Automatic modeling method and system for thermal hydraulic model, storage medium and electronic equipment

Abstract

The invention relates to an automatic modeling method and system for a thermal hydraulic model, a storage medium and electronic equipment, and the modeling method comprises the steps: carrying out the data extraction in a system specification, and obtaining the modeling data of a process system; carrying out deep learning to obtain a modeling principle of the process system; generating a modeling design drawing of the process system according to the modeling principle and the modeling data; according to a modeling principle and the modeling design drawing, generating a process system node model; generating a process system model based on the process system node model; and dynamically testing the process system model based on the modeling data until the verification is passed, and finishing the modeling of the process system model. According to the method, the AI technology can be utilized to automatically extract data required by modeling, and the process system model is automatically constructed and checked, so that the modeling efficiency and modeling quality of the process system model can be remarkably improved, and human errors are effectively avoided.

Description

Technical Field

[0001] The present invention relates to the technical field of thermal hydraulic process system modeling, and more particularly to a thermal hydraulic model automatic modeling method, system, storage medium and electronic equipment. Background Art

[0002] Nuclear power plant full-scale simulators and engineering simulators are crucial to the safe and economical operation of nuclear power plants and are essential components of nuclear power unit design, commissioning, and operation. Due to the numerous system equipment and parameters involved in nuclear power plant units, the number of thermal and hydraulic models required is large and complex. Existing modeling techniques rely on extensive system data manuals for input, and compiling this data required for preliminary modeling design is time-consuming and inefficient. Modeling quality varies widely due to the technical expertise of modeling engineers. Modeling and commissioning require extensive data input, which is currently performed manually, leading to omissions and errors and significant deviations in model calculations. Existing model commissioning techniques rely heavily on the experience of the modeling engineer and are therefore time-consuming. After modeling is complete, consistency checks rely on manual testing and review. Summary of the Invention

[0003] The technical problem to be solved by the present invention is to provide a method, system, storage medium and electronic equipment for automatic modeling of a thermal hydraulic model in response to the problems existing in the prior art.

[0004] The technical solution adopted by the present invention to solve the technical problem is to construct an automatic modeling method for a thermal hydraulic model, comprising the following steps:

[0005] Extract data from the system manual to obtain modeling data for the process system;

[0006] Conducting in-depth study on the functions of each module of the process system to obtain the modeling principles of the process system;

[0007] generating a modeling design diagram of the process system according to the modeling principles and the modeling data;

[0008] Generate a process system node model according to the modeling principles and the modeling design diagram;

[0009] generating a process system model based on the process system node model;

[0010] The process system model is dynamically tested based on the modeling data until the modeling of the process system model is completed after verification.

[0011] In the automatic modeling method for thermal hydraulic modeling of the present invention, extracting data from the system specification to obtain modeling data of the process system includes:

[0012] Extracting normal operating parameters of the process system and generating a normal operating parameter table;

[0013] Extracting target equipment data of the process system and generating an equipment data table;

[0014] Extracting target pipeline data of the process system and generating a pipeline data table;

[0015] Extract the specification content of the process system and generate a test program.

[0016] In the automatic modeling method for a thermal hydraulic model of the present invention, generating a modeling design diagram of the process system according to the modeling principle and the modeling data includes:

[0017] Determine the equipment and pipelines to be simulated based on the modeling principles;

[0018] Determining the location of a pressure node in the process system flow network;

[0019] Marking the positions of the equipment to be simulated, the pipeline to be simulated, and the pressure nodes to generate a modeling design diagram of the process system;

[0020] Name each pressure node in the modeling design diagram in sequence and generate a pressure node table.

[0021] In the automatic modeling method for thermal hydraulic model of the present invention, generating the process system node model according to the modeling principle and the modeling design diagram includes:

[0022] generating an initial node model of the process system according to the modeling design diagram;

[0023] Naming the corresponding flow network nodes in the initial node model according to the node names in the pressure node table;

[0024] Connecting the pressure nodes in the initial node model based on the modeling principle;

[0025] Naming the pipelines in the initial node model according to the names of the upstream and downstream pipelines of the pressure nodes in the pressure node table, and generating a node graph pipeline data table;

[0026] Adding the device to be simulated to the initial node model;

[0027] Naming the devices in the initial node model according to the device data table;

[0028] The node graph pipeline data table is modified according to the pipeline data table to obtain the process system node model.

[0029] In the automatic modeling method for thermal hydraulic models of the present invention, generating a process system model based on the process system node model includes:

[0030] Based on the process system node model, an initial system model is generated using a template-driven generation method;

[0031] The initial system model is optimized using a reinforcement learning algorithm to obtain the process system model.

[0032] In the automatic modeling method for thermal hydraulic models of the present invention, generating a process system model based on the process system node model includes:

[0033] Determining a preset pressure value for each pressure node based on pressure data in the system specification in the modeling data;

[0034] Calculate the admittance value of each pipeline according to the preset pressure value of each pressure node according to the flow network calculation formula, and store the admittance value of each pipeline in the corresponding pipeline data in the pipeline data table of the node graph;

[0035] Calculating according to the CV curve parameters of the valve and the pipeline diameter to obtain the admittance values of the valve and the filter, and saving the admittance values of the valve and the filter in the device data table;

[0036] Importing the data in the pressure node table into the process system node model and saving the data;

[0037] The equipment data table and the pipeline data table are imported into the process T system node model and saved to obtain the process system model.

[0038] In the automatic modeling method for a thermal hydraulic model of the present invention, the step of dynamically testing the process system model based on the modeling data until the modeling of the process system model is completed after verification includes:

[0039] Determine the normal operating state of the process system model using the normal operating state data in the system specification in the modeling data;

[0040] Based on the normal operating status of the process system model, running the process system model on a simulation platform and collecting real-time operating parameters of the process system model;

[0041] Comparing the real-time operating parameters with corresponding parameters in the normal operating parameter table;

[0042] If the real-time operating parameters are within the deviation range, it is determined that the process system model test has passed;

[0043] If the real-time operating parameter is not within the deviation range, adjusting the admittance parameter value of the valve or pipeline until it is within the deviation range;

[0044] Performing system testing on the process system model according to the test procedure;

[0045] After the system test is completed, a test report of the process system model is generated.

[0046] The present invention also provides a thermal hydraulic model automatic modeling system, comprising:

[0047] A modeling data extraction unit is used to extract data from the system specification to obtain modeling data of the process system;

[0048] a modeling principle determination unit, configured to perform in-depth learning on the functions of each module of the process system to obtain the modeling principle of the process system;

[0049] a modeling design drawing generating unit, configured to generate a modeling design drawing of the process system according to the modeling principle and the modeling data;

[0050] A node model generating unit, configured to generate a process system node model according to the modeling principle and the modeling design diagram;

[0051] A system model generating unit, configured to generate a process system model based on the process system node model;

[0052] The system model testing unit is used to perform dynamic testing on the process system model based on the modeling data until the modeling of the process system model is completed after verification.

[0053] The present invention also provides a storage medium storing a computer program, wherein the computer program is suitable for being loaded by a processor to execute the steps of the above-mentioned method for automatic modeling of a thermal-hydraulic model.

[0054] The present invention also provides an electronic device comprising a memory and a processor, wherein the memory stores a computer program, and the processor executes the steps of the above-mentioned automatic modeling method for thermal hydraulic models by calling the computer program stored in the memory.

[0055] The automatic modeling method, system, storage medium and electronic device for thermal hydraulic modeling of the present invention have the following beneficial effects: the modeling method includes: extracting data from the system specification to obtain modeling data of the process system; obtaining the modeling principles of the process system through deep learning; generating a modeling design diagram of the process system based on the modeling principles and modeling data; generating a process system node model based on the modeling principles and modeling design diagram; generating a process system model based on the process system node model; and dynamically testing the process system model based on the modeling data until the modeling of the process system model is completed after verification. The present invention can use AI technology to automatically extract the data required for modeling, automatically construct a process system model and check the model, which can significantly improve the modeling efficiency and quality of the process system model and effectively avoid human errors. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] The present invention will be further described below with reference to the accompanying drawings and embodiments, in which:

[0057] Figure 1 This is a flow chart of an embodiment of the automatic modeling method for a thermal hydraulic model provided by the present invention;

[0058] Figure 2 This is a flow chart of an embodiment of modeling data extraction provided by the present invention;

[0059] Figure 3 The generative modeling design provided by the present invention Figure 1 Schematic diagram of the process of the embodiment;

[0060] Figure 4 This is a flow chart of an embodiment of constructing a process system node model provided by the present invention;

[0061] Figure 5 This is a flow chart of an embodiment of a process system model construction provided by the present invention;

[0062] Figure 6 This is a flow chart of an embodiment of a test process system model provided by the present invention;

[0063] Figure 7 It is a logic block diagram of the automatic modeling system for thermal hydraulic model provided by the present invention. DETAILED DESCRIPTION

[0064] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0065] In order to solve the problems existing in the existing thermal hydraulic modeling, the present invention provides a method for automatic thermal hydraulic modeling, which can be applied to nuclear power plants. The method can be implemented based on AI technology. Specifically, AI technology (i.e., natural language processing technology) can be used to extract the modeling data required for building a process system model from the system specification, and then AI technology can be used to learn the modeling principles of the process system and determine the equipment and pipelines that need to be simulated, as well as the equipment and pipelines that need to be simplified, and the node positions in the system flow network. AI technology (i.e., graphic generation technology) is then used to generate a modeling design diagram (i.e., a system flow network node diagram), and then the existing thermal hydraulic model of the process system node model is used to train AI (generative AI) to model the process system. A model file is generated based on the marked system flow network diagram, and each module in the model is named according to the naming rules. At the same time, the generated normal operating parameters, equipment data, and pipeline data table data are input into the built model. Finally, the AI model is tested and verified to complete the automatic modeling of the thermal hydraulic model.

[0066] In a preferred embodiment, Figure 1 As shown, the automatic modeling method of the thermal hydraulic model includes the following steps:

[0067] Step S100: extracting data from the system specification to obtain modeling data of the process system.

[0068] Specifically, in this step, AI technology can be used to extract the data required for the process system model (i.e., modeling data) from the system manual that needs to be modeled. The extraction of modeling data can be performed using deep learning-based convolutional neural network (CNN) technology to extract and train the content in the system manual (e.g., PDF format). Through training and learning of text data, various specific professional terms, professional symbols, and logical combinations of the former two can be identified.

[0069] In some embodiments, as Figure 2 As shown, extracting data from the system specification to obtain modeling data for the process system includes the following steps:

[0070] Step S101: extracting normal operating parameters of the process system and generating a normal operating parameter table.

[0071] Specifically, in this step, AI technology can be used to extract parameters. The normal operating parameters of the process system need to be determined according to the process system to be modeled. For example, taking an important plant water system as an example, it is necessary to extract the operating parameters such as temperature, pressure, flow rate, etc. required for the normal operation of the system, and after extracting these normal operating parameters, generate a normal operating parameter table in accordance with the prescribed format. The prescribed format here can be determined according to the actual modeling requirements, and the present invention does not make specific limitations. Optionally, the normal operating parameter table may include but is not limited to the type, unit, and numerical values under different operating conditions of the main system parameters.

[0072] Step S102: extract target equipment data of the process system and generate an equipment data table.

[0073] Specifically, in this step, AI technology can be used to extract equipment data. The target equipment here refers to the main equipment in the process system. For example, taking a critical plant water system as an example, the main equipment data of this system may include, but is not limited to: pump and fan data: type, flow-head curve, power, minimum NPSH, height, dimensions, speed, etc.; motor data: operating current, voltage, frequency, speed, power, etc.; valves are more complex and are categorized by type into manual valves, electric valves, pneumatic valves, hydraulic valves, solenoid valves, check valves, safety valves, regulating valves, and bursting valves. Manual valves, electric valves, pneumatic valves, hydraulic valves, regulating valves, and bursting valves require data such as dimensions, CV curves, valve opening and closing time, valve position limits, and admittance. Pneumatic and hydraulic valves also require dynamic pressure limits. Check valves and safety valves require data such as dimensions, operating pressure, and reseating pressure. Filter: type, size, design pressure difference, height, admittance parameter value, etc.; heat exchanger: type, size, height, heat exchange area, number of heat exchange tubes, heat exchange tube diameter, heat exchange tube length, heat exchange tube wall thickness, heat exchange tube structure layout, heat exchanger wall thickness, metal material, heat capacity, working fluid flow on both sides of the heat exchanger, inlet and outlet temperature, inlet and outlet pressure, etc.; water tank: type, volume, height, height, layout, etc.; sensors are divided into two types according to the output method: output measurement value and output action signal, and are divided into pressure, temperature, flow, pressure difference, liquid level, vibration, displacement, valve position, concentration, etc. according to the measured physical properties.

[0074] After extracting the above-mentioned main equipment data, a equipment data table is generated according to a prescribed format. The equipment data table includes the equipment name, equipment type, and the characteristics of the above-mentioned different equipment. The prescribed format here can be determined according to actual modeling requirements and is not specifically limited by the present invention.

[0075] Step S103: extracting target pipeline data of the process system and generating a pipeline data table.

[0076] Specifically, in this step, AI technology can be used to extract the target pipeline data of the process system. The target pipeline here refers to the main pipeline in the process system, which is specifically determined by the actual process system. The target pipeline data may include but is not limited to: the length, diameter, inlet and outlet height, angle and other values of the target pipeline. After the target management data is extracted, a pipeline data table is generated according to the prescribed format. The prescribed format here can be determined according to the actual modeling requirements, and the present invention does not make specific limitations. Optionally, the pipeline data table may include but is not limited to the pipeline name, length, diameter, inlet and outlet height, angle, measurement unit and other contents.

[0077] Step S104: extract the specification content of the process system and generate a test program.

[0078] Specifically, in this step, AI technology can be used to extract the content in the process system manual and generate a test program. The test program may include, but is not limited to: normal operating status of system equipment, normal operating parameter values, equipment start and stop operations, and system fault operation (if any). The test program may also include: equipment operating status, operating parameter values, equipment start and stop operations, and system fault operation results in the corresponding process system model. It should be noted that if the process system model has not been built, the results of the process system model are empty.

[0079] Step S200: Conduct deep learning on the functions of each module of the process system to obtain the modeling principles of the process system.

[0080] In some embodiments, in this step, AI technology can be used to enhance the learning of the modeling principles of the process system. Specifically, AI technology is used to learn the functions of each module of the process system, such as the external features and internal parameters of modules such as pressure nodes, connecting pipelines, pumps and fans, motors, various types of valves, filters, heat exchangers, heaters, water tanks, sensors, etc. The text extracted from the process system modeling manual (PDF file) is subjected to natural language processing. Lexical analysis is performed, followed by syntactic analysis to determine the grammatical structure. Using techniques such as semantic role labeling, the semantic roles of each component in the text are understood, thereby obtaining the modeling principles of the process system. Optionally, the modeling principles of the process system may include: functional descriptions, external features, conditional judgments, and operating procedures of each basic module in the manual.

[0081] Step S300: Generate a modeling design diagram of the process system according to the modeling principles and modeling data.

[0082] In some embodiments, such as Figure 3 As shown, generating a modeling design diagram of a process system according to modeling principles and modeling data includes the following steps:

[0083] Step S301: Determine the equipment and pipelines to be simulated based on the modeling principle.

[0084] Specifically, in this step, after determining the modeling principles, AI technology can be used to determine the equipment and pipelines to be simulated, that is, the equipment and pipelines that need to be simulated, as well as the equipment and pipelines that need to be simplified. Due to the complexity of the process system, it is not necessary to simulate all equipment and pipelines. For example, some steam traps, air exhaust valves, instrument primary valves and their pipelines can be simplified or not simulated. The data tables of the equipment and pipelines that need to be simulated can be revised.

[0085] Step S302: Determine the position of the pressure node in the process system flow network.

[0086] Specifically, in this step, the positions of all pressure nodes in the process system flow network can be determined through AI training and learning. It should be noted that the pressure nodes are not clear in the process flow diagram of the system manual, but they need to be clear in the process system modeling. Due to the importance of pressure nodes in process system modeling, they represent the pressure, temperature, enthalpy, position height and other information of this section of pipeline. Pipelines need to be connected between the two pressure nodes, and the flow rate and heat continuity of the fluid can be calculated based on the mass conservation equation, energy conservation equation and momentum conservation equation of the vapor phase and liquid phase. Therefore, the pressure nodes, the pipelines connected to them and the relationship between different equipment constitute the process system model.

[0087] In some embodiments, the position of the pressure node is determined according to the following principles:

[0088] 1) Pressure nodes are required at both ends of the flow network where there are obvious pressure changes, such as the inlet and outlet of the pump, the inlet and outlet of the regulating valve, the inlet and outlet of the filter and the inlet and outlet of the heat exchanger;

[0089] (2) There are large resistances along the pipeline at both ends;

[0090] (3) Locations where bifurcated pipelines exist;

[0091] (4) The location where the pressure sensor is installed;

[0092] (5) Other locations where pressure nodes are required.

[0093] Step S303: Mark the equipment to be simulated, the pipeline to be simulated, and the pressure nodes according to their positions to generate a modeling design diagram for the process system.

[0094] In this step, AI technology can be used to mark the equipment, pipelines, and pressure nodes to be simulated on the system flowchart. Specifically, based on the equipment and pipelines to be simulated determined in step S301 and the locations of the pressure nodes determined in step S302, the AI is trained to color-code the simulated equipment, pipelines, and interfaces in the system flowchart in the system manual. For example, pressure nodes are marked in red, equipment in purple, pipelines in yellow, and external system interfaces in green. This generates a flow network design diagram with these markings, i.e., a modeling design diagram.

[0095] Step S304: Name each pressure node in the modeling design diagram in sequence and generate a pressure node table.

[0096] Specifically, after generating the modeling design diagram in step S304, AI technology is required to sequentially name each pressure node in the modeling design diagram. This involves determining the name of each pressure node in the modeling design diagram and generating a complete pressure node table. The pressure node name includes: unit name + system name + serial number + node identifier. The pressure node table may include, but is not limited to: node name, node height, node upstream and downstream pipeline names, node inertia, node initial pressure, node initial temperature, node initial enthalpy, node initial working fluid concentration, etc.

[0097] Among them, during the execution of steps S301 to S304, the output results of each step can be quality checked by the user to determine whether the AI output results are correct through manual secondary verification. If incorrect or inaccurate, the problems found in the inspection are input and the AI is re-trained and corrected through iterative training.

[0098] Step S400: Generate a process system node model according to the modeling principles and the modeling design diagram.

[0099] In some embodiments, such as Figure 4 As shown, generating a process system node model according to the modeling principles and modeling design diagram includes the following steps:

[0100] Step S401: Generate an initial node model of the process system according to the modeling design drawing.

[0101] Specifically, in this step, AI technology, such as image generation technology, can be used to generate a process system flow network node model, that is, an initial node model of the process system, based on the modeling design diagram generated in step S300. Among them, the construction of the initial node model of the process system first requires extracting information from the document to construct a flow network knowledge graph, and then using the knowledge in the flow network knowledge graph, combined with the reasoning engine based on modeling rules and the machine learning model to perform reasoning to obtain the initial node model of the process system. For example, based on the conditional judgment in the system manual and the process direction in the marked system process, the interaction relationship between the various pressure node modules of the system is inferred. Among them, the knowledge graph represents entities (such as system pressure nodes, various equipment) and the relationships between them (such as sequential relationships, causal relationships) in a graphical structure. Through the knowledge graph, the knowledge related to the modeling of the system flow network node graph can be clearly organized and managed, which is convenient for subsequent reasoning and decision-making.

[0102] Step S402: Name the corresponding flow network nodes in the initial node model according to the node names in the pressure node table.

[0103] Specifically, in this step, the corresponding flow network nodes in the initial node model are named according to the node names in the pressure node table generated in the aforementioned step S304.

[0104] Step S403: Connecting the pressure nodes in the initial node model based on the modeling principle.

[0105] Specifically, after all flow network nodes in the initial node model are named in step S402, AI technology can be used to connect the pressure nodes in the initial node model to obtain the corresponding process connection lines. These process connection lines are the pipeline models of the system flow chart in the process system specification.

[0106] Step S404: Name the pipelines in the initial node model according to the names of the upstream and downstream pipelines of the pressure nodes in the pressure node table, and generate a node graph pipeline data table.

[0107] Specifically, after completing the process connection, the pipelines in the initial node model can be named based on the names of the upstream and downstream pipelines in the pressure node table, and a node graph pipeline data table can be generated. The node graph pipeline data table generated in this step includes, but is not limited to, pipeline name, length, diameter, inlet and outlet height, angle, etc.

[0108] Step S405: Add the device to be simulated to the initial node model.

[0109] Specifically, in this step, based on the devices to be simulated determined in step S301, these devices are added to the initial node model to complete the addition of the devices to be simulated. The water tank module can be considered a pressure node with a volume and can replace the corresponding node module; the pump and fan modules can be considered booster pipelines and can replace the corresponding pipeline modules; the sensor modules are connected using data cables and cannot be connected using process cables. Pressure, temperature, differential pressure, and concentration sensors are connected to the pressure node, flow sensors are connected to the pipeline, liquid level sensors are connected to the water tank, and vibration and displacement sensors are connected to the motor accessory model; other devices can be placed directly on the pipeline module.

[0110] Step S406: Name the devices in the initial node model according to the device data table.

[0111] Specifically, in this step, the corresponding devices in the initial node model may be named according to the device data table obtained in step S102.

[0112] Step S407: Modify the node graph pipeline data table according to the pipeline data table to obtain a process system node model.

[0113] Specifically, in this step, the node graph pipeline data table generated in step S404 needs to be improved based on the pipeline data table generated in step S103. Since the modeling involves some pipeline merging, the node graph has fewer pipelines than the actual system flow chart. Therefore, to maximize the physical characteristics of the pipelines, post-merger data processing is required.

[0114] After completing the above steps, the construction of the process system node model is completed.

[0115] Step S500: Generate a process system model based on the process system node model.

[0116] Optionally, in some embodiments, generating a process system model based on a process system node model includes: generating an initial system model based on the process system node model using a template-driven generation method; and optimizing the initial system model using a reinforcement learning algorithm to obtain a process system model. That is, AI technology, such as a generative AI learning process system modeling method, can be used to generate a process system model. The template-driven generation method is as follows: first, based on modeling of process systems of the same type, a model template is predefined. The template contains common structures and parameters, and a specific process system model is generated by filling the template with information extracted and inferred from documents. The generated process system model is then optimized using a reinforcement learning algorithm. By defining an appropriate reward function, the intelligent agent is allowed to explore and learn during modeling, continuously adjusting its modeling capabilities to achieve process system modeling with optimal performance.

[0117] In a preferred embodiment, Figure 5 As shown, generating a process system model based on a process system node model includes the following steps:

[0118] Step S501: Determine the preset pressure value of each pressure node according to the pressure data in the system specification in the modeling data.

[0119] Specifically, in this step, the preset pressure values required for each pressure node are assigned according to the system specification. Since the pressure in the system specification is segmented and not specific to each pressure node, the preset pressure value assigned to each pressure node can be allocated based on the AI's reasoning ability and stored in the pressure node table.

[0120] Step S502: Calculate the admittance value of each pipeline according to the preset pressure value of each pressure node and the flow network calculation formula, and store the admittance value of each pipeline in the corresponding pipeline data in the node graph pipeline data table.

[0121] Specifically, in this step, the admittance value of each pipeline is calculated according to the preset pressure value of each pressure node according to the flow network calculation formula, and the calculated admittance value is saved in the corresponding pipeline data in the node graph pipeline data table generated in step S404.

[0122] Step S503: Calculate the admittance values of the valve and the filter based on the CV curve parameters of the valve and the pipeline diameter, and save the admittance values of the valve and the filter in the device data table.

[0123] Specifically, in this step, the admittance values of the valve and filter can be calculated based on the valve's CV curve parameters and the pipeline diameter. If this is not available in the system manual, the data for the pipeline in the node diagram can be used and the values can be saved in the corresponding valve admittance in the device data sheet.

[0124] Step S504: Import the data in the pressure node table into the process system node model and save it.

[0125] Specifically, in this step, the pressure node table generated in step S304 is automatically imported into the corresponding pressure node in the process system node model generated in step S400.

[0126] Step S505: Import the equipment data table and pipeline data table into the process T system node model and save it to obtain the process system model.

[0127] Specifically, in this step, the equipment data table generated in step S102 and the pipeline data table generated in step S103 are automatically imported into the corresponding equipment and pipeline parameters in the process system model. After the pressure node, equipment, and pipeline parameters are imported, these parameters are stored in the process system model, along with the initial operating conditions.

[0128] After the above is completed, a testable process system model is obtained.

[0129] Step S600: Dynamically test the process system model based on the modeling data until the process system model is successfully tested.

[0130] In some embodiments, such as Figure 6 As shown, the process system model is dynamically tested based on the modeling data until the modeling of the process system model is completed after verification, which includes the following steps:

[0131] Step S601: Determine the normal operating state of the process system model using the normal operating state data in the system specification in the modeling data.

[0132] Specifically, in this step, AI technologies, such as machine learning, can be used to explicitly translate the normal operating status in the system manual into the process system model generated in step S500. This means determining which equipment and pipelines in the process system model are operational, such as pumps or fans running, valves open, heat exchangers in operation, and water tanks in operation.

[0133] Step S602: Based on the normal operating status of the process system model, the process system model is run on the simulation platform and real-time operating parameters of the process system model are collected.

[0134] Specifically, the process system model may be run on a simulation platform to check various real-time operating parameters of the process system model during operation.

[0135] Step S603: Compare the real-time operating parameters with the corresponding parameters in the normal operating parameter table.

[0136] Specifically, in this step, each real-time operating parameter is compared one by one with the normal operating parameter table generated in step S101, and a deviation range is set.

[0137] Step S604: If the real-time operating parameters are within the deviation range, it is determined that the process system model test has passed.

[0138] Step S605: If the real-time operating parameters are not within the deviation range, the admittance parameter values of the valves or pipelines are adjusted until they are within the deviation range. If the parameters are outside the deviation range, AI can be used to check and adjust the admittance parameter values of the valves or pipelines based on its reasoning capabilities until they are within the deviation range. When all parameters are within the deviation range, the standard normal operating condition of the process system model is stored.

[0139] Step S606: Perform system testing on the process system model according to the testing program.

[0140] Specifically, in this step, the process system model is systematically tested according to the test program generated in step S104 under the stored standard normal operating conditions of the process system model.

[0141] Step S607: After the system test is completed, a test report of the process system model is generated.

[0142] Specifically, in this step, AI technology, such as generative AI, can be used to generate a test report for the process system model. The content of the test report must be consistent with the test program, and the results of the process system model must be entered into the test program.

[0143] The automatic thermal-hydraulic modeling method provided by the present invention facilitates standardized and accurate modeling, improves the quality of process system modeling, significantly shortens modeling time, and improves process system modeling efficiency. Furthermore, the present invention can shorten model testing time and significantly simplify the iterative steps for process model updates.

[0144] refer to Figure 7 The present invention also provides an automatic modeling system for thermal hydraulic models.

[0145] like Figure 7 As shown, the automatic modeling system of the thermal hydraulic model includes:

[0146] The modeling data extraction unit 701 is used to extract data from the system specification to obtain modeling data of the process system.

[0147] The modeling principle determination unit 702 is used to perform in-depth learning on the functions of each module of the process system to obtain the modeling principle of the process system.

[0148] The modeling design drawing generating unit 703 is used to generate a modeling design drawing of the process system according to the modeling principles and modeling data.

[0149] The node model generating unit 704 is used to generate a process system node model according to the modeling principle and the modeling design diagram.

[0150] The system model generating unit 705 is configured to generate a process system model based on the process system node model.

[0151] The system model testing unit 706 is used to perform dynamic testing on the process system model based on the modeling data until the modeling of the process system model is completed after verification.

[0152] Specifically, the specific coordination operation process between the units in the automatic modeling system of the thermal hydraulic model can refer to the above-mentioned automatic modeling method of the thermal hydraulic model, which will not be repeated here.

[0153] In addition, an electronic device of the present invention includes a memory and a processor; the memory is used to store a computer program; the processor is used to execute the computer program to implement a method for automatic modeling of a thermal hydraulic model as described in any one of the above. Specifically, according to an embodiment of the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present invention includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program contains program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed by an electronic device and, when executed, performs the above functions defined in the method of the embodiment of the present invention. The electronic device in the present invention can be a terminal such as a notebook, a desktop, a tablet computer, a smart phone, or a server.

[0154] In addition, the present invention provides a storage medium having a computer program stored thereon, which, when executed by a processor, implements any of the above-mentioned methods for automatically modeling a thermal hydraulic model. Specifically, it should be noted that the storage medium of the present invention can be a computer-readable signal medium or a computer-readable storage medium, or any combination of the two. The computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any combination of the above. More specific examples of computer-readable storage media can include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present invention, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, device, or device. In the present invention, a computer-readable signal medium can include a data signal transmitted in baseband or as part of a carrier wave, which carries computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transport a program for use by or in conjunction with an instruction execution system, apparatus, or device. Program code embodied on a computer-readable medium may be transmitted using any suitable medium, including but not limited to wires, optical cables, RF (radio frequency), or any suitable combination thereof.

[0155] The computer-readable medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device.

[0156] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. Reference can be made to the common and similar parts between the various embodiments. For the devices disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the description is relatively simple, and the relevant parts can be referred to the method description.

[0157] Professionals may further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the above description has generally described the components and steps of each example according to their functions. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present invention.

[0158] The steps of the methods or algorithms described in conjunction with the embodiments disclosed herein may be implemented directly using hardware, a software module executed by a processor, or a combination of the two. The software module may be placed in a random access memory (RAM), internal memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

[0159] The above embodiments are intended only to illustrate the technical concepts and features of the present invention. Their purpose is to enable those skilled in the art to understand the present invention and implement it accordingly. They are not intended to limit the scope of protection of the present invention. All equivalent variations and modifications within the scope of the claims of the present invention are intended to be covered by the claims of the present invention.

Claims

1. A method for automatically building a thermal hydraulic model, characterized in that: The following steps are involved: Extract data from the system manual to obtain modeling data for the process system; Conducting in-depth study on the functions of each module of the process system to obtain the modeling principles of the process system; generating a modeling design diagram of the process system according to the modeling principles and the modeling data; Generate a process system node model according to the modeling principles and the modeling design diagram; generating a process system model based on the process system node model; The process system model is dynamically tested based on the modeling data until the modeling of the process system model is completed after verification.

2. The automatic modeling method of thermal hydraulic model according to claim 1, characterized in that: The data extraction in the system specification to obtain the modeling data of the process system includes: Extracting normal operating parameters of the process system and generating a normal operating parameter table; Extracting target equipment data of the process system and generating an equipment data table; Extracting target pipeline data of the process system and generating a pipeline data table; Extract the specification content of the process system and generate a test program.

3. The automatic modeling method of thermal hydraulic model according to claim 2, characterized in that: Generating the modeling design diagram of the process system according to the modeling principle and the modeling data includes: Determine the equipment and pipelines to be simulated based on the modeling principles; Determining the location of a pressure node in the process system flow network; Marking the positions of the equipment to be simulated, the pipeline to be simulated, and the pressure nodes to generate a modeling design diagram of the process system; Name each pressure node in the modeling design diagram in sequence and generate a pressure node table.

4. The automatic modeling method of thermal hydraulic model according to claim 3, characterized in that: Generating a process system node model according to the modeling principle and the modeling design diagram includes: generating an initial node model of the process system according to the modeling design diagram; Naming the corresponding flow network nodes in the initial node model according to the node names in the pressure node table; Connecting the pressure nodes in the initial node model based on the modeling principle; Naming the pipelines in the initial node model according to the names of the upstream and downstream pipelines of the pressure nodes in the pressure node table, and generating a node graph pipeline data table; Adding the device to be simulated to the initial node model; Naming the devices in the initial node model according to the device data table; The node graph pipeline data table is modified according to the pipeline data table to obtain the process system node model.

5. The automatic modeling method of thermal hydraulic model according to claim 1, characterized in that: Generating a process system model based on the process system node model includes: Based on the process system node model, an initial system model is generated using a template-driven generation method; The initial system model is optimized using a reinforcement learning algorithm to obtain the process system model.

6. The automatic modeling method of thermal hydraulic model according to claim 4, characterized in that: Generating a process system model based on the process system node model includes: Determining a preset pressure value for each pressure node based on pressure data in the system specification in the modeling data; Calculate the admittance value of each pipeline according to the preset pressure value of each pressure node according to the flow network calculation formula, and store the admittance value of each pipeline in the corresponding pipeline data in the pipeline data table of the node graph; Calculating according to the CV curve parameters of the valve and the pipeline diameter to obtain the admittance values of the valve and the filter, and saving the admittance values of the valve and the filter in the device data table; Importing the data in the pressure node table into the process system node model and saving the data; The equipment data table and the pipeline data table are imported into the process T system node model and saved to obtain the process system model.

7. The automatic modeling method of thermal hydraulic model according to claim 2, characterized in that: The dynamically testing the process system model based on the modeling data until the modeling of the process system model is completed after verification includes: Determine the normal operating state of the process system model using the normal operating state data in the system specification in the modeling data; Based on the normal operating status of the process system model, running the process system model on a simulation platform and collecting real-time operating parameters of the process system model; Comparing the real-time operating parameters with corresponding parameters in the normal operating parameter table; If the real-time operating parameters are within the deviation range, it is determined that the process system model test has passed; If the real-time operating parameter is not within the deviation range, adjusting the admittance parameter value of the valve or pipeline until it is within the deviation range; Performing system testing on the process system model according to the test procedure; After the system test is completed, a test report of the process system model is generated.

8. A thermal hydraulic model automatic modeling system, characterized in that: include: A modeling data extraction unit is used to extract data from the system specification to obtain modeling data of the process system; a modeling principle determination unit, configured to perform in-depth learning on the functions of each module of the process system to obtain the modeling principle of the process system; a modeling design drawing generating unit, configured to generate a modeling design drawing of the process system according to the modeling principle and the modeling data; A node model generating unit, configured to generate a process system node model according to the modeling principle and the modeling design diagram; A system model generating unit, configured to generate a process system model based on the process system node model; The system model testing unit is used to perform dynamic testing on the process system model based on the modeling data until the modeling of the process system model is completed after verification.

9. A storage medium, characterized in that: The storage medium stores a computer program, which is suitable for being loaded by a processor to execute the steps of the automatic modeling method of a thermal-hydraulic model according to any one of claims 1 to 7.

10. An electronic device, characterized in that: The method comprises a memory and a processor, wherein a computer program is stored in the memory, and the processor executes the steps of the automatic modeling method of the thermal-hydraulic model according to any one of claims 1 to 7 by calling the computer program stored in the memory.

Images