the operation of the plant equipment using the preprocessed data in the stable region as input values ​​for the process simulation, and obtains simulation results such as the thermal efficiency of the plant.

[0019] In step (6), the data scientist constructs a surrogate model (substitute model) to replace the process simulation. The surrogate model inputs preprocessed stable region data and outputs simulation results without simulating the operation of the plant equipment. The surrogate model may be constructed using a neural network or the like. The data scientist trains the surrogate model using the preprocessed data and simulation results from the process simulation as training data. For example, when preprocessed data is input to the input layer of the neural network, the middle layer of the neural network may be adjusted so that actual data corresponding to the preprocessed data or simulation results output when the preprocessed data is input to the process simulation are output from the output layer of the neural network. Note that the surrogate model may be an emulation model constructed based on operational data or a physical model constructed using first principles.

[0020] In step (7), the process engineer defines constraints for optimizing the operation of the plant equipment. The constraints may be upper and lower limits of various parameters. The process engineer may define the constraints based on information obtained through interviews with customers, equipment design information, instrumentation alarm information, etc.

[0021] In step (8), the operation optimization AI searches for values ​​of operation parameters that optimize the operation of the plant equipment under the defined constraints. The operation optimization AI inputs a large amount of preprocessed data into a surrogate model and searches for input data values ​​that will optimize predetermined data values ​​among the output data according to a predetermined optimization algorithm. Because the surrogate model can instantaneously calculate output data from input data, it can be used to search for optimal solutions from among combinations of vast amounts of input data, even for complex processes that require days or weeks of simulation calculations.

[0022] The above-described workflow is similar when developing AI for optimizing the operation of other plant equipment. Therefore, if information about the workflow used when developing a model is accumulated, the next time a similar model is developed, it is possible to smoothly develop the model using a similar workflow by referring to past performance. This makes it easier to formulate a workflow plan for developing a model and manage the workflow, thereby reducing the cost, time, and effort required for model development.

[0023] Some of the work steps involved in the development of operation optimization AI are also performed in the development of operation optimization AI for other plant equipment and other models. For example, operation data is time-series data collected during the operation of plant equipment. Given that values ​​are typically expected to be continuous and it is unlikely that the data will suddenly change to a completely different value without context, preprocessing the operation data involves removing outliers, i.e., data that has increased or decreased by more than a specified rate from the previous value. This preprocessing is a common task that should be performed in the development of operation optimization AI for other plant equipment and other models. If such common tasks are packaged in advance, existing packages can be used when developing new models, significantly reducing the cost, time, and effort required for model development.

[0024] 2 shows the configuration of a development support system according to an embodiment. The development support system 1 includes a development device 3, a design device 4, an operation control device 5, a construction support device 100, a development support device 200, and a communication network 2 for connecting these devices so that they can communicate with each other.

[0025] The plant facility 10 includes facilities, equipment, devices, piping, etc. for carrying out processes in the plant. For example, in a chemical plant, the plant facility 10 includes a reactor, a separation device, a drying device, piping, etc.

[0026] The development device 3 develops a model related to the operation of the plant equipment 10. The model may be a simulation model that simulates the operating state or fluid state of the plant equipment 10, a reaction model that simulates a chemical reaction in the plant equipment 10, a substitute model that replaces the simulation model or reaction model, AI for verifying scale-up or scale-down in the design of the plant equipment 10, AI for optimizing the operation of the plant equipment 10, AI for detecting or predicting abnormalities during the operation of the plant equipment 10, or the like.

[0027] The design device 4 designs the plant equipment 10 using the model developed by the development device 3 .

[0028] The operation control device 5 controls the operation of the plant equipment 10 using the model developed by the development device 3 .

[0029] The development support device 200 supports the development of a model in the development device 3. The development support device 200 acquires equipment identification information of the plant equipment 10 or process identification information of a process executed in the plant equipment 10, and target output information of the model, and outputs a processing element list including processing elements that should constitute the development process of the model, based on the acquired equipment identification information or process identification information and target output information. This allows the developer to develop a model using the processing element list of a model developed in the past, thereby significantly reducing development costs, time, labor, etc.

[0030] The target output information of a model is information that the model outputs ultimately or intermediately according to the purpose of the model. For example, the target output information of a simulation model is a simulation result, and the target output information of an operation optimization AI is an operation parameter for optimizing the operation of the plant equipment 10.

[0031] The construction support device 100 accumulates past performance information that the development support device 200 references to output a processing element list, and supports the construction of a development support environment. The construction support device 100 acquires equipment identification information of the plant equipment 10 that is the target of the developed model or process identification information of the process executed in the plant equipment 10, and target output information of the developed model, acquires processing elements that make up the development process of the developed model, and stores the processing elements in association with the equipment identification information or the process identification information and / or the target output information.

[0032] 3 shows the configuration of a construction support device 100 according to an embodiment. The construction support device 100 includes a communication device 101, a display device 102, an input device 103, a processing device 120, and a storage device 130.

[0033] The communication device 101 controls wireless or wired communication. The display device 102 displays a screen generated by the processing device 120. The display device 102 may be a liquid crystal display device, an organic EL display device, or the like. The input device 103 transmits instructions input by a user of the construction support device 100 to the processing device 120. The input device 103 may be a mouse, a keyboard, a touchpad, or the like. The display device 102 and the input device 103 may be implemented as a touch panel.

[0034] The storage device 130 stores data and computer programs used by the processing device 120. The storage device 130 includes a processing element holding unit 131.

[0035] The processing element holding unit 131 holds processing elements that constitute a development process of a model related to the operation of the plant equipment 10, in association with equipment identification information or process identification information of the plant equipment 10 and / or target output information of the model. The processing element holding unit 131 may hold source code of modules that constitute the development process of the model and models. Furthermore, the processing element holding unit 131 may hold variables, constants, parameters, etc. included in the source code.

[0036] The processing device 120 includes an information acquisition unit 121, a processing acquisition unit 122, a processing division unit 123, and a processing element registration unit 124. These components are realized by hardware components such as any circuit, a computer CPU, memory, and programs loaded into memory, but the functional blocks realized by the cooperation of these components are depicted here. Therefore, those skilled in the art will understand that these functional blocks can be realized in various forms using only hardware, only software, or a combination of these.

[0037] 4 is a flowchart showing the procedure of the support method according to the embodiment. The procedure for supporting the construction of a development support environment by the construction support device 100 will be described with reference to FIGS. 3 and 4. The model that has already been developed is referred to as the "first model," and the model to be newly developed is referred to as the "second model."

[0038] The information acquisition unit 121 acquires equipment identification information of plant equipment that is the target of the developed first model, or process identification information of a process executed in the plant equipment (S10). The equipment identification information may include information such as the type, scale, size, and performance of the plant equipment. The process identification information may include information such as the type, time, and conditions of raw materials, final products, intermediate products, reactions, and processing. The information acquisition unit 121 may acquire the equipment identification information or the process identification information from the development device 3, the design device 4, the development support device 200, etc. The information acquisition unit 121 may acquire the equipment identification information or the process identification information from a developer, etc. via the input device 103.

[0039] The information acquisition unit 121 acquires target output information of the developed first model (S12). The target output information is information that the model outputs ultimately or intermediately, and for example, in the above-mentioned plant optimization model, includes conditions such as values ​​of controlled variables for optimizing plant operation. The information acquisition unit 121 may acquire the target output information from the development device 3, the design device 4, the development support device 200, etc. The information acquisition unit 121 may acquire the target output information from a developer or the like via the input device 103. The information acquisition unit 121 may acquire the target output information by analyzing the source code, system design diagram, etc. of the first model.

[0040] The process acquisition unit 122 acquires the processes that constitute the developed first model (S14). The processes may include work steps for developing the first model and components (modules) that constitute the first model. The process acquisition unit 122 may acquire source code, variables, constants, parameters, etc. of the modules that constitute the first model. The process acquisition unit 122 may acquire the processes from the development device 3, the design device 4, the development support device 200, etc. The process acquisition unit 122 may acquire the processes from a developer, etc. via the input device 103.

[0041] When the process acquisition unit 122 has acquired the entire first model, the process division unit 123 divides the acquired process into multiple process elements as necessary (S16). The process division unit 123 may divide the process into units of work steps. The process division unit 123 may divide the process into process elements that are common to the development of multiple models and process elements that differ individually depending on the type of plant, the target output information of the model, etc. Note that when the process acquisition unit 122 can acquire the process of the first model for each process element, the process division unit 123 does not have to divide the process.

[0042] The processing element registration unit 124 stores the processing elements in the processing element holding unit 131 in association with the equipment identification information or process identification information and / or target output information.

[0043] 5 shows an example of the data structure of the processing element storage unit 131. In this example, processing elements are stored for each target plant equipment, process, and problem (target output information). In addition, processing elements that are commonly included in the model regardless of the target plant equipment, process, or problem are stored.

[0044] 6 shows an example of the data structure of the processing element storage unit 131. In this example, a processing element storage unit 131 is provided for each work process. The processing element storage unit 131 for each work process stores processing elements in a matrix of target plant equipment and processes and target tasks (target output information). Note that the processing element storage unit 131 is not limited to a relational database such as those shown in FIGS. 5 and 6 , and may be configured as a graph database in which, for example, individual processing elements are linked by edges to target plant equipment and processes and / or target tasks.

[0045] 7 shows the configuration of a development support device 200 according to an embodiment. The development support device 200 includes a communication device 201, a display device 202, an input device 203, a processing device 220, and a storage device 230.

[0046] The communication device 201 controls wireless or wired communication. The display device 202 displays a screen generated by the processing device 220. The display device 202 may be a liquid crystal display device, an organic EL display device, or the like. The input device 203 transmits instructions input by a user of the development support device 200 to the processing device 220. The input device 203 may be a mouse, a keyboard, a touchpad, or the like. The display device 202 and the input device 203 may be implemented as a touch panel.

[0047] The storage device 230 stores data and computer programs used by the processing device 220. The storage device 230 includes a processing element holding unit 231.

[0048] The processing element holding unit 231 holds processing elements that are to constitute the development process of a model related to the operation of the plant equipment 10, in association with equipment identification information or process identification information of the plant equipment 10 and / or target output information of the model. The processing element holding unit 231 may be the same as the processing element holding unit 131. The processing element holding unit 231 may be acquired from the system construction support device 100 and stored in the storage device 230. When the development support device 200 accesses the processing element holding unit 131 of the system construction support device 100, the processing element holding unit 231 does not need to be provided.

[0049] The processing device 220 includes an information acquisition unit 221, a processing element list acquisition unit 222, an output unit 223, a processing element determination unit 224, a processing parameter acceptance unit 225, a processing order determination unit 226, a connection element acceptance unit 227, a processing element connection unit 228, and a processing element registration unit 229. These components are realized by hardware components such as arbitrary circuits, a computer CPU, memory, and programs loaded into memory, but the functional blocks shown here are realized by the cooperation of these components. Therefore, those skilled in the art will understand that these functional blocks can be realized in various forms using only hardware, only software, or a combination of these.

[0050] 8 is a flowchart showing the procedure of the support method according to the embodiment. The procedure for supporting the development of a model by the development support device 200 will be described with reference to FIGS.

[0051] The information acquisition unit 221 acquires equipment identification information of the plant equipment to be developed or process identification information of the process executed in the plant equipment (S20). The information acquisition unit 221 may acquire the equipment identification information or the process identification information from the development device 3, the design device 4, or the like. The information acquisition unit 221 may acquire the equipment identification information or the process identification information from the developer or the like via the input device 203.

[0052] The information acquisition unit 221 acquires target output information of the model (S22). The information acquisition unit 221 may acquire the target output information from the development device 3, the design device 4, etc. The information acquisition unit 221 may acquire the target output information from a developer, etc. via the input device 203.

[0053] The processing element list acquisition unit 222 acquires a processing element list including processing elements that should constitute the model development process based on the equipment identification information or process identification information and the target output information (S24). The processing element list acquisition unit 222 may acquire the processing element list by referencing the processing element holding unit 231 or the processing element holding unit 131. If the processing element holding unit 231 or the processing element holding unit 131 has the data structure shown in FIG. 5, the processing element list acquisition unit 222 acquires the processing element list by extracting processing elements whose target equipment, target process, and target task match the equipment identification information, process identification information, and target output information, respectively, and common processing elements. If the processing element holding unit 231 or the processing element holding unit 131 has the data structure shown in FIG. 6, the processing element list acquisition unit 222 acquires the processing element list by extracting processing elements whose target equipment, target process, and target task match the equipment identification information, process identification information, and target output information, respectively, and common processing elements, for each work process.

[0054] The output unit 223 outputs the acquired processing element list to the developer as a candidate list of processing elements that should constitute the development process of the model (S25). The output unit 223 may display the candidate list on the display device 202. The output unit 223 may also transmit the candidate list to a terminal device used by the developer.

[0055] The processing element determination unit 224 accepts a selection of processing elements to be included in the model development process from the candidate list (S26), and determines the selected processing elements as processing elements that will be included in the model development process (S28). The processing element determination unit 224 may accept the selection of processing elements from the developer via the input device 203. The processing element determination unit 224 may also accept the selection of processing elements from a terminal device used by the developer. The processing element determination unit 224 may automatically determine processing elements listed in the processing element list as processing elements that will be included in the model development process. The processing element determination unit 224 may automatically select processing elements based on predetermined selection criteria and determine the selected processing elements as processing elements that will be included in the model development process. When processing elements are automatically selected, the selection of processing elements may be performed by a machine learning model. In this case, the machine learning model may be a model that learns the relationship between the equipment identification information and / or process identification information of previously constructed AI, the target output information, and the processing elements included in the development process of that AI, as well as general AI construction flows that are not limited to the plant field, and determines the processing elements of the second model by inputting the equipment identification information, process identification information, or target output information of the second model.

[0056] The processing parameter receiving unit 225 receives input of processing parameters for the determined processing element (S30). The processing parameters may include parameters used when executing the processing element. The processing parameter receiving unit 225 sets the received processing parameters to the processing element. The processing parameter receiving unit 225 may receive processing parameters from the developer via the input device 203. The processing parameter receiving unit 225 may also receive processing parameters from a terminal device used by the developer. For example, if the processing element relates to outlier removal processing in preprocessing of driving data, the processing parameter receiving unit 225 receives input of parameters that serve as criteria for removing outliers. The parameters that serve as criteria for removing outliers may be, for example, based on the interquartile range (IQR) of the acquired data: a lower limit: (first quartile) - 1.5 x IQR; and an upper limit: (third quartile) + 1.5 x IQR. Note that the processing parameters may be set without requiring input by the developer. In this case, the processing element may store initial setting parameters, such as the setting parameters in the first model, and may be further configured to allow a developer to review and edit the initial setting parameters as necessary.

[0057] The processing order determination unit 226 determines the processing order in which the processing elements are to be executed (S32). The processing order determination unit 226 may receive the processing order from the developer via the input device 203. The processing order determination unit 226 may receive the processing order from a terminal device used by the developer. The processing order determination unit 226 may automatically determine the processing order based on a predetermined criterion. The predetermined criterion may be, for example, the processing order in the first model, a criterion based on the processing order in AI related to the operation of multiple plants previously constructed, such as the first model, or a criterion based on the order in AI development in other fields, not limited to plant operation. Such processing order criterion may refer to the criterion stored in the processing element storage unit 231, or may be learned based on the processing order of AI previously constructed.

[0058] The combined element receiving unit 227 receives processing elements necessary for combining the determined processing elements (S34). In cases where the information output from the preceding processing element does not match the information to be input to the subsequent processing element, a processing element that generates input information for the subsequent processing element from the output information of the preceding processing element may be added as a combined element. The combined element receiving unit 227 may receive source code, parameters, etc. of the combined element from the developer via the input device 203. The combined element receiving unit 227 may receive source code, parameters, etc. of the combined element from a terminal device used by the developer. The combined element receiving unit 227 may automatically generate a combined element based on the output information of the preceding processing element and the input information of the subsequent processing element.

[0059] The processing element combining unit 228 combines the determined processing elements (S36). The processing element combining unit 228 combines the determined processing elements and the combined elements in the determined processing order. In this way, a second model is generated.

[0060] The processing element registration unit 229 stores the equipment identification information or process identification information, the target output information, and the determined processing elements in the processing element holding unit 231 (S38). This allows the processing elements that make up the development process of the developed model to be used in the development of subsequent models.

[0061] When a developed model is changed or added, the contents of the processing element holding unit 131 and the processing element holding unit 231 may be updated accordingly.

[0062] 9 shows an example of a screen displayed on the display device 202 of the development support device 200. In this figure, a user interface screen is displayed for the developer to select the type of equipment to be developed and the type of model or problem. When the developer selects the type of equipment and the type of model or problem, the information acquisition unit 221 acquires the equipment identification information of the plant equipment to be developed and the target output information of the model.

[0063] 10 shows an example of a screen displayed on the display device 202 of the development support device 200. In this figure, the output unit 223 displays a list of processing elements that should constitute the model development process, which is acquired by the processing element list acquisition unit 222 in accordance with the type of device selected by the developer and the type of model or problem.

[0064] Next, examples of processing elements held in the processing element holding unit 131 and / or the processing element holding unit 231 will be described.

[0065] 1. Common Processing Elements In the embodiment, the common processing elements include a plant design information acquisition element, an acquired data tag identification element, a data acquisition period identification element, an operation data acquisition element, an operation data time series visualization element, an operation data processing / visualization element, an operation data sufficiency check element, and an operation data storage element.

[0066] The plant design information acquisition element is a processing element that acquires design information related to the equipment identification information or process identification information that is input as the plant equipment that is the target of the model to be developed. The plant design information acquisition element is a module that executes processing to acquire, for example, the process flow diagram, P&ID diagram, data sheets for each device, etc. of the plant that is the target of the development model.

[0067] The acquired data tag identification element is an element that identifies data tags (equipment constituting the plant and parameters related to the equipment) necessary for developing a target model from information included in the plant design information acquired by the plant design information acquisition element. The acquired data tag identification element may be a module that includes, for example, a process for identifying equipment on the P&ID of the target plant of the model being developed this time and the inlet and outlet conditions (material, temperature, pressure, flow rate) of each equipment, a process for acquiring target equipment and parameters of operating data used in the development of a previously developed similar model, and a process for identifying data tags to be acquired by comparing the target equipment and parameters acquired for the previously developed model with the equipment and inlet and outlet conditions of the target plant of the model being developed this time.

[0068] The data acquisition period specification element is a processing element that specifies a period for acquiring plant operation data corresponding to the data tag to be acquired specified by the acquisition data tag specification element. The data acquisition period specification element is a module that sets a period for ensuring the accuracy of the model to be constructed, for example, based on the period of operation data used for construction of a previously constructed model.

[0069] The operating data acquisition element is a processing element that executes acquisition of plant operating data corresponding to the data tag identified by the acquisition data tag identification element over a period identified by the data acquisition period identification element. The operating data acquisition element may further execute processing to extract a data range necessary for constructing an AI model from the acquired operating data. In this case, for example, a data area where the pressure, flow rate, or liquid level values ​​are zero, or a range excluding data at the start or switchover of plant operation, may be extracted.

[0070] The driving data time series visualization element is a processing element that visualizes acquired driving data in time series. The driving data time series visualization element is a module that executes, for example, a process of displaying each acquired driving data in chronological order, a process of displaying the driving data in a histogram, a process of displaying the correlation between each driving data, or a process of displaying the average / maximum / minimum values ​​of each driving data.

[0071] The operation data processing / visualization element is a processing element that calculates parameters that are not directly measured in the plant based on acquired operation data and visualizes the parameters. The operation data processing / visualization element is a processing element that executes a process to calculate a reaction rate from temperature data and concentration data acquired as operation data and display the calculated reaction rate in chronological order. The operation data processing / visualization element may also execute a process to divide the acquired operation data by the flow rate and visualize the result in the form of a value per unit flow rate (e.g., heat input per unit flow rate).

[0072] The driving data sufficiency check element is a processing element that compares the acquired driving data with the data tag identified by the acquired data tag identification element and the acquisition period identified by the data acquisition period identification element, and determines whether the required type of driving data and period are sufficient. The driving data sufficiency check element is, for example, a module that executes a process of comparing the identified data tag with the acquired driving data and a process of comparing the identified period with the acquired driving data, and executes a process of displaying the type of data or period if there is an excess or deficiency of the type of driving data or the period.

[0073] The driving data storage element is a processing element that executes a process of storing the acquired driving data in a storage unit.

[0074] The processing element storage unit 131 and / or the processing element storage unit 231 further includes the following processing elements for each piece of target output information.

[0075] 2. Processing elements for steady-state fluid simulation The processing elements for constructing a model with AI-based steady-state fluid simulation as target output information include a stable operation region extraction element, a simulation input data determination element, a simulation convergence element, an AI learning data generation element, and a learning execution element.

[0076] The stable operation region extraction element is a processing element that extracts a region of stable operation from the operation data stored in the storage unit. The stable operation region extraction element is a module that defines criteria, such as a predetermined upper limit value or lower limit value or a predetermined rate of change, for each operation data to be extracted, and executes processing to extract operation data that meets these criteria.

[0077] The simulation input data determination element is a processing element that determines the data to be input to a steady-state fluid simulation. The simulation input data determination element is, for example, a module that determines parameters (temperature, pressure, composition, etc.) and data points (such as the inlet, outlet, and specific internal locations of equipment) that affect the fluid state represented in the simulation, and executes processing to determine the corresponding operating data as input data.

[0078] The simulation execution element is a processing element that executes a simulation using input data determined by the simulation input data determination element. The simulation execution element may execute a process to acquire an existing simulator or a process to build a new simulator. The simulation execution element may also execute a process to adjust parameters in the simulation so that the simulation results converge within a certain range during the execution of the simulation.

[0079] The AI ​​learning data generation element is a processing element that prepares a data set of input data determined by the simulation input data determination element and corresponding simulation results, and generates data for AI learning. In addition, the AI ​​learning data generation element may be set with a range of learning data and a distribution of data suitable for further improving the accuracy of the AI, and learning data with the set range and distribution may be generated.

[0080] The learning execution element is a processing element that executes AI learning processing using the learning data generated by the AI ​​learning data generation element. The learning execution element is, for example, a module in which a learning algorithm is defined.

[0081] 3. Processing Elements for Anomaly Detection As processing elements for constructing an AI-based anomaly detection model for plant operation, the processing element storage unit includes a data classification element, a data preprocessing element, a learning data generation element, a learning execution element, and an AI verification element.

[0082] The data classification element is a processing element that classifies the operation data stored in the storage unit into data corresponding to abnormal operation and data corresponding to normal operation. The data classification element is a module that, for example, acquires the time when an abnormality occurred in the operation of the plant, identifies each corresponding operation data, identifies the characteristics (values, rate of change of values, etc.) of the operation data when the abnormality occurred, and classifies the data when the abnormality occurred from the time-series operation data.

[0083] The data preprocessing element is a processing element that processes data so that operation data when an abnormality occurs and operation data when normal are distinguishable. The data preprocessing element is, for example, a module that executes a process of adding operation data when an abnormality occurs and operation data when normal are respectively added.

[0084] The learning data generation element is a processing element that generates learning data for training the AI. The learning data generation element is, for example, a module that prepares operating data labeled with whether or not it is data generated when an abnormality occurs. Note that there are limited situations in which abnormalities occur during plant operation, and there are cases in which an abundance of operating data generated when an abnormality occurs is not obtained. Therefore, when the amount of operating data generated when an abnormality occurs to be used for learning is limited, the learning data generation element may execute a process of generating operating data generated when an abnormality occurs through simulation and adding the data as learning data.

[0085] The learning execution element is a processing element that executes AI learning using the learning data generated by the learning data generation element. The learning execution element is, for example, a module in which a learning algorithm is defined.

[0086] The AI ​​verification element is a processing element that verifies whether the AI ​​learned by the learning execution element can correctly determine driving abnormalities. The AI ​​verification element is a module that executes a process to verify whether the AI ​​can correctly determine whether an abnormality exists by, for example, acquiring driving data from a period different from the driving data used to learn the AI ​​and information indicating whether the driving data is from the time an abnormality occurred, and inputting the driving data from that period into the constructed AI. The AI ​​verification element may also include a process to define a reference threshold (e.g., the number of times an abnormal value is detected within a specified time) that identifies the occurrence of an abnormality. The reference threshold may be selected or modified from a previous definition.

[0087] 4. Processing elements for reaction models The processing elements for constructing a model with an AI-based reaction model as target output information include a prediction data range determination element, an operation data preprocessing element, a reaction analysis element, a learning data generation element, and a learning execution element.

[0088] The prediction data range determination element is a processing element that determines the range of data to be predicted by an AI-based reaction model. The prediction data range determination element is a module that executes processing to determine the data range to be predicted by the reaction model to be constructed, based on, for example, the progress of reactions that may occur during plant operation (reaction rate, catalyst activity, etc.).

[0089] The operating data preprocessing element is a processing element that acquires operating data from the storage unit and performs preprocessing necessary for constructing a reaction model.

[0090] The reaction analysis element is a processing element that analyzes one or more reaction paths that may occur in a target plant facility or process, the occurrence rate of each reaction, etc. The reaction analysis element may be, for example, a module in which a reaction path and occurrence rate are set in advance for each plant facility or each process, or a module that acquires plant design information and operation data, and analyzes and identifies the reaction path and occurrence rate based on the acquired data.

[0091] The learning data generation element is a processing element that generates learning data for learning an AI reaction model. The learning data generation element is, for example, a module that executes a process of linking the driving data preprocessed by the driving data preprocessing element with each reaction path and its occurrence rate analyzed by the reaction analysis element to generate data.

[0092] The learning execution element is a processing element that executes AI learning using the learning data generated by the learning data generation element. The learning execution element is, for example, a module in which a learning algorithm is defined.

[0093] The processing elements described above can be held as common elements or processing elements specialized for each target output information. In model development using the development support device 200, all of these processing elements can be used, or some of them can be created by the developer. Developers can combine these pre-prepared processing elements to quickly and easily develop models.

[0094] According to the development support system of this embodiment, knowledge and resources gained from previous model development are utilized, thereby improving the efficiency of model development, which has traditionally been carried out individually, and significantly reducing the cost, time, and labor required to develop a new model. Furthermore, because it is possible to divide the work involved in model development, process engineers, data scientists, AI developers, and the like can each focus on their essential tasks.

[0095] The present invention has been described above based on the embodiments. These embodiments are merely examples, and it will be understood by those skilled in the art that various modifications are possible in the combination of the components and treatment processes, and that such modifications are also within the scope of the present invention.

[0096] In the embodiment, an example has been described in which processing elements constituting a previously developed model are stored in advance in the processing element storage unit 131. In another example, information about previously developed models may be collected when the processing element list acquisition unit 222 acquires a list of processing elements. In this case, the processing element storage unit 131 may also be temporarily generated.

[0097] 1 Development support system, 2 Communication network, 3 Development device, 4 Design device, 5 Operation control device, 10 Plant equipment, 100 Construction support device, 101 Communication device, 102 Display device, 103 Input device, 120 Processing device, 121 Information acquisition unit, 122 Processing acquisition unit, 123 Processing division unit, 124 Processing element registration unit, 130 Storage device, 131 Processing element holding unit, 200 Development support device, 201 Communication device, 202 Display device, 203 Input device, 220 Processing device, 221 Information acquisition unit, 222 Processing element list acquisition unit, 223 Output unit, 224 Processing element determination unit, 225 Processing parameter reception unit, 226 Processing order determination unit, 227 Connection element reception unit, 228 Processing element connection unit, 229 Processing element registration unit, 230 Storage device, 231 Processing element holding unit.

[0098] The present invention can be used in a support device that supports the development of a model relating to the operation of a plant facility.

Claims

1. A method for supporting the development of a model related to the operation of a plant equipment, the method being executed by a processor and including: acquiring equipment identification information of the plant equipment or process identification information of a process executed in the plant equipment; acquiring target output information of the model; and outputting a processing element list including processing elements that should constitute a development process of the model based on the equipment identification information or process identification information and the target output information.

2. The method according to claim 1, wherein the processing element list is a candidate list of processing elements that should constitute the development process of the model.

3. The method according to claim 2, wherein the processor further executes: accepting a selection of a processing element from the candidate list that is to constitute the development process of the model; and determining the selected processing element as the processing element that constitutes the development process of the model.

4. The method according to claim 1, wherein the list of processing elements is determined by the processor as processing elements that constitute the development process of the model.

5. The method according to claim 3 or 4, wherein the processor accepts input of processing parameters for the determined processing element.

6. The method of claim 1, wherein the processor further performs determining a processing order for executing the processing elements.

7. The method of claim 1, wherein the processing elements include source code or models for corresponding processes.

8. The method of claim 3 or 4, wherein the processor further executes storing the equipment identification information or process identification information, the intended output information, and the determined processing element.

9. The method of claim 3 or 4, wherein the processor further performs the step of combining the determined processing elements.

10. The method of claim 8, further comprising: receiving a processing element required to combine the determined processing element.

11. The method according to claim 1, wherein the processing elements are elements formed by dividing processes constituting a development process of a previously created model.

12. A support device comprising: an information acquisition unit that acquires equipment identification information of a plant equipment or process identification information of a process executed in the plant equipment, and target output information of a model related to the operation of the plant equipment; and an output unit that outputs a processing element list including processing elements that should constitute the development process of the model, based on the equipment identification information or process identification information and the target output information acquired by the information acquisition unit.

13. A support program for causing a computer to function as: an information acquisition unit that acquires equipment identification information of a plant equipment or process identification information of a process executed in the plant equipment, and target output information of a model related to the operation of the plant equipment; and an output unit that outputs a processing element list including processing elements that should constitute the development process of the model, based on the equipment identification information or process identification information and target output information acquired by the information acquisition unit.

14. A method for constructing a development support system for a second model related to the operation of a plant equipment, the method being executed by a processor and including: acquiring equipment identification information of the plant equipment that is the subject of a developed first model or process identification information of a process executed in the plant equipment, and target output information of the first model; acquiring processing elements that constitute a development process of the developed first model; and storing the processing elements in correspondence with the equipment identification information or the process identification information, and / or the target output information.

15. The method according to claim 14, wherein the processor divides the processes constituting the development process of the first model to create processing elements.

16. A support device for constructing a development support system for a second model related to the operation of a plant equipment, comprising: an information acquisition unit for acquiring equipment identification information of the plant equipment that is the subject of a developed first model or process identification information of a process executed in the plant equipment, and target output information of the first model; a processing element acquisition unit for acquiring processing elements that constitute a development process of the developed first model; and a memory unit for storing the processing elements in correspondence with the equipment identification information or the process identification information, and / or the target output information.

17. A support program for constructing a development support system for a second model related to the operation of plant equipment, causing a computer to function as: an information acquisition unit that acquires equipment identification information of the plant equipment that is the subject of a developed first model or process identification information of a process executed in the plant equipment, and target output information of the first model; a processing element acquisition unit that acquires processing elements that constitute the development process of the developed first model; and a memory unit that stores the processing elements in correspondence with the equipment identification information or the process identification information, and / or the target output information.

Images