Methods for constructing support methods, support devices, support programs, and development support systems.

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

Technical Field

[0001] The present invention relates to a method for assisting in the development of a model related to the operation of plant facilities, an assisting device, an assisting program, and a method for constructing a development assistance system.

Background Art

[0002] In order to design, construct, operate, and manage a plant, various models are used. Models adapted to the type, scale, location, etc. of the plant are developed for each plant.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] While being involved in the design, construction, operation, management, etc. of many plants, the present inventors recognized that there are many common parts in the work processes for developing a model and processing elements such as algorithms constituting the model, even if the type, scale, location, etc. of the plant are different. And they came up with a technology that enables reducing the costs, time, labor, etc. required for developing a new model by actively using the knowledge and resources when developing a model in the past.

[0005] The present invention has been made in view of such a situation, and its object is to provide a technology for assisting in the development of a model related to the operation of plant facilities.

Means for Solving the Problems

[0006] To solve the above problems, a method in one aspect of the present disclosure is a method for supporting the development of a model relating to the operation of plant equipment, the method being executed by a processor and including obtaining equipment identification information of plant equipment or process identification information of a process performed on plant equipment, obtaining target output information of a model, and outputting a list of processing elements that should constitute a model development process based on the equipment identification information or process identification information and the target output information.

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

[0008] A further aspect of this disclosure is a method for constructing a development support system. This method is a method for constructing a development support system for a second model relating to the operation of plant equipment, the method comprising: being executed by a processor and obtaining equipment identification information of a plant equipment or process identification information of a process performed on a plant equipment that is the subject of a first model that has been developed, and target output information of the first model; obtaining processing elements that constitute the development steps of the first model that has been developed; and storing the processing elements in association with the equipment identification information or process identification information and / or target output information.

[0009] A further aspect of the present invention is a support device. This device is a support device for constructing a development support system for a second model relating to the operation of plant equipment, and comprises: an information acquisition unit that acquires equipment identification information of the plant equipment that is the target of the developed first model or process identification information of the process executed in the plant equipment and target output information of the first model; a processing element acquisition unit that acquires processing elements constituting the development process of the developed first model; and a storage unit that stores the processing elements in association with the equipment identification information or process identification information and / or target output information.

[0010] Furthermore, any combination of the above components, as well as conversions of the expression of the present invention between methods, apparatus, systems, recording media, computer programs, etc., are also valid embodiments of the present invention. [Effects of the Invention]

[0011] According to the present invention, it is possible to provide technology to support the development of models related to the operation of plant equipment. [Brief explanation of the drawing]

[0012] [Figure 1] This diagram schematically illustrates an example of a method for developing a model related to the operation of plant equipment. [Figure 2] This diagram shows the configuration of the development support system according to the embodiment. [Figure 3] This diagram shows the configuration of the construction support device according to the embodiment. [Figure 4] This flowchart shows the procedure for the support method according to the embodiment. [Figure 5] This figure shows an example of the data structure of the processing element holding section. [Figure 6] This figure shows an example of the data structure of the processing element holding section. [Figure 7] This diagram shows the configuration of the development support device according to the embodiment. [Figure 8] This flowchart shows the procedure for the support method according to the embodiment. [Figure 9] This figure shows an example of a screen displayed on the display device of a development support system. [Figure 10] This figure shows an example of a screen displayed on the display device of a development support system. [Modes for carrying out the invention]

[0013] Figure 1 schematically illustrates an example of a method for developing a model related to the operation of plant equipment. This figure shows the procedure for developing AI (artificial intelligence) to optimize the operation of plant equipment, as an example of a model related to the operation of plant equipment.

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

[0015] In step (2), preprocessing is performed on the operational data stored in the database server. Preprocessing may include, for example, assigning the same tag to operational data if identical or similar operational data has been assigned different tags, aligning the units of operational data, adjusting the offset of operational data, handling outliers in operational data, normalizing operational data, supplementing missing operational data, and calculating other data representing physical properties or conditions from operational data using predetermined formulas, algorithms, simulations, etc. Preprocessing may also be performed by referring to a tag correspondence table that defines the correspondence between tags assigned to operational data. The content of the preprocessing may be determined by a data scientist with expertise in organizing and analyzing data.

[0016] In step (3), the data scientist visualizes the preprocessed data by referring to design information such as a process flow diagram (PFD), heat and material balance (H&MB), etc. The data scientist visualizes the preprocessed data in a manner that matches the plant's design information, such as a time series plot, histogram, box and whisker plot, etc. The visualized data may be referred to by the data scientist or process engineer in subsequent steps or provided to the customer. The visualized data can be used, for example, to understand the operating state of the plant (such as the production volume of the product, the presence or absence of a shutdown, the efficiency of the equipment, etc.), and to confirm the validity of the selection of operating data (data type, extraction period) and the preprocessing of the operating data.

[0017] In step (4), a process engineer with expertise in the design and operation of plant facilities constructs a process simulation to simulate the operation of the plant facilities 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 uses the preprocessed data in the stable region as the input value for the process simulation to simulate the operation of the plant facilities and obtains simulation results such as the thermal efficiency of the plant.

[0019] In step (6), the data scientist constructs a surrogate model to replace the process simulation. The surrogate model takes pre-processed stable region data as input 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 pre-processed data and the simulation results from the process simulation as training data. For example, the intermediate layers of the neural network may be adjusted so that when pre-processed data is input to the input layer of the neural network, the actual data corresponding to that pre-processed data, or the simulation results output when that pre-processed data was input to the process simulation, are output from the output layer of the neural network. The surrogate model may also utilize an emulation model constructed based on operating data or a physical model constructed using first principles.

[0020] In step (7), the process engineer defines the constraints for optimizing the operation of the plant equipment. These constraints may include upper and lower limits for various parameters. The process engineer may also define the constraints based on information obtained from interviews with the customer, 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 defined constraints. The operation optimization AI inputs a large amount of pre-processed data into a surrogate model and searches for input data values ​​such that a predetermined data value among the output data becomes the optimal value, according to a predetermined optimization algorithm. Since the surrogate model can instantly calculate output data from input data, even in complex processes where simulation calculations take several days to several weeks, the surrogate model can be used to search for the optimal solution from a vast number of input data combinations.

[0022] The workflow described above is the same when developing AI for optimizing the operation of other plant equipment. Therefore, by accumulating information on the workflow used when developing a model, it becomes possible to smoothly develop similar models in the future by referring to past results and following a similar workflow. This makes it easier to formulate work plans and manage the workflow for model development, thereby reducing the cost, time, and effort required for model development.

[0023] Some of the work processes involved in developing operation optimization AI are also performed in the development of operation optimization AI and other models for other plant equipment. For example, considering that operation data is time-series data collected during the operation of plant equipment, and that the values ​​are usually expected to be continuous and it is unlikely that they will suddenly change to completely different values ​​without any context, the process of preprocessing the operation data and removing outliers that have increased or decreased by more than a predetermined rate from the previous value is a process that should be commonly performed in the development of operation optimization AI and other models for other plant equipment. If such common processes are packaged in advance, existing packages can be used when developing new models, which can significantly reduce the cost, time, and effort required for model development.

[0024] Figure 2 shows the configuration of a development support system according to an embodiment. The development support system 1 comprises 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 them in a communicative manner.

[0025] Plant equipment 10 includes equipment, machinery, devices, piping, etc., for carrying out processes in the plant. For example, in a chemical plant, plant equipment 10 includes reactors, separation equipment, drying equipment, piping, etc.

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

[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 assists in the development of the 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 the processes executed in the plant equipment 10, and the target output information of the model. Based on the acquired equipment identification information or process identification information and the target output information, it outputs a list of processing elements that should constitute the model development process. As a result, developers can develop models using processing element lists of previously developed models, thereby significantly reducing development costs, time, and effort.

[0030] The objective output information of a model is the information that the model outputs, either final or intermediate, according to the model's purpose. For example, the objective output information of a simulation model is the simulation results, and the objective output information of an operation optimization AI is the operation parameters for optimizing the operation of plant equipment 10.

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

[0032] Figure 3 shows the configuration of the construction support device 100 according to the 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 from the user of the construction support device 100 to the processing device 120. The input device 103 may be a mouse, keyboard, 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 should constitute the development process of a model related to the operation of the plant equipment 10, associating them with the equipment identification information or process identification information of the plant equipment 10, and / or the target output information of the model. The processing element holding unit 131 may also hold the source code of modules that should constitute the development process of the model, or the model itself. Furthermore, the processing element holding unit 131 may also hold variables, constants, parameters, etc., included in the source code.

[0036] The processing unit 120 comprises an information acquisition unit 121, a processing acquisition unit 122, a processing division unit 123, and a processing element registration unit 124. While these configurations can be realized using hardware components such as arbitrary circuits, a computer's CPU, memory, and programs loaded into memory, this description focuses on functional blocks realized through their coordinated operation. Therefore, it will be understood by those skilled in the art that these functional blocks can be realized in various ways using hardware alone, software alone, or a combination thereof.

[0037] Figure 4 is a flowchart illustrating the procedure for the support method according to the embodiment. Referring to Figures 3 and 4, the procedure for supporting the construction of the development support environment using the construction support device 100 will be explained. Note that the already developed model is referred to as the "first model," and the newly developed model is referred to as the "second model."

[0038] The information acquisition unit 121 acquires equipment identification information for the plant equipment that is the target of the developed first model, or process identification information for the process performed at 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 equipment identification information or process identification information from the development device 3, design device 4, development support device 200, etc. The information acquisition unit 121 may also acquire equipment identification information or process identification information from developers, etc., via the input device 103.

[0039] The information acquisition unit 121 acquires the target output information of the developed first model (S12). The target output information is information that the model outputs finally or intermediately, and in the plant optimization model described above, for example, it includes conditions such as the values ​​of control variables for optimizing the operation of the plant. 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 also acquire the target output information from a developer or the like via the input device 103. The information acquisition unit 121 may also acquire the target output information by analyzing the source code or system design drawings of the first model.

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

[0041] The processing division unit 123 divides the acquired processing into multiple processing elements as necessary, for example, when the processing acquisition unit 122 has acquired the entire first model (S16). The processing division unit 123 may divide the processing into work processes. The processing division unit 123 may also divide the processing into processing elements that are common in the development of multiple models and processing elements that are individually different depending on the type of plant or the target output information of the model. Note that if the processing acquisition unit 122 can acquire the processing of the first model for each processing element, the processing division by the processing division unit 123 does not need to be performed.

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

[0043] Figure 5 shows an example of the data structure of the processing element holding unit 131. In this example, processing elements are held for each target plant equipment, process, and issue (target output information). In addition, processing elements that are included in the model in common regardless of the target plant equipment, process, or issue are also held.

[0044] Figure 6 shows an example of the data structure of the processing element holding unit 131. In this example, a processing element holding unit 131 is provided for each work process. In the processing element holding unit 131 of each work process, processing elements are held in a matrix of the target plant equipment and processes and the target issues (target output information). Note that the processing element holding unit 131 is not limited to a relational database as shown in Figures 5 and 6, but may also be configured as a graph database in which, for example, each processing element is linked by edges to the target plant equipment and processes, and / or the target issues.

[0045] Figure 7 shows the configuration of the development support device 200 according to the 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 from the user of the development support device 200 to the processing device 220. The input device 203 may be a mouse, keyboard, 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 should constitute the development process of a model relating to the operation of the plant equipment 10, in association with the equipment identification information or process identification information of the plant equipment 10, and / or the 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 construction support device 100 and stored in the storage device 230. If the development support device 200 accesses the processing element holding unit 131 of the construction support device 100, the processing element holding unit 231 may not be provided.

[0049] The processing unit 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 reception unit 225, a processing order determination unit 226, a coupling element reception unit 227, a processing element coupling unit 228, and a processing element registration unit 229. These configurations can be realized using hardware components such as arbitrary circuits, a computer's CPU, memory, and programs loaded into memory, but here we are describing functional blocks realized through their cooperation. Therefore, it will be understood by those skilled in the art that these functional blocks can be realized in various ways using hardware alone, software alone, or a combination thereof.

[0050] Figure 8 is a flowchart illustrating the procedure of the support method according to the embodiment. Referring to Figures 7 and 8, the procedure for supporting model development using the development support device 200 will be explained.

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

[0052] The information acquisition unit 221 acquires the 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 also acquire the target output information from a developer or the like via the input device 203.

[0053] The processing element list acquisition unit 222 acquires a processing element list containing 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 also acquire the processing element list by referring to 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 Figure 5, the processing element list acquisition unit 222 acquires a processing element list by extracting processing elements that match the equipment identification information, process identification information, and target output information of the target equipment, target process, and target issue, respectively, as well as common processing elements. If the processing element holding unit 231 or the processing element holding unit 131 has the data structure shown in Figure 6, the processing element list acquisition unit 222 acquires a processing element list for each work process by extracting processing elements that match the equipment identification information, process identification information, and target output information of the target equipment, target process, and target issue, respectively, as well as common processing elements.

[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 model development process (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 the selection of processing elements that should constitute the model development process from the candidate list (S26), and determines the selected processing elements as processing elements that constitute 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 accept the selection of processing elements from a terminal device used by the developer. The processing element determination unit 224 may automatically determine the processing elements listed in the processing element list as processing elements that constitute 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 constitute the model development process. When processing elements are selected automatically, the selection of processing elements may be performed by a machine learning model. In that 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 built AIs, the target output information, and the processing elements included in the development process of the said AI, as well as a general AI construction flow that is 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 for 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 receive processing parameters from a terminal device used by the developer. For example, if the processing element relates to outlier removal processing in the preprocessing of driving data, the unit receives input of parameters that serve as the criteria for removing outliers. The parameters that serve as the criteria for removing outliers may be, for example, based on the interquartile range (IQR) of the acquired data. • The lower limit is (first quartile) - 1.5 × IQR • The upper limit is (third quartile) + 1.5 × IQR This may also be the case. Furthermore, processing parameters may be set without requiring input from the developer. In this case, the processing element may store initial setting parameters, such as the setting parameters in the first model. In this case, the system may be configured so that the developer can further review the initial setting parameters and edit them as needed.

[0057] The processing order determination unit 226 determines the processing order in which the processing elements are 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 also 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 predetermined criteria. The predetermined criteria may be, for example, the processing order in the first model, or criteria based on the processing order in AI related to the operation of multiple plants built in the past, such as the first model, or criteria based on the order in AI development in fields other than plant operation. Such criteria for processing order may refer to those stored in the processing element holding unit 231, or may be learned based on the processing order of AI built in the past.

[0058] The coupling element receiving unit 227 receives the processing elements necessary to combine the determined processing elements (S34). If 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 the input information for the subsequent processing element from the output information of the preceding processing element may be added as a coupling element. The coupling element receiving unit 227 may also receive source code and parameters of coupling elements from the developer via the input device 203. The coupling element receiving unit 227 may also receive source code and parameters of coupling elements from a terminal device used by the developer. The coupling element receiving unit 227 may automatically generate coupling elements based on the output information of the preceding processing element and the input information of the subsequent processing element.

[0059] The processing element coupling unit 228 combines the determined processing elements (S36). The processing element coupling unit 228 combines the determined processing elements and coupling elements in the determined processing order. This generates the second model.

[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 constitute the development process of the developed model to be used in the development of models to be developed in the future.

[0061] If the developed model is modified or added to, the contents of the processing element holder 131 and the processing element holder 231 may be updated accordingly.

[0062] Figure 9 shows an example of a screen displayed on the display device 202 of the development support device 200. This figure shows a user interface screen for the developer to select the type of equipment to be developed and the type of model or problem. Once 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] Figure 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 has been acquired by the processing element list acquisition unit 222 according to the type of device and the type of model or problem selected by the developer.

[0064] Next, an example of a processing element held by the processing element holding unit 131 and / or processing element holding unit 231 is shown.

[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 equipment identification information or process identification information entered as the target plant equipment for the model being developed. For example, the plant design information acquisition element is a module that executes the process of acquiring the process flow diagram, P&ID diagram, data sheets for each piece of equipment, etc., of the plant targeted by the development model.

[0067] The acquired data tag identification element is an element that identifies the data tags (equipment that constitutes the plant and parameters related to that equipment) necessary for developing the target model from the information contained in the plant design information acquired by the plant design information acquisition element. The acquired data tag identification element may be a module consisting of, for example, a process to identify the equipment on the P&ID of the target plant of the model to be developed, as well as the inlet and outlet conditions (material, temperature, pressure, flow rate) of each piece of equipment; a process to acquire the target equipment and parameters of the operating data used in the development of a similar model developed in the past; and a process to identify the data tags to be acquired by comparing the target equipment and parameters acquired for the previously developed model with the equipment, inlet and outlet conditions of the target plant of the model to be developed in the past.

[0068] The data acquisition period specification element is a processing element that specifies the period for acquiring plant operation data corresponding to the data tags to be acquired, as identified by the data acquisition tag specification element. The data acquisition period specification element is, for example, a module that sets a period to ensure the accuracy of the model being built now, based on the period of operation data used to build a previously constructed model.

[0069] The operational data acquisition element is a processing element that acquires operational data of the plant over a period specified by the data acquisition period specification element, corresponding to the data tags identified by the data acquisition tag specification element. The operational data acquisition element may further extract the data range necessary for building the AI ​​model from the acquired operational data. In this case, for example, data areas where the values ​​for pressure, flow rate, or liquid level are zero, or data during plant operation startup and switchover may be excluded from the extracted range.

[0070] The driving data time series visualization element is a processing element that visualizes acquired driving data in a time series. For example, the driving data time series visualization element is a module that performs processes such as displaying each acquired driving data in a time series, displaying driving data as a histogram, displaying the correlation between each driving data, or displaying the average / maximum / minimum values ​​of each driving data.

[0071] The operational data processing / visualization element is a processing element that calculates parameters that are not directly measured in the plant based on acquired operational data and visualizes those parameters. For example, the operational data processing / visualization element calculates the reaction rate from temperature data and concentration data acquired as operational data and performs processing to display the calculated reaction rate in time series. Alternatively, the operational data processing / visualization element may perform processing to divide the acquired operational data by the flow rate and visualize it in the form of a value per unit flow rate (for example, heat input per unit flow rate).

[0072] The driving data sufficiency check element is a processing element that compares the data tags identified by the acquired data tag identification element and the acquisition period identified by the data acquisition period identification element with the acquired driving data, and determines whether the required types and periods of driving data are satisfied. The driving data sufficiency check element is a module that, for example, performs the process of comparing the identified data tags with the acquired driving data, and the process of comparing the identified period with the acquired driving data, and if there are any excesses or deficiencies in the types or periods of driving data, it performs the process of displaying those data types or periods.

[0073] The operation data storage element is a processing element that performs the process of saving the acquired operation data to the storage unit.

[0074] The processing element holding unit 131 and / or the processing element holding unit 231 further include the following processing elements for each target output information.

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

[0076] The stable operation area extraction element is a processing element that extracts areas of stable operation from the operation data stored in the memory unit. The stable operation area extraction element is a module that defines criteria such as a predetermined upper or lower limit or a predetermined rate of change for each operation data to be extracted, and performs a process to extract operation data that satisfies these criteria.

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

[0078] The simulation execution element is a processing element that executes a simulation using the input data determined by the simulation input data determination element. The simulation execution element may perform a process to acquire an existing simulator or a process to construct a new simulator. The simulation execution element may also perform a process to adjust the parameters within the simulation so that the simulation results converge to a certain range while the simulation is being executed.

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

[0080] A learning execution element is a processing element that executes the AI ​​learning process using the learning data generated by the AI ​​learning data generation element. A 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 holder unit includes a data classification element, a data preprocessing element, a training data generation element, a training execution element, and an AI verification element.

[0082] The data classification element is a processing element that classifies the operational data stored in the memory unit into data corresponding to abnormal operation and data corresponding to normal operation. For example, the data classification element is a module that obtains the time when an abnormality occurred in the plant's operation, identifies the corresponding operational data, identifies the characteristics of the operational data at the time of the abnormality (value, rate of change of value, etc.), and classifies the data at the time of the abnormality from the time-series operational data.

[0083] A data preprocessing element is a processing element that transforms data so that it can distinguish between operating data during abnormal conditions and operating data during normal conditions. For example, a data preprocessing element is a module that performs processing to add operating data during abnormal conditions and operating data during normal conditions, respectively.

[0084] The learning data generation element is a processing element that generates learning data for training an AI. For example, the learning data generation element is a module that prepares operating data labeled to indicate whether or not an anomaly occurred. However, anomalies occur only in limited situations during plant operation, and it may not be possible to acquire abundant operating data when an anomaly occurs. Therefore, if the operating data from anomalies available for training is limited, the learning data generation element may perform a process to generate operating data from anomalies through simulation and add it as learning data.

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

[0086] The AI ​​verification element is a processing element that verifies whether the AI ​​trained by the learning execution element can correctly determine driving anomalies. For example, the AI ​​verification element is a module that performs a process to verify whether the AI ​​can correctly determine the presence or absence of an anomaly by obtaining driving data from a different period than the driving data used to train the AI, and information indicating whether that driving data is from a time when an anomaly 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 threshold value for identifying an anomaly (for example, the number of times an anomaly value is detected within a predetermined time). The threshold value may be selected or modified from past definitions.

[0087] 4. Processing elements for reaction models The system includes processing elements for constructing a model that uses an AI-based reaction model as the target output information, such as a prediction data range determination element, a driving data preprocessing element, a reaction analysis element, a training data generation element, and a training execution element.

[0088] The predictive data range determination element is a processing element that determines the range of data to be predicted by the AI-based reaction model. For example, the predictive data range determination element is a module that performs the process of determining the data range to be predicted by the reaction model to be constructed, based on the progress of reactions that may occur in plant operation (reaction rate, catalyst activity, etc.).

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

[0090] A reaction analysis element is a processing element that analyzes one or more reaction pathways and the occurrence rate of each reaction that may occur in a target plant facility or process. For example, a reaction analysis element may be a module in which reaction pathways and occurrence rates are pre-defined for each plant facility or process, or it may be a module that acquires plant design information and operating data, analyzes the acquired data to identify reaction pathways and occurrence rates.

[0091] The learning data generation element is a processing element that generates learning data for training an AI reaction model. For example, the learning data generation element is a module that performs the process of generating data by linking the operation data preprocessed by the operation data preprocessing element with each reaction pathway and its occurrence rate analyzed by the reaction analysis element.

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

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

[0094] According to this embodiment of the development support system, since it utilizes knowledge and resources from past model development, it can streamline model development, which was previously done individually, and significantly reduce the cost, time, and effort required for developing new models. Furthermore, it enables the division of labor in model development, allowing process engineers, data scientists, AI developers, etc., to concentrate on their respective essential tasks.

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

[0096] In the embodiment described, an example was given in which processing elements constituting a previously developed model are stored in the processing element holding unit 131 in advance. In another example, when the processing element list acquisition unit 222 acquires a list of processing elements, information about a previously developed model may be collected. In this case as well, the processing element holding unit 131 may be generated temporarily. [Explanation of symbols]

[0097] 1 Development support system, 2 Communication network, 3 Development equipment, 4 Design equipment, 5 Operation control device, 10 Plant equipment, 100 Construction support equipment, 101 Communication equipment, 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 equipment, 201 Communication equipment, 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 sequence determination unit, 227 Coupling element reception unit, 228 Processing element coupling unit, 229 Processing element registration unit, 230 Storage device, 231 Processing element holding unit. [Industrial applicability]

[0098] This invention can be used in support devices that assist in the development of models related to the operation of plant equipment.

Claims

1. A method for supporting the development of models related to the operation of plant equipment, The aforementioned method is performed by a processor, To obtain equipment identification information of the plant equipment or process identification information of a process executed in the plant equipment, To obtain the target output information of the aforementioned model, The process involves referring to a processing element holding unit that stores processing elements that constitute the development process of a model relating to the operation of plant equipment, associating them with the equipment identification information or process identification information and the target output information, and extracting processing elements from the processing element holding unit that match the acquired equipment identification information or process identification information and the acquired target output information, thereby outputting a processing element list that includes the processing elements that constitute the development process of the model. A method that includes this.

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

3. The aforementioned processor, The system accepts the selection of processing elements that should constitute the development process of the model from the aforementioned candidate list, The selected processing elements are determined to be processing elements that constitute the development process of the model, Further execution The method according to claim 2.

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

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

6. The processor further performs the task of determining the processing order in which to execute the processing elements. The method according to claim 1.

7. The processing element includes source code or a model relating to the corresponding processing. The method according to claim 1.

8. The processor further stores the equipment identification information or process identification information, the target output information, and the determined processing elements. The method according to claim 3 or 4.

9. The processor further performs the task of combining the determined processing elements. The method according to claim 3 or 4.

10. The processor further performs the task of receiving processing elements necessary to combine the determined processing elements. The method according to claim 8.

11. The aforementioned processing element is an element formed by dividing the processing that constitutes the development process of a previously created model. The method according to claim 1.

12. 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 relating to the operation of the plant equipment, Based on the equipment identification information or process identification information acquired by the information acquisition unit and the target output information, the output unit refers to a processing element holding unit that holds processing elements that should constitute the development process of the model in association with the target equipment or target process and target issue, extracts processing elements from the processing element holding unit that match the acquired equipment identification information or process identification information and the target output information, and outputs a processing element list that includes the processing elements that should constitute the development process of the model. A support device equipped with the following features.

13. Computers, 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 relating to the operation of the plant equipment, Based on the equipment identification information or process identification information acquired by the information acquisition unit and the target output information, the output unit refers to a processing element holding unit that holds processing elements that should constitute the development process of the model in association with the target equipment or target process and target issue, extracts processing elements from the processing element holding unit that match the acquired equipment identification information or process identification information and the target output information, and outputs a processing element list that includes the processing elements that should constitute the development process of the model. A support program to enable it to function as such.

14. A method for constructing a development support system for a second model relating to the operation of plant equipment, The aforementioned method is performed by a processor, To obtain the equipment identification information of the plant equipment or the process identification information of the process executed in the plant equipment, which is the target of the first model developed, and the target output information of the first model, To obtain the processes that constitute the development process of the first model developed, The process obtained above is divided into multiple processing elements, The divided processing elements are stored in association with the equipment identification information or the process identification information and / or the target output information. Includes, The stored processing elements are extracted during the development of the second model based on the equipment identification information or process identification information and the target output information of the second model, and output as a processing element list including processing elements that should constitute the development process of the second model. method.

15. A support device for constructing a development support system for a second model related to the operation of plant equipment, An information acquisition unit that acquires equipment identification information of the plant equipment or process identification information of a process executed in the plant equipment, which is the target of the first model developed, and the target output information of the first model, A processing acquisition unit that acquires the processes constituting the development process of the first model developed, A processing division unit that divides the acquired processing into multiple processing elements, A storage unit that stores the divided processing elements in association with the equipment identification information or the process identification information and / or the target output information, Equipped with, The processing elements stored in the memory unit are extracted during the development of the second model based on the equipment identification information or process identification information of the second model and the target output information, and output as a processing element list including processing elements that should constitute the development process of the second model. Support equipment.

16. A support program for constructing a development support system for a second model related to the operation of plant equipment, Computers, An information acquisition unit that acquires equipment identification information of the plant equipment or process identification information of a process executed in the plant equipment, which is the target of the first model developed, and the target output information of the first model, A processing acquisition unit that acquires the processes constituting the development process of the first model developed, A processing division unit that divides the acquired processing into multiple processing elements, A storage unit that stores the divided processing elements in association with the equipment identification information or the process identification information and / or the target output information, To make it function as, The processing elements stored in the memory unit are extracted during the development of the second model based on the equipment identification information or process identification information of the second model and the target output information, and output as a processing element list including processing elements that should constitute the development process of the second model. Support program.

Images