Simulation test model training method and device
By training a deep learning model that integrates historical testing procedures and system characteristic information in nuclear power plant simulation testing, the problems of low efficiency and high labor costs in existing technologies have been solved, and efficient and accurate simulation testing has been achieved.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- STATE POWER INVESTMENT CORPORATION RESEARCH INSTITUTE
- Filing Date
- 2024-10-31
- Publication Date
- 2026-05-01
AI Technical Summary
In existing technologies, nuclear power plant simulation testing relies on manually written test procedures and scripts, which leads to problems such as low efficiency, long testing cycles, high labor costs, and complex software configuration management.
By acquiring feature information from historical testing procedures and nuclear power plant simulation systems, feature fusion is performed and then input into the simulation test model. The simulation test model is trained using a deep learning model, loss values are generated and trained, thereby improving the model's predictive ability.
It improves the efficiency, accuracy, and adaptability of nuclear power plant simulation testing, reduces the workload of manual testing, and enhances the level of intelligence in testing.
Smart Images
Figure CN121960093A_ABST
Abstract
Description
Technical Field
[0001] This disclosure relates to the field of nuclear power simulation technology, and in particular to a training method and apparatus for a simulation test model. Background Technology
[0002] Currently, nuclear power plants primarily utilize simulators for simulation testing, relying on traditional methods of manually writing test procedures and scripts. These test procedures are typically based on expert knowledge and experience, covering common operating scenarios and failure modes. During testing, these scripts are manually executed, placing the simulator under preset conditions to verify its performance and reliability. In nuclear power plant simulator testing, there are over 200 test procedures, covering a wide range of operation types, resulting in a massive workload for operators, requiring approximately three months to complete one round of testing. Simultaneously, simulator development engineers need to conduct extensive debunking work before releasing new simulator versions for operator regression testing. The correctness of simulator software configuration is also a factor affecting the smooth progress of the testing phase. The overall simulator testing iteration cycle is approximately one year. Therefore, how to solve the problems of low efficiency, long testing cycles, high labor costs, and complex software configuration management caused by the current manual writing of test cases and scripts is an urgent issue to be addressed in this field. Summary of the Invention
[0003] This disclosure aims to at least partially address one of the technical problems in the related art.
[0004] Therefore, the first aspect of this disclosure proposes a training method for a simulation test model, which is used for simulation testing of a nuclear power plant simulation system; the training method includes the following steps:
[0005] Obtain historical test procedures; the historical test procedures include historical test operation sequence information and historical test result information;
[0006] Obtain the characteristic information of the nuclear power plant simulation system;
[0007] The historical test operation sequence information and historical feature information are fused to obtain historical fused feature information;
[0008] The historical fusion feature information is input into the simulation test model to obtain the first test result information;
[0009] Based on the historical test results and the first test results, a loss value for the simulation test model is generated, and the simulation test model is trained based on the loss value.
[0010] In some embodiments of this disclosure, the historical feature information includes at least one of the following: equipment information of the nuclear power plant simulation system, connection information between equipment, and operation information.
[0011] The second aspect of this disclosure provides a simulation testing method for a nuclear power plant simulation system, characterized by comprising the following steps:
[0012] When performing simulation tests on the nuclear power plant simulation system using the test procedure, the test operation sequence information in the test procedure is obtained;
[0013] Obtain the characteristic information of the nuclear power plant simulation system;
[0014] The test operation sequence information and the feature information are fused to obtain fused feature information;
[0015] The fused feature information is input into a pre-trained simulation test model to obtain the second test result information output by the simulation test model; wherein the simulation test model is trained using the method described in any one of claims 1-2.
[0016] In some embodiments of this disclosure, the simulation testing method for a nuclear power plant simulation system further includes: acquiring expected test result information in the test procedure; and determining whether an anomaly has occurred in the nuclear power plant simulation system based on the second test result information and the expected test result information.
[0017] In some embodiments of this disclosure, the simulation testing method for a nuclear power plant simulation system further includes: determining that an anomaly has occurred in the nuclear power plant simulation system, and generating an anomaly report based on the second test result information and the expected test result information.
[0018] In some embodiments of this disclosure, the simulation testing method for a nuclear power plant simulation system further includes: inputting the test operation sequence information into a pre-built simulator to obtain third test result information; wherein the simulator is used for simulation testing of the nuclear power plant simulation system; and comparing and verifying the second test result information using the third test result information.
[0019] A third aspect of this disclosure provides a training device for a simulation test model used for simulation testing of a nuclear power plant simulation system; the training device includes the following steps:
[0020] The first acquisition module is used to acquire historical test procedures; the historical test procedures include historical test operation sequence information and historical test result information.
[0021] The second acquisition module is used to acquire the feature information of the nuclear power plant simulation system;
[0022] The feature fusion module is used to fuse the historical test operation sequence information and historical feature information to obtain historical fused feature information;
[0023] The third acquisition module is used to input the historical fusion feature information into the simulation test model to obtain the first test result information;
[0024] The training module is used to generate a loss value for the simulation test model based on the historical test result information and the first test result information, and to train the simulation test model based on the loss value.
[0025] A fourth aspect of this disclosure provides a simulation testing apparatus for a nuclear power plant simulation system, comprising the following steps:
[0026] The first acquisition module is used to acquire test operation sequence information in the test procedure when the nuclear power plant simulation system is simulated using the test procedure;
[0027] The second acquisition module is used to acquire the feature information of the nuclear power plant simulation system;
[0028] The feature fusion module is used to fuse the test operation sequence information and the feature information to obtain fused feature information;
[0029] The third acquisition module is used to input the fused feature information into a pre-trained simulation test model to acquire the second test result information output by the simulation test model; wherein the simulation test model is trained using the method described in the first aspect above.
[0030] A fifth aspect of this disclosure provides an electronic device, including: a processor, and a memory communicatively connected to the processor;
[0031] The memory stores computer-executed instructions;
[0032] The processor executes computer execution instructions stored in the memory to implement the method described in the first aspect above, or to implement the method described in the second aspect above.
[0033] A sixth aspect of this disclosure provides a computer-readable storage medium, characterized in that the computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the method described in the first aspect above, or to implement the method described in the second aspect above.
[0034] The training method for the simulation test model provided in this disclosure fuses historical test operation sequence information and historical feature information to train the simulation test model. This enables the simulation test model to learn the ability to predict the test results corresponding to the test operation sequence information based on the feature information of the nuclear power plant simulation system, thereby adapting to different states of the nuclear power plant simulation system and accurately predicting the test results. This disclosure improves the efficiency, accuracy, and adaptability of simulation testing of nuclear power plant simulation systems, enhances the intelligence level of testing, and reduces the workload of manual testing.
[0035] Additional aspects and advantages of this disclosure will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this disclosure. Attached Figure Description
[0036] The above and / or additional aspects and advantages of this disclosure will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, in which:
[0037] Figure 1 This is a flowchart illustrating a training method for a simulation test model provided in an embodiment of this disclosure.
[0038] Figure 2 A schematic flowchart illustrating a simulation testing method for a nuclear power plant simulation system provided in this embodiment of the present disclosure;
[0039] Figure 3 A schematic diagram of a training device for a simulation test model provided in an embodiment of this disclosure;
[0040] Figure 4 This is a schematic diagram of a simulation test device for a nuclear power plant simulation system provided in an embodiment of this disclosure. Detailed Implementation
[0041] Embodiments of this disclosure are described in detail below, examples of which are illustrated in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this disclosure, and should not be construed as limiting this disclosure.
[0042] Specifically, the training method and apparatus for the simulation test model of the present disclosure are described below with reference to the accompanying drawings.
[0043] Figure 1 This is a flowchart illustrating a training method for a simulation test model provided in an embodiment of this disclosure. The simulation test model is used for simulation testing of a nuclear power plant simulation system, and it employs a deep learning model framework.
[0044] like Figure 1 As shown, the training method for this simulation test model may include the following steps:
[0045] Step 101: Obtain historical test procedures. Historical test procedures include historical test operation sequence information and historical test result information.
[0046] The historical test operation sequence information is obtained by transforming historical test operation steps, while the historical test result information is the expected equipment response of each device in the nuclear power plant simulation system after performing historical test operation steps. This response is in numerical form, such as pressurizer level and steam generator level data. It should be noted that both the historical test operation sequence information and the historical test result information are vector or time series data obtained through certain data transformations, and further normalization processing may be performed if necessary. Data transformation may include the following steps: data cleaning, feature extraction, feature encoding, and feature matrix construction.
[0047] Step 102: Obtain the feature information of the nuclear power plant simulation system.
[0048] The characteristic information of a nuclear power plant simulation system can be extracted from its requirements or design documents (such as system design drawings, equipment manuals, and interface specifications). This characteristic information can include at least one of the following: equipment information, connection information between equipment, and operational information. Equipment information can include the names and attributes of the equipment in the simulation system (such as valve opening range, characteristic curves, and switching stroke times). Connection information between equipment can include physical connections, such as piping connections between devices, and logical connections, such as data interface I / O information. Operational information represents the operational information for artificially simulated faults in the nuclear power plant simulation system. Faults can include system faults, equipment faults, and local equipment faults. During testing of the nuclear power plant simulation system, the introduction of operational information can be used to test whether the response of the simulation system and equipment meets design expectations.
[0049] The characteristic information of a nuclear power plant simulation system can reflect the different states of the system, as well as the attributes and parameters of the equipment within the system and the relationships between the equipment.
[0050] Step 103: Perform feature fusion on the historical test operation sequence information and historical feature information to obtain historical fused feature information.
[0051] Optionally, in some embodiments of this disclosure, historical test operation sequence information and historical feature information can be fused using feature fusion methods such as weighted averaging, feature connection, and linear transformation to generate a feature matrix and obtain historical fused feature information.
[0052] Step 104: Input the historical fusion feature information into the simulation test model to obtain the first test result information.
[0053] The simulation test model can optionally use a recurrent neural network to adapt to the processing requirements of sequence data. The neural network structure is designed, including input layers, hidden layers, and output layers, as well as the connection methods between layers, activation functions, and loss functions. The learning rate, batch size, and number of iterations are determined. Based on historical feature information from the nuclear power plant simulation system, the simulation test model predicts the test results corresponding to historical test operation sequences.
[0054] Step 105: Based on the historical test results and the first test results, generate the loss value of the simulation test model, and train the simulation test model based on the loss value.
[0055] Optionally, cross-entropy loss function, mean squared error loss function, etc., can be used to determine the loss value, and then the simulation test model can be trained. This allows the simulation test model to learn the mapping relationship between the feature information of the nuclear power plant simulation system, the test operation sequence information, and the test results. It gains the ability to predict the test results corresponding to the test operation sequence information based on the feature information of the nuclear power plant simulation system. By replacing expert knowledge and experience through the learning of the simulation test model, the workload of operators in the simulation test tasks of the nuclear power plant simulation system is reduced, while ensuring the accuracy of the predicted test results.
[0056] By implementing the embodiments of this disclosure, historical test operation sequence information and historical feature information are fused together and then used to train the simulation test model. This enables the simulation test model to learn the ability to predict the test results corresponding to the test operation sequence information based on the feature information of the nuclear power plant simulation system, thereby adapting to different states of the nuclear power plant simulation system and accurately predicting the test results. This disclosure improves the efficiency, accuracy, and adaptability of simulation testing of nuclear power plant simulation systems, enhances the level of intelligence in testing, and reduces the workload of manual testing.
[0057] Figure 2 This is a schematic flowchart illustrating a simulation testing method for a nuclear power plant simulation system provided in an embodiment of this disclosure. Figure 2 As shown, the simulation testing method of this nuclear power plant simulation system may include the following steps:
[0058] Step 201: When performing simulation testing on the nuclear power plant simulation system using the test procedure, obtain the test operation sequence information in the test procedure.
[0059] Among them, the test operation sequence information is obtained by data transformation of the test operation steps.
[0060] Step 202: Obtain the feature information of the nuclear power plant simulation system.
[0061] The characteristic information of the nuclear power plant simulation system is described in step 102 and will not be repeated here.
[0062] Step 203: Perform feature fusion on the test operation sequence information and feature information to obtain fused feature information.
[0063] Step 204: Input the fused feature information into the pre-trained simulation test model to obtain the second test result information output by the simulation test model.
[0064] Among them, the simulation test model adopts Figure 1 The method shown in the embodiment trains a simulation test model that has learned to predict test results corresponding to test operation sequence information based on feature information from a nuclear power plant simulation system. The simulation test model predicts test results based on the test operation sequence information and feature information, outputting second test result information. The second test result information includes the correspondence between the equipment in the nuclear power plant simulation system and the equipment corresponding to the test operation sequence information when the aforementioned feature information is present. Based on the second test result information, it can be determined whether the test procedure has passed.
[0065] In some embodiments of this disclosure, appropriate evaluation metrics, such as system prediction accuracy and recall, can be selected to evaluate the accuracy of the model results. In one implementation, expected test result information corresponding to the test operation sequence information in the test procedure can be obtained. This expected test result information represents the equipment response when the test operation sequence information meets the design requirements. The expected test result information can be a specific value or a range of values. An anomaly is determined based on the second test result information and the expected test result information. If the difference between the second test result information and the expected test result information is greater than a preset threshold, or if the second test result information exceeds the range of the expected test result information, it can be determined that an anomaly has occurred in the nuclear power plant simulation system when the test procedure is used to perform simulation testing. An anomaly report can be generated based on the second test result information and the expected test result information, and the anomaly report can be sent to the terminal to provide feedback to the operator, locate, and resolve the problem.
[0066] Optionally, in some embodiments of this disclosure, the test results output by the simulation test model can be compared and verified with the test results output by the simulator to improve the accuracy of the simulation test. As an example, test operation sequence information can be input into a pre-built simulator to obtain third test result information. The simulator is used for simulation testing of a nuclear power plant simulation system. The third test result information is used to compare and verify the second test result information. If the difference between the second and third test result information is greater than a preset threshold, both the second and third test result information can be labeled as having questionable credibility. This helps to comprehensively evaluate the performance of the simulation test model and the simulator, providing guidance for subsequent model optimization of the simulation test model and the simulator.
[0067] In some embodiments of this disclosure, an AR display device can be used to display the operation screen of a nuclear power plant simulation system in real time, allowing testers to intuitively see the system's operating status and changes. Through the interactive functions of the AR device, testers can operate in the virtual environment, such as clicking and dragging, to control the system under test. The second test result information output by the simulation test model is displayed on the AR display device in a visual form, such as through charts and animations, showing the trend of test result changes and key indicators. The spatial positioning capabilities of the AR device can also be used to quickly locate errors in the test and provide repair suggestions or guide testers to perform repairs. A virtual assistant function can be developed to provide real-time help and guidance to testers through the AR display device, such as test step prompts and answers to frequently asked questions.
[0068] By implementing the embodiments of this disclosure, a trained simulation testing model is used to accurately predict test results for test operation sequence information in the test procedure. This simulation testing model has learned to predict test results corresponding to test operation sequence information based on the characteristic information of the nuclear power plant simulation system. It can adapt to different states of the nuclear power plant simulation system and accurately predict test results. This disclosure improves the efficiency, accuracy, and adaptability of simulation testing in nuclear power plant simulation systems, enhances the intelligence level of testing, and thus reduces the workload of manual testing.
[0069] Figure 3 This is a schematic diagram of a training device for a simulation test model provided in an embodiment of this disclosure. The simulation test model is used for simulation testing of a nuclear power plant simulation system. Figure 3 As shown, the training device for the simulation test model may include: a first acquisition module 301, a second acquisition module 302, a feature fusion module 303, a third acquisition module 304, and a training module 305.
[0070] The first acquisition module 301 is used to acquire historical test procedures; the historical test procedures include historical test operation sequence information and historical test result information.
[0071] The second acquisition module 302 is used to acquire feature information of the nuclear power plant simulation system.
[0072] In some embodiments of this disclosure, historical feature information includes at least one of the following: equipment information of the nuclear power plant simulation system, connection information between equipment, and operation information.
[0073] The feature fusion module 303 is used to fuse historical test operation sequence information and historical feature information to obtain historical fused feature information.
[0074] The third acquisition module 304 is used to input historical fusion feature information into the simulation test model to obtain the first test result information.
[0075] The training module 305 is used to generate the loss value of the simulation test model based on the historical test result information and the first test result information, and to train the simulation test model based on the loss value.
[0076] Regarding the apparatus in the above embodiments, the specific manner in which each module performs its operation has been described in detail in the embodiments related to the method, and will not be elaborated upon here.
[0077] Figure 4 This is a schematic diagram of a simulation test apparatus for a nuclear power plant simulation system provided in an embodiment of this disclosure. Figure 4 As shown, the simulation test device of the nuclear power plant simulation system may include: a first acquisition module 401, a second acquisition module 402, a feature fusion module 403, and a third acquisition module 404.
[0078] The first acquisition module 401 is used to acquire the test operation sequence information in the test procedure when performing simulation testing on the nuclear power plant simulation system using the test procedure.
[0079] The second acquisition module 402 is used to acquire feature information of the nuclear power plant simulation system.
[0080] The feature fusion module 403 is used to fuse test operation sequence information and feature information to obtain fused feature information.
[0081] The third acquisition module 404 is used to input the fused feature information into the pre-trained simulation test model and acquire the second test result information output by the simulation test model.
[0082] Among them, the simulation test model adopts Figure 1 The method in the illustrated embodiment is used for training.
[0083] In some embodiments of this disclosure, in such Figure 4 Based on the illustrated embodiment, the simulation testing device for the nuclear power plant simulation system may further include an anomaly detection module. This anomaly detection module is used to: acquire expected test result information from the test procedure; and determine whether an anomaly has occurred in the nuclear power plant simulation system based on the second test result information and the expected test result information.
[0084] In some embodiments of this disclosure, the anomaly detection module is further configured to: determine that an anomaly has occurred in the nuclear power plant simulation system, and generate an anomaly report based on the second test result information and the expected test result information.
[0085] In some embodiments of this disclosure, in such Figure 4 Based on the illustrated embodiment, the simulation testing device for the nuclear power plant simulation system may further include a verification module. This verification module is used to: input test operation sequence information into a pre-built simulator to obtain third test result information; wherein the simulator is used for simulation testing of the nuclear power plant simulation system; and compare and verify the second test result information using the third test result information.
[0086] Regarding the apparatus in the above embodiments, the specific manner in which each module performs its operation has been described in detail in the embodiments related to the method, and will not be elaborated upon here.
[0087] To implement the above embodiments, this disclosure also proposes an electronic device, including: a processor and a memory communicatively connected to the processor; the memory stores computer execution instructions; the processor executes the computer execution instructions stored in the memory to execute the training method of the simulation test model provided in the foregoing embodiments, or to execute the simulation test method of the nuclear power plant simulation system provided in the foregoing embodiments.
[0088] To implement the above embodiments, this disclosure also proposes a computer-readable storage medium storing computer-executable instructions. When executed by a processor, the computer-executable instructions are used to implement the training method of the simulation test model provided in the foregoing embodiments, or to implement the simulation test method of the nuclear power plant simulation system provided in the foregoing embodiments.
[0089] To implement the above embodiments, this disclosure also proposes a computer program product, including a computer program that, when executed by a processor, implements the methods provided in the foregoing embodiments.
[0090] In the foregoing descriptions of the embodiments, the terms "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., refer to specific features, structures, materials, or characteristics described in connection with that embodiment or example, which are included in at least one embodiment or example of this disclosure. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.
[0091] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this disclosure, "a plurality of" means at least two, such as two, three, etc., unless otherwise explicitly specified.
[0092] Any process or method description in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more executable instructions for implementing custom logic functions or processes, and the scope of preferred embodiments of this disclosure includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as will be understood by those skilled in the art to which embodiments of this disclosure pertain.
[0093] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Alternatively, the computer-readable medium may be paper or other suitable media on which the program can be printed, since the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in a computer memory.
[0094] It should be understood that various parts of this disclosure can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.
[0095] Those skilled in the art will understand that all or part of the steps of the methods in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.
[0096] Furthermore, the functional units in the various embodiments of this disclosure can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.
[0097] The storage medium mentioned above can be a read-only memory, a disk, or an optical disk, etc. Although embodiments of the present disclosure have been shown and described above, it is to be understood that the above embodiments are exemplary and should not be construed as limiting the present disclosure. Those skilled in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present disclosure.
Claims
1. A training method for a simulation test model, characterized in that, The simulation test model is used for simulation testing of a nuclear power plant simulation system; the training method includes the following steps: Obtain historical test procedures; the historical test procedures include historical test operation sequence information and historical test result information; Obtain the characteristic information of the nuclear power plant simulation system; The historical test operation sequence information and historical feature information are fused to obtain historical fused feature information; The historical fusion feature information is input into the simulation test model to obtain the first test result information; Based on the historical test results and the first test results, a loss value for the simulation test model is generated, and the simulation test model is trained based on the loss value.
2. The method according to claim 1, characterized in that, The historical feature information includes at least one of the following: equipment information, connection information between equipment, and operation information of the nuclear power plant simulation system.
3. A simulation testing method for a nuclear power plant simulation system, characterized in that, Includes the following steps: When performing simulation tests on the nuclear power plant simulation system using the test procedure, the test operation sequence information in the test procedure is obtained; Obtain the characteristic information of the nuclear power plant simulation system; The test operation sequence information and the feature information are fused to obtain fused feature information; The fused feature information is input into a pre-trained simulation test model to obtain the second test result information output by the simulation test model; wherein the simulation test model is trained using the method described in any one of claims 1-2.
4. The method according to claim 3, characterized in that, Also includes: Obtain the expected test result information from the test procedure; Based on the second test result information and the expected test result information, determine whether the nuclear power plant simulation system has experienced an anomaly.
5. The method according to claim 4, characterized in that, Also includes: An anomaly is determined in the nuclear power plant simulation system, and an anomaly report is generated based on the second test result information and the expected test result information.
6. The method according to claim 3, characterized in that, Also includes: The test operation sequence information is input into a pre-built simulator to obtain third test result information; wherein, the simulator is used for simulation testing of a nuclear power plant simulation system; The second test result information is compared and verified using the third test result information.
7. A training device for a simulation test model, characterized in that, The simulation test model is used for simulation testing of a nuclear power plant simulation system; the training device includes the following steps: The first acquisition module is used to acquire historical test procedures; the historical test procedures include historical test operation sequence information and historical test result information. The second acquisition module is used to acquire the feature information of the nuclear power plant simulation system; The feature fusion module is used to fuse the historical test operation sequence information and historical feature information to obtain historical fused feature information; The third acquisition module is used to input the historical fusion feature information into the simulation test model to obtain the first test result information; The training module is used to generate a loss value for the simulation test model based on the historical test result information and the first test result information, and to train the simulation test model based on the loss value.
8. A simulation testing device for a nuclear power plant simulation system, characterized in that, Includes the following steps: The first acquisition module is used to acquire test operation sequence information in the test procedure when the nuclear power plant simulation system is simulated using the test procedure; The second acquisition module is used to acquire the feature information of the nuclear power plant simulation system; The feature fusion module is used to fuse the test operation sequence information and the feature information to obtain fused feature information; The third acquisition module is used to input the fused feature information into a pre-trained simulation test model to acquire the second test result information output by the simulation test model; wherein the simulation test model is trained using the method described in any one of claims 1-2.
9. An electronic device, characterized in that, include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory to implement the method as described in any one of claims 1-2, or to implement the method as described in any one of claims 3-6.
10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the method as described in any one of claims 1-2, or to implement the method as described in any one of claims 3-6.