Importance degree analysis method and device based on characteristic parameters of large break water loss accident

Abstract

The invention relates to an importance degree analysis method and device based on characteristic parameters of a large break water loss accident. The method comprises the following steps: constructing a reactor type steady-state simulation model of a target nuclear power station and a transient model of the large break water loss accident; determining characteristic parameters according to the accident acceptance criterion, the accident response program table, the accident sequence and the nuclear power station system response; generating a plurality of groups of random samples based on the parameter range of the model, and constructing an accident feature database covering the accident under various working conditions by using the plurality of groups of random samples as input conditions and combining the feature parameters; according to the model simulation data, in combination with the characteristic parameter data under various working conditions, constructing a target agent model of the accident among the characteristic parameters under different working conditions; and based on response analysis of the target agent model, analyzing the importance degree of the feature parameters in the target agent model, and sorting according to the influence degree of the feature parameters on the accident response. The method can better guarantee the safe operation of the nuclear power station.

Description

Technical Field

[0001] The present invention relates to the technical field of nuclear power plants, and in particular to an importance analysis method and device based on characteristic parameters of a large break loss of coolant accident. Background Art

[0002] In the nuclear energy industry, the safety analysis of nuclear power plants has always occupied a core position due to its criticality. Especially in the face of extreme situations such as large break loss of coolant accidents, the accurate evaluation and optimization of the performance of nuclear power plant safety systems becomes particularly critical. Traditionally, the safety analysis of nuclear power plants mainly relies on two major technical routes: determinism and probability theory. These two methods together constitute the basic guarantee framework for the safe operation of nuclear power plants and have long played an important role in preventing and mitigating accident risks.

[0003] However, although these methods have achieved remarkable results, they still have certain limitations when quantitatively analyzing the specific impact of different parameters on accident consequences. Summary of the invention

[0004] The present invention aims to solve one of the technical problems in the related art at least to a certain extent.

[0005] To this end, the first object of the present invention is to propose an importance analysis method based on characteristic parameters of large break loss of coolant accidents, which can improve the accuracy, reliability and adaptability of nuclear power plant safety analysis, thereby better ensuring the safe operation of nuclear power plants.

[0006] The second object of the present invention is to provide an importance analysis device based on characteristic parameters of a large break loss of coolant accident.

[0007] A third objective of the present invention is to provide an electronic device.

[0008] A fourth object of the present invention is to provide a computer-readable storage medium.

[0009] A fifth object of the present invention is to provide a computer program product.

[0010] To achieve the above-mentioned purpose, the first embodiment of the present invention proposes an importance analysis method based on characteristic parameters of a large break loss of coolant accident, including: constructing a reactor type steady-state simulation model of a target nuclear power plant and a transient model of a large break loss of coolant accident; determining characteristic parameters according to the accident acceptance criteria, accident response procedure table, accident sequence and nuclear power plant system response of the large break loss of coolant accident; generating multiple groups of random samples based on the parameter ranges of the reactor type steady-state simulation model and the transient model, and using the multiple groups of random samples as input conditions, combined with the characteristic parameters, constructing an accident characteristic database covering the large break loss of coolant accident under various working conditions; constructing a target proxy model between the characteristic parameters of the large break loss of coolant accident under different working conditions according to the simulation data of the reactor type steady-state simulation model and the transient model, combined with the characteristic parameter data under various working conditions stored in the accident characteristic database; based on the response analysis of the target proxy model, analyzing the importance of the characteristic parameters in the target proxy model, and ranking them according to their influence on the accident response.

[0011] According to an embodiment of the present invention, the importance analysis method based on the characteristic parameters of the large break loss of coolant accident includes: constructing a reactor type steady-state simulation model of the target nuclear power plant and a transient model of the large break loss of coolant accident; determining the characteristic parameters according to the accident acceptance criteria, accident response procedure table, accident sequence and nuclear power plant system response of the large break loss of coolant accident; generating multiple groups of random samples based on the parameter range of the reactor type steady-state simulation model and the transient model, and using the multiple groups of random samples as input conditions, combined with the characteristic parameters, constructing an accident characteristic database covering the large break loss of coolant accident under various working conditions; constructing a target proxy model between the characteristic parameters of the large break loss of coolant accident under different working conditions based on the simulation data of the reactor type steady-state simulation model and the transient model, combined with the characteristic parameter data under various working conditions stored in the accident characteristic database; based on the response analysis of the target proxy model, analyzing the importance of the characteristic parameters in the target proxy model, and ranking them according to their influence on the accident response. This method can improve the accuracy, reliability and adaptability of nuclear power plant safety analysis, thereby better ensuring the safe operation of nuclear power plants.

[0012] In addition, the importance analysis method based on characteristic parameters of a large break loss of coolant accident proposed in the first aspect of the present invention may also have the following additional technical features:

[0013] In one embodiment of the present invention, the characteristic parameters include characteristic input parameters and characteristic output parameters, and the characteristic parameters are determined according to the accident acceptance criteria, accident response procedure table, accident sequence and nuclear power plant system response of the large break loss of coolant accident, including:

[0014] According to the accident acceptance criteria, the characteristic output parameters are determined; wherein the characteristic output parameters include the peak temperature of the fuel cladding, the core collapse liquid level, and the pressure of the main steam pipeline;

[0015] The characteristic input parameters are determined according to the accident response procedure table, the accident sequence and the nuclear power plant system response; wherein the characteristic input parameters include breach size, blowdown coefficient, pipeline along-the-line resistance coefficient, initial reactor power and system pressure.

[0016] In one embodiment of the present invention, based on the parameter range of the reactor steady-state simulation model and the transient model, multiple groups of random samples are generated, and the multiple groups of random samples are used as input conditions, combined with the characteristic parameters, to construct an accident feature database covering the large break loss of coolant accident under various working conditions, including:

[0017] Determining a distribution interval of characteristic input parameters based on parameter ranges of the reactor type steady-state simulation model and the transient model;

[0018] Using the large break loss of coolant accident analysis procedure and combining with the Latin hypercube sampling method, data sampling is performed on the determined characteristic input parameters within their respective distribution intervals to generate multiple groups of random samples for simulation;

[0019] Using a simulation program that simulates the behavior of a nuclear power plant under the large break loss of coolant accident condition, simulation calculations are performed on each group of random samples to obtain characteristic output parameters under corresponding working conditions for each group of random samples;

[0020] The accident feature database is constructed according to the corresponding relationship between the feature input parameters and the feature output parameters.

[0021] In one embodiment of the present invention, the response analysis based on the target proxy model analyzes the importance of characteristic parameters in the target proxy model and sorts them according to their influence on the accident response, including:

[0022] The Sobol sensitivity analysis method based on variance decomposition and the correlation analysis method based on the accident database are adopted, and the target proxy model is used as an iterative tool to analyze the importance of the characteristic input parameters;

[0023] Calculate the impact of each characteristic input parameter on the accident response output, and evaluate the importance of each characteristic input parameter through quantitative analysis;

[0024] According to the result of the quantitative evaluation, the feature input parameters are sorted to generate an importance sequence of the feature input parameters.

[0025] To achieve the above-mentioned purpose, the second embodiment of the present invention proposes an importance analysis device based on characteristic parameters of a large break loss of coolant accident, comprising: a first construction module, used to construct a reactor type steady-state simulation model of a target nuclear power plant and a transient model of a large break loss of coolant accident; a determination module, used to determine the characteristic parameters according to the accident acceptance criteria, accident response procedure table, accident sequence and nuclear power plant system response of the large break loss of coolant accident; a second construction module, used to generate multiple groups of random samples based on the parameter range of the reactor type steady-state simulation model and the transient model, and use the multiple groups of random samples as input conditions, combined with the characteristic parameters, to construct an accident feature database covering the large break loss of coolant accident under various working conditions; a third construction module, used to construct a target proxy model between the characteristic parameters of the large break loss of coolant accident under different working conditions according to the simulation data of the reactor type steady-state simulation model and the transient model, combined with the characteristic parameter data under various working conditions stored in the accident feature database; an analysis module, used to analyze the importance of the characteristic parameters in the target proxy model based on the response analysis of the target proxy model, and rank them according to their influence on the accident response.

[0026] According to the importance analysis device based on the characteristic parameters of the large break loss of coolant accident of the embodiment of the present invention, the reactor type steady-state simulation model of the target nuclear power plant and the transient model of the large break loss of coolant accident are constructed by the first construction module, the characteristic parameters are determined according to the accident acceptance criteria, accident response procedure table, accident sequence and nuclear power plant system response of the large break loss of coolant accident by the determination module, multiple groups of random samples are generated based on the parameter range of the reactor type steady-state simulation model and the transient model by the second construction module, and the multiple groups of random samples are used as input conditions, combined with the characteristic parameters, to construct an accident characteristic database covering the large break loss of coolant accident under various working conditions, and the target proxy model between the characteristic parameters of the large break loss of coolant accident under different working conditions is constructed by the third construction module according to the simulation data of the reactor type steady-state simulation model and the transient model, combined with the characteristic parameter data under various working conditions stored in the accident characteristic database, and the importance of the characteristic parameters in the target proxy model is analyzed by the analysis module based on the response analysis of the target proxy model, and the parameters are ranked according to their influence on the accident response. Therefore, the device can improve the accuracy, reliability and adaptability of the safety analysis of the nuclear power plant, so as to better ensure the safe operation of the nuclear power plant.

[0027] In addition, the importance analysis device based on characteristic parameters of a large break loss of coolant accident proposed in the second aspect of the present invention may also have the following additional technical features:

[0028] In one embodiment of the present invention, the characteristic parameters include characteristic input parameters and characteristic output parameters, and the determination module is used to determine the characteristic parameters according to the accident acceptance criteria, accident response procedure table, accident sequence and nuclear power plant system response of the large break loss of coolant accident, including:

[0029] Determining the characteristic output parameters according to the accident acceptance criteria; wherein the characteristic output parameters include the peak temperature of the fuel cladding, the core collapse liquid level, and the pressure of the steam pipeline;

[0030] The characteristic input parameters are determined according to the accident response procedure table, the accident sequence and the nuclear power plant system response; wherein the characteristic input parameters include breach size, blowdown coefficient, pipeline along-the-line resistance coefficient, initial reactor power and system pressure.

[0031] In one embodiment of the present invention, the second construction module is used to generate multiple groups of random samples based on the parameter range of the reactor type steady-state simulation model and the transient model, and use the multiple groups of random samples as input conditions and combine the characteristic parameters to construct an accident feature database covering the large break loss of coolant accident under various working conditions, including:

[0032] Determining a distribution interval of characteristic input parameters based on parameter ranges of the reactor type steady-state simulation model and the transient model;

[0033] Using the large break loss of coolant accident analysis procedure and combining with the Latin hypercube sampling method, data sampling is performed on the determined characteristic input parameters within their respective distribution intervals to generate multiple groups of random samples for simulation;

[0034] Using a simulation program that simulates the behavior of a nuclear power plant under the large break loss of coolant accident condition, simulation calculations are performed on each group of random samples to obtain characteristic output parameters under corresponding working conditions for each group of random samples;

[0035] The accident feature database is constructed according to the corresponding relationship between the feature input parameters and the feature output parameters.

[0036] In one embodiment of the present invention, the analysis module is used to analyze the importance of characteristic parameters in the target proxy model based on the response analysis of the target proxy model, and rank them according to their influence on the accident response, including:

[0037] The Sobol sensitivity analysis method based on variance decomposition and the correlation analysis method based on the accident database are adopted, and the target proxy model is used as an iterative tool to analyze the importance of the characteristic input parameters;

[0038] Calculate the impact of each characteristic input parameter on the accident response output, and evaluate the importance of each characteristic input parameter through quantitative analysis;

[0039] According to the result of the quantitative evaluation, the feature input parameters are sorted to generate an importance sequence of the feature input parameters.

[0040] To achieve the above object, the third aspect of the present invention further provides an electronic device, including:

[0041] at least one processor; and,

[0042] a memory communicatively connected to the at least one processor; wherein,

[0043] The memory stores instructions that can be executed by the at least one processor. The instructions are executed by the at least one processor so that the at least one processor can perform the above method.

[0044] The electronic device of the embodiment of the present invention can improve the accuracy, reliability and adaptability of nuclear power plant safety analysis by executing the above method, thereby better ensuring the safe operation of the nuclear power plant.

[0045] To achieve the above objectives, the fourth aspect of the present invention further proposes a computer-readable storage medium, wherein the computer instructions are used to enable the computer to execute the above method.

[0046] The computer-readable storage medium of the embodiment of the present invention can improve the accuracy, reliability and adaptability of nuclear power plant safety analysis by executing the above method, thereby better ensuring the safe operation of the nuclear power plant.

[0047] To achieve the above-mentioned purpose, a fifth aspect of the present invention further provides a computer program product, which executes the above-mentioned method when an instruction processor in the computer program product executes it.

[0048] The computer program product of the embodiment of the present invention can improve the accuracy, reliability and adaptability of nuclear power plant safety analysis by executing the above method, thereby better ensuring the safe operation of the nuclear power plant.

[0049] Additional aspects and advantages of the present invention will be given in part in the following description and in part will be obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0051] Figure 1is a flow chart of a method for analyzing the importance of characteristic parameters of a large break loss of coolant accident according to an embodiment of the present invention;

[0052] Figure 2 4 is a block diagram of an importance analysis device based on characteristic parameters of a large break loss of coolant accident according to an embodiment of the present invention. DETAILED DESCRIPTION

[0053] Embodiments of the present invention are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present invention, and should not be construed as limiting the present invention.

[0054] The following describes a method and device for analyzing importance of characteristic parameters of a large break loss of coolant accident according to an embodiment of the present invention with reference to the accompanying drawings.

[0055] In the nuclear energy industry, the safety analysis of nuclear power plants has always occupied a core position due to its criticality. Especially in the face of extreme situations such as large break loss of coolant accidents, the accurate evaluation and optimization of the performance of nuclear power plant safety systems becomes particularly critical. Traditionally, the safety analysis of nuclear power plants mainly relies on two major technical routes: determinism and probabilism.

[0056] Among them, the deterministic method:

[0057] Relying on a series of engineering judgments and conservative assumptions to ensure a safety margin in the design;

[0058] More effective when dealing with known and expected operating conditions;

[0059] Its predictive capabilities may be limited when faced with unknown or extreme situations;

[0060] The analysis is often based on conservative assumptions and simplified models, which may lead to overly conservative results or deviation from the actual situation;

[0061] When assuming the most severe accident scenario, some possible failure modes may be ignored, thereby underestimating the risk of accidents.

[0062] Probabilistic approach:

[0063] Assess the likelihood and consequences of accidents through statistical and probability theory;

[0064] Consider multiple combinations of failure modes and events;

[0065] Relying on a large amount of data to estimate the probability of different events, its accuracy and reliability are challenged when data is scarce;

[0066] Probabilistic models usually require complex mathematical calculations and have high professional requirements for analysts, which limits their popularity and application.

[0067] With the changes in the operating environment of nuclear power plants and the development of technology, the existing safety analysis methods need to be further improved and developed. Develop a special importance analysis method that focuses on the importance ranking of characteristic parameters, which can adapt to complex and changing operating conditions and improve the accuracy and reliability of predictions. This method will help to better understand and quantify the impact of different parameters on nuclear power plant safety, thereby significantly improving the depth and breadth of safety analysis. Through this refined analysis, nuclear power plants can more effectively prevent and respond to extreme events and ensure the safety of the public and the environment.

[0068] At present, safety analysis in the nuclear energy industry mostly relies on empirical judgment and general simulation tools. Although these tools can provide certain analytical capabilities, they have the following problems when dealing with multi-parameter impact assessments in complex situations:

[0069] (1) Low computational efficiency: Existing tools often require a long computational time when processing large-scale data analysis and complex model calculations;

[0070] (2) Limited parameter research and analysis functions: It is difficult to conduct in-depth research and detailed analysis of characteristic parameters, and it is difficult to accurately identify and quantify the specific impact of each parameter on safety performance;

[0071] (3) Lack of adaptability and flexibility: Existing safety analysis methods are not flexible enough to adapt to new operating conditions and deal with unknown situations;

[0072] (4) Over-reliance on historical data and expert judgment: Safety analysis relies heavily on the accumulation of historical data and expert judgment.

[0073] Although this approach has its value, it also has limitations. Historical data may not fully reflect all potential accident scenarios, and expert judgment may be affected by personal experience and cognitive biases, resulting in subjective analysis results and limiting the comprehensiveness and objectivity of safety analysis.

[0074] In summary, it is necessary to develop a new importance analysis method, which can overcome the limitations of existing methods, improve the accuracy, reliability and adaptability of nuclear power plant safety analysis, and thus better ensure the safe operation of nuclear power plants.

[0075] Figure 1 It is a flow chart of a method for analyzing the importance of characteristic parameters of a large break loss of coolant accident according to an embodiment of the present invention.

[0076] like Figure 1As shown, the importance analysis method based on characteristic parameters of a large break loss of coolant accident according to an embodiment of the present invention includes:

[0077] S1, construct the reactor steady-state simulation model of the target nuclear power plant and the transient model of the large break loss of coolant accident.

[0078] First, a specific nuclear power plant needs to be selected as the research object, such as a standard 1000MWe pressurized water reactor (PWR) nuclear power plant, and detailed information such as the design parameters, safety reports and operation history of the power plant should be collected. Then, through detailed system response analysis, the key safety parameters and system behaviors that may occur in the large break loss of coolant accident, such as coolant loss rate, pressure and temperature changes, core liquid level and fuel cladding temperature, etc., are clarified. Based on these analysis results, professional simulation software (such as COSINE or RELAP5) is used to build a reactor type steady-state simulation model of the target nuclear power plant and a transient model of the large break loss of coolant accident, including the main components such as the reactor pressure vessel, steam generator, and main pump, and reasonable initial conditions and boundary conditions are set. Finally, the control logic is written to simulate the emergency response measures, and simulation calculations are performed to compare the simulation results with actual data or literature reports to ensure the accuracy and reliability of the model.

[0079] S2, determine the characteristic parameters based on the accident acceptance criteria, accident response procedure table, accident sequence and nuclear power plant system response of the large break loss of coolant accident.

[0080] According to the accident acceptance criteria, key characteristic output parameters are determined, which are used to measure the impact of the accident on the safety of the nuclear power plant. For example:

[0081] Peak temperature of fuel cladding: used to assess whether damage to the fuel cladding has occurred.

[0082] Core collapse level: used to assess whether the core cooling is sufficient.

[0083] Main steam pipe pressure: used to assess the safety of steam generators and related systems.

[0084] According to the accident response procedure table, accident sequence and dynamic response of nuclear power plant system, important characteristic input parameters are determined. For example:

[0085] Breach size and spray coefficient: directly affect the water loss rate and system response.

[0086] Pipeline resistance coefficient: affects the flow characteristics of the coolant.

[0087] Initial reactor power and system pressure: operating status before the accident, affecting the system response after the accident.

[0088] In practical applications, it is also necessary to identify the uncertainty of characteristic input parameters: the uncertainty of characteristic input parameters mainly comes from a variety of factors, including measurement errors, changes in material properties, fluctuations in operating conditions, etc. These factors may cause the input parameters to deviate from their expected values, thereby causing deviations in system responses. In the actual quantification process, historical data, expert judgment, and specialized experimental measurements can be combined to comprehensively evaluate and quantify the uncertainty range of each characteristic input parameter.

[0089] The uncertainty of feature input parameters is usually expressed through probability distribution.

[0090] If the feature input parameter X follows a normal distribution, its uncertainty can be expressed as:

[0091] X~N(μ,σ);

[0092] Among them, μ is the mean, σ is the standard deviation, which represents the random distribution of the parameter around the mean;

[0093] If the feature input parameter X follows a uniform distribution, its uncertainty can be expressed as:

[0094] X~U(a,b);

[0095] Where [a, b] represents the possible maximum and minimum ranges of the parameter, and each value has the same probability of occurring.

[0096] S3, based on the parameter range of the reactor steady-state simulation model and the transient model, generates multiple groups of random samples, and uses the multiple groups of random samples as input conditions and combines the characteristic parameters to build an accident characteristic database covering large break loss of coolant accidents under various working conditions.

[0097] In this step, based on the parameter range of the reactor type steady-state simulation model and the transient model, the distribution interval of the characteristic input parameters is determined, and the analysis program of the large break loss of coolant accident is used, and combined with the Latin hypercube sampling method, data sampling is performed on the determined characteristic input parameters within their respective distribution intervals to generate multiple groups of random samples for simulation. Afterwards, a simulation program that simulates the behavior of the nuclear power plant under the large break loss of coolant accident conditions is used to perform simulation calculations on each group of random samples, obtain the characteristic output parameters under the corresponding working conditions of each group of random samples, and construct the accident characteristic database based on the corresponding relationship between the characteristic input parameters and the characteristic output parameters.

[0098] It should be noted that in the process of sampling data for the determined characteristic input parameters within their respective distribution intervals, it is necessary to ensure that each characteristic input parameter is sampled within its defined uncertainty range. For example, if the breach size D follows a normal distribution N(1.0,0.1), then sampling is performed within the distribution range.

[0099] Define parameter range: You can define a reasonable value range for each feature input parameter. For example:

[0100] Breach size: 0.5m 2 To 2m 2

[0101] Spray coefficient: 0.8 to 1.3

[0102] Pipeline resistance coefficient: 0.01 to 0.1

[0103] Initial Reactor Power: 50% to 100%

[0104] System pressure: 15.2MPa to 15.8MPa

[0105] In the present invention, a Latin hypercube sampling method is used to generate a certain number of random samples within the definition range of each parameter, for example, 100 groups of samples are generated.

[0106] Choose appropriate simulation tools, such as COSINE, RELAP5 or ATHLET, which are able to simulate the behavior of nuclear power plants in large break loss of coolant accidents.

[0107] For each group of samples, the corresponding initial conditions and boundary conditions are set, and the simulation program is run.

[0108] Extract data of characteristic output parameters from the simulation results. For example, for each set of samples, record the peak temperature of the fuel cladding, the core collapse level, and the pressure of the main steam pipe.

[0109] The mapping relationship between feature input parameters and feature output parameters can be expressed as:

[0110] f(x)=f(X1,X2,…,X n ).

[0111] All samples and their corresponding simulation results are organized into a structured database. The database can be a table, where each row represents a sample and the columns include characteristic input parameters and characteristic output parameters.

[0112] Example database structure:

[0113] The following is a simplified example database structure:

[0114]

[0115]

[0116] Data Storage:

[0117] Store your database in an easily accessible and manageable format, such as a CSV file, a database management system (such as MySQL), or an Excel spreadsheet.

[0118] S4, constructing a target proxy model between the characteristic parameters of the large break loss of coolant accident under different working conditions according to the simulation data of the reactor steady-state simulation model and the transient model and the characteristic parameter data under various working conditions stored in the accident characteristic database.

[0119] Before building the target proxy model, the data needs to be preprocessed to ensure the quality and consistency of the data. For example, preprocessing includes at least standardization / normalization and outlier removal. Standardization / normalization is to standardize or normalize the feature input parameters and feature output parameters to have the same scale. Outlier removal is to check and remove possible outliers or erroneous data.

[0120] The present invention can use the following proxy model algorithms to construct the target proxy model:

[0121] General Polynomial Chaos Expansion (PCE);

[0122] Stochastic Collocation (SC);

[0123] Arbitrary Polynomial Chaos (APC).

[0124] Taking the non-restricted polynomial chaos expansion algorithm as an example, the mapping relationship between characteristic parameters is approximately equivalent to a simple form of a series of polynomial linear weightings:

[0125]

[0126] Where M represents the number of terms in the polynomial, n is the number of feature input parameters, and C k is the corresponding polynomial system.

[0127] For example, suppose we have built three surrogate models and verified that they all approximate the simulation results well. We can choose one or a combination of models to predict the response under new conditions.

[0128] Example steps

[0129] New case input:

[0130] Given a new working condition, for example:

[0131] Breach size: 1.5m

[0132] Spray coefficient: 1.0

[0133] Pipeline resistance coefficient: 0.04

[0134] Initial reactor power: 85%

[0135] System pressure: 15.5MPa

[0136] Model predictions:

[0137] The constructed target surrogate model (such as the PCE model) is used to predict the characteristic output parameters under this operating condition: the peak temperature of the fuel cladding, the core collapse level, and the pressure of the main steam pipe.

[0138] The predicted results of the target proxy model are compared with the actual results of the simulation program to verify the accuracy of the target proxy model.

[0139] S5, based on the response analysis of the target proxy model, analyzing the importance of the characteristic parameters in the target proxy model, and ranking them according to their influence on the accident response.

[0140] The verified target proxy model is used as an iterative tool to carry out the importance analysis of the characteristic input parameters. The importance analysis algorithm adopts the Sobol sensitivity analysis method based on variance decomposition and the correlation analysis method based on the accident database. By calculating the influence of each input parameter on the accident response output, its importance is quantified and sorted. Finally, the importance sequence of the input parameters is obtained, and the most critical parameters for the accident process and safety margin are identified, providing a reference for the optimization of accident prevention and response measures.

[0141] The importance analysis algorithm based on variance decomposition decomposes the total variance of the model output results into the sum of the variances of a single parameter and its interaction with other parameters. It can measure the comprehensive index of the influence of the model input parameters on the output results. This index comprehensively considers the main effect of a single input parameter and all possible interactions between input parameters.

[0142] This method breaks the limitations of a single model by introducing three different proxy model algorithms, including the general polynomial chaos expansion algorithm, the random configuration method, and the non-restricted polynomial chaos expansion algorithm, based on importance analysis algorithms such as variance decomposition and correlation analysis, and provides more comprehensive modeling and analysis capabilities for complex systems. This diversified algorithm design not only improves the prediction accuracy and computational efficiency of the model, but also realizes mutual verification and complementation between different algorithms through a dynamic iteration mechanism, ensuring the robustness and reliability of the modeling results.

[0143] The method of the present invention establishes a dynamic analysis framework through the coordinated application of the proxy model and the importance analysis algorithm, which can automatically identify and sort key feature parameters in large-scale data sampling and high-frequency model interaction. This automated importance sorting function significantly improves the accuracy and efficiency of the analysis and reduces the need for manual intervention. At the same time, the modular algorithm library design enables users to freely select or combine these algorithms according to different data characteristics and analysis requirements, further enriching the analysis function of the system and improving the flexibility and scalability of the application.

[0144] The present invention not only provides a rich tool library through diversified proxy model algorithms and importance analysis algorithms, but also supports seamless integration with external tools and libraries, greatly expanding the application scenarios and scope of the system. At the same time, modular design provides technical support for the continuous updating and expansion of the algorithm, ensuring that the system can continue to evolve and optimize with the development of technology. Overall, this method provides an efficient, flexible, and customizable technical framework for nuclear power plant accident analysis, laying a solid foundation for future nuclear safety management and decision support.

[0145] In an embodiment of the present invention, in the process of agent model construction and importance analysis, the method of the present invention can adopt a modular design to ensure the accuracy and efficiency of the analysis. The entire framework consists of five main modules: IO module, algorithm module, processor module, interface module and data module. The modules work closely together to achieve a complete analysis process from data input to importance ranking result output through standardized interfaces and flexible coupling mechanisms. At the same time, a variety of agent model algorithms and importance analysis algorithms are introduced into the framework to further enhance the analysis capability and adaptability of the system.

[0146] Specifically, the IO module is responsible for the input and output of data, supports data sources of different formats, and provides data preprocessing functions to ensure the quality and integrity of the input data. The algorithm module is the core of the method of the present invention, integrating a variety of proxy model algorithms, and can flexibly select the optimal algorithm according to different data characteristics and analysis requirements to build a complex input-output mapping relationship. In addition, the algorithm module also includes a variety of importance analysis algorithms such as variance decomposition and correlation analysis. Through multi-angle analysis strategies, the importance of feature parameters is comprehensively evaluated to avoid the limitations of a single algorithm. The processor module plays a key role in data processing and analysis execution in the system. It connects the IO module and the algorithm module, and is responsible for operations such as data cleaning, feature extraction, and parameter setting, providing high-quality input data for the algorithm module. At the same time, the module is also responsible for processing and converting the analysis results, so that the parameter importance ranking of the final output is more intuitive and easy to understand. The interface module enables the framework to be seamlessly integrated with external tools and technologies through standardized interface definitions. The interface modules can efficiently interact with data, further enriching the functions and application scenarios of the analysis framework. The data module is responsible for storing and managing data in all analysis processes, including raw data, sampled data, proxy model training data, and analysis results. It provides data support for the entire analysis process through structured data storage and efficient retrieval mechanisms, and ensures data security and traceability. This modular design not only improves the efficiency and accuracy of the analysis process, but also allows each module to be updated and expanded independently, enhancing the flexibility and maintainability of the system.

[0147] The IO module, algorithm module, processor module, interface module and data module are described below:

[0148] a)IO module

[0149] The IO module is a crucial part of the importance analysis method. It is responsible for handling all data exchanges with users and file systems. This module not only reads importance analysis input files, generates and manages output results, but is also responsible for recording and reporting important information and possible errors during the calculation process. This allows users to easily monitor and debug the calculation process while ensuring that the integrity and accuracy of the data are protected. Its functions range from parsing user input to providing detailed logging and error reporting to support complex data analysis.

[0150] b) Data module

[0151] The data module is mainly responsible for data management in the importance analysis method. It is responsible for organizing, storing and retrieving all data related to the calculation task, including parameters, variables, constraints and objective function values. In addition, this module provides data management, sample data collation and analysis results summary. Through built-in statistical analysis tools, the data module enhances the ability to describe and process data, allowing users to understand and analyze calculation results more deeply.

[0152] c) Processor module

[0153] The processor module is the core component that controls the execution order and iteration process of the algorithm in the importance analysis method. It manages the sequential execution of operations such as sampling, building surrogate models, and sensitivity analysis, and is responsible for coordinating the data interaction between the algorithm module and the data module. This module performs calculation tasks by calling different algorithms and models, and dynamically adjusts samples to improve the efficiency and accuracy of calculations. It also defines the conditions for the termination of iterations to ensure that the calculation can end after meeting specific criteria, thereby efficiently utilizing resources.

[0154] d) Algorithm module

[0155] As the computational core of the importance analysis method, the algorithm module integrates a variety of numerical algorithms and importance analysis core algorithms to meet different analysis needs. The numerical algorithms include basic mathematical functions such as linear algebra, numerical calculation, probability distribution and interpolation, which provide the basis for more complex algorithm implementation. In addition, the module also implements core algorithms such as sampling algorithms, surrogate model algorithms and importance analysis algorithms. The Latin hypercube sampling algorithm is used for large-scale data sampling; the surrogate model algorithm includes the general polynomial chaos expansion algorithm, the random configuration method, and the non-restricted polynomial chaos expansion algorithm; the importance analysis algorithm includes the variance decomposition algorithm and the correlation analysis algorithm. The design of the entire algorithm module not only considers the accuracy and efficiency of importance analysis, but also focuses on the user's accessibility and customization capabilities of different algorithms, ensuring that the importance analysis method can flexibly adapt to the solution of various scientific and engineering problems.

[0156] e) Interface module

[0157] The interface module acts as a bridge between external tools, simulators, and numerical libraries in the importance analysis method. It manages model evaluation, data exchange, and function calls to ensure collaboration with external computing resources. The module supports data interaction with various simulation tools. Through standardized model wrappers, users can quickly integrate custom code or simulation tools as analysis drivers for the importance analysis method, greatly expanding the scope and flexibility of the importance analysis method.

[0158] The importance analysis framework of the method of the present invention not only utilizes advanced modular design, but also improves the ability to identify and process key characteristic parameters by introducing multiple proxy model algorithms and importance analysis algorithms, thereby greatly improving the accuracy and efficiency of importance analysis. The framework adopts multiple proxy model algorithms to construct a complex mapping relationship between characteristic parameters and system responses. At the same time, combined with multiple importance analysis algorithms such as variance decomposition and correlation analysis, multi-angle and multi-level parameter importance evaluation is realized. This algorithm diversity effectively avoids the limitations of a single algorithm and makes the analysis process more comprehensive and reliable. In addition, the modular design of the importance analysis framework makes it highly flexible and scalable, and can easily integrate new technologies such as artificial intelligence, big data and Internet of Things technologies. This will further enhance the modeling ability and prediction accuracy of the importance analysis method. For example, by combining with machine learning algorithms, the nonlinear relationship between parameters can be more accurately captured under large-scale data; with the help of big data technology, more extensive data collection and processing can be achieved, thereby providing richer data support for the safety assessment of nuclear power plants; the application of Internet of Things technology can monitor and feedback the status of key parameters in real time, providing more timely and dynamic data input for the analysis framework. These characteristics greatly expand the application scenarios of this method and improve its practicality in nuclear safety analysis.

[0159] In summary, the importance analysis method based on the characteristic parameters of the large break loss of coolant accident according to the embodiment of the present invention includes: constructing a reactor type steady-state simulation model of the target nuclear power plant and a transient model of the large break loss of coolant accident; determining the characteristic parameters according to the accident acceptance criteria, accident response procedure table, accident sequence and nuclear power plant system response of the large break loss of coolant accident; generating multiple groups of random samples based on the parameter range of the reactor type steady-state simulation model and the transient model, and using the multiple groups of random samples as input conditions, combined with the characteristic parameters, constructing an accident characteristic database covering the large break loss of coolant accident under various working conditions; constructing a target proxy model between the characteristic parameters of the large break loss of coolant accident under different working conditions according to the simulation data of the reactor type steady-state simulation model and the transient model, combined with the characteristic parameter data under various working conditions stored in the accident characteristic database; based on the response analysis of the target proxy model, analyzing the importance of the characteristic parameters in the target proxy model, and ranking them according to their influence on the accident response. This method can improve the accuracy, reliability and adaptability of nuclear power plant safety analysis, thereby better ensuring the safe operation of nuclear power plants.

[0160] Figure 2 is a schematic diagram of a device for analyzing importance based on characteristic parameters of a large break loss of coolant accident according to an embodiment of the present invention.

[0161] like Figure 2 As shown, the importance analysis device 200 based on characteristic parameters of a large break loss of coolant accident according to an embodiment of the present invention comprises:

[0162] The first construction module 210 is used to construct a reactor type steady-state simulation model of the target nuclear power plant and a transient model of a large break loss of coolant accident;

[0163] A determination module 220, for determining characteristic parameters according to the accident acceptance criteria of the large break loss of coolant accident, the accident response procedure table, the accident sequence and the nuclear power plant system response;

[0164] The second construction module 230 is used to generate multiple groups of random samples based on the parameter range of the reactor type steady-state simulation model and the transient model, and use the multiple groups of random samples as input conditions and combine characteristic parameters to construct an accident feature database covering large break loss of coolant accidents under various working conditions;

[0165] The third construction module 240 is used to construct a target proxy model between characteristic parameters of a large break loss of coolant accident under different operating conditions based on the simulation data of the reactor type steady-state simulation model and the transient model and in combination with characteristic parameter data under various operating conditions stored in the accident characteristic database;

[0166] The analysis module 250 is used to analyze the importance of characteristic parameters in the target proxy model based on the response analysis of the target proxy model, and to sort them according to their influence on the accident response.

[0167] In one embodiment of the present invention, the characteristic parameters include characteristic input parameters and characteristic output parameters. The determination module 220 is used to determine the characteristic parameters according to the accident acceptance criteria, accident response procedure table, accident sequence and nuclear power plant system response of the large break loss of coolant accident, including:

[0168] According to the accident acceptance criteria, characteristic output parameters are determined; wherein the characteristic output parameters include the peak temperature of the fuel cladding, the core collapse liquid level, and the pressure of the main steam pipeline;

[0169] According to the accident response procedure table, accident sequence and nuclear power plant system response, characteristic input parameters are determined; wherein the characteristic input parameters include breach size, pipeline resistance coefficient along the pipeline, initial reactor power and system pressure.

[0170] In one embodiment of the present invention, the second construction module 230 is used to generate multiple groups of random samples based on the parameter range of the reactor type steady-state simulation model and the transient model, and use the multiple groups of random samples as input conditions and combine characteristic parameters to construct an accident feature database covering large break loss of coolant accidents under various working conditions, including:

[0171] Determine the distribution interval of characteristic input parameters based on the parameter range of the reactor steady-state simulation model and transient model;

[0172] Using the large-break LOCA analysis program and the Latin hypercube sampling method, data sampling is performed on the determined characteristic input parameters within their respective distribution intervals to generate multiple groups of random samples for simulation.

[0173] Using a simulation program that simulates the behavior of a nuclear power plant under a large break loss of coolant accident, simulation calculations are performed on each group of random samples to obtain characteristic output parameters under corresponding working conditions for each group of random samples;

[0174] According to the correspondence between feature input parameters and feature output parameters, an accident feature database is constructed.

[0175] In one embodiment of the present invention, the analysis module 250 is used to analyze the importance of characteristic parameters in the target proxy model based on the response analysis of the target proxy model, and to sort them according to their influence on the accident response, including:

[0176] The Sobol sensitivity analysis method based on variance decomposition and the correlation analysis method based on the accident database are used, and the target surrogate model is used as an iterative tool to analyze the importance of the characteristic input parameters.

[0177] Calculate the impact of each characteristic input parameter on the accident response output, and evaluate the importance of each characteristic input parameter through quantitative analysis;

[0178] According to the results of the quantitative evaluation, the feature input parameters are sorted to generate an importance sequence of the feature input parameters.

[0179] It should be noted that, for details not disclosed in the importance analysis device based on characteristic parameters of a large break loss of coolant accident in an embodiment of the present invention, please refer to the details disclosed in the importance analysis method based on characteristic parameters of a large break loss of coolant accident in an embodiment of the present invention, and no further details will be given here.

[0180] According to the importance analysis device based on the characteristic parameters of the large break loss of coolant accident of the embodiment of the present invention, the reactor type steady-state simulation model of the target nuclear power plant and the transient model of the large break loss of coolant accident are constructed by the first construction module, the characteristic parameters are determined according to the accident acceptance criteria, accident response procedure table, accident sequence and nuclear power plant system response of the large break loss of coolant accident by the determination module, multiple groups of random samples are generated based on the parameter range of the reactor type steady-state simulation model and the transient model by the second construction module, and the multiple groups of random samples are used as input conditions, combined with the characteristic parameters, to construct an accident characteristic database covering the large break loss of coolant accident under various working conditions, and the target proxy model between the characteristic parameters of the large break loss of coolant accident under different working conditions is constructed by the third construction module according to the simulation data of the reactor type steady-state simulation model and the transient model, combined with the characteristic parameter data under various working conditions stored in the accident characteristic database, and the importance of the characteristic parameters in the target proxy model is analyzed by the analysis module based on the response analysis of the target proxy model, and the parameters are ranked according to their influence on the accident response. Therefore, the device can improve the accuracy, reliability and adaptability of the safety analysis of the nuclear power plant, so as to better ensure the safe operation of the nuclear power plant.

[0181] Based on the above embodiments, the present invention further provides an electronic device.

[0182] An electronic device according to an embodiment of the present invention comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the above method.

[0183] The electronic device of the embodiment of the present invention can improve the accuracy, reliability and adaptability of nuclear power plant safety analysis by executing the above method, thereby better ensuring the safe operation of the nuclear power plant.

[0184] The computer instructions in the computer-readable storage medium of the embodiment of the present invention are used to enable a computer to execute the above method.

[0185] The computer-readable storage medium of the embodiment of the present invention can improve the accuracy, reliability and adaptability of nuclear power plant safety analysis by executing the above method, thereby better ensuring the safe operation of the nuclear power plant.

[0186] Based on the above embodiments, the present invention also proposes a computer program product.

[0187] In an embodiment of the present invention, when an instruction processor in a computer program product executes, the above method is performed.

[0188] The computer program product of the embodiment of the present invention can improve the accuracy, reliability and adaptability of nuclear power plant safety analysis by executing the above method, thereby better ensuring the safe operation of the nuclear power plant.

[0189] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0190] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In the description of the present invention, the meaning of "plurality" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0191] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, segment or portion of code comprising one or more executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present invention includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in reverse order depending on the functions involved, which should be understood by technicians in the technical field to which the embodiments of the present invention belong.

[0192] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute the instructions), or in combination with these instruction execution systems, devices or apparatuses. For the purpose of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in combination with these instruction execution systems, devices or apparatuses. More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting or processing in other suitable ways if necessary, and then stored in a computer memory.

[0193] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0194] A person skilled in the art may understand that all or part of the steps in the method for implementing the above-mentioned embodiment may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.

[0195] In addition, each functional unit in each embodiment of the present invention may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0196] The storage medium mentioned above may be a read-only memory, a magnetic disk or an optical disk, etc. Although the embodiments of the present invention have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limiting the present invention. A person of ordinary skill in the art may change, modify, replace and modify the above embodiments within the scope of the present invention.

Claims

1. A method for importance analysis based on characteristic parameters of large break loss of coolant accidents, characterized in that: include: Construct a steady-state simulation model of the target nuclear power plant and a transient model of a large-break loss-of-coolant accident; Determine the characteristic parameters based on the accident acceptance criteria, accident response procedure table, accident sequence and nuclear power plant system response of the large break loss of coolant accident; Based on the parameter range of the reactor steady-state simulation model and the transient model, multiple groups of random samples are generated, and the multiple groups of random samples are used as input conditions, combined with the characteristic parameters, to construct an accident characteristic database covering the large break loss of coolant accident under various working conditions; According to the simulation data of the reactor steady-state simulation model and the transient model, combined with the characteristic parameter data under various working conditions stored in the accident characteristic database, a target proxy model between the characteristic parameters of the large break loss of coolant accident under different working conditions is constructed; Based on the response analysis of the target proxy model, the importance of the characteristic parameters in the target proxy model is analyzed and ranked according to their influence on the accident response.

2. The method according to claim 1, characterized in that The characteristic parameters include characteristic input parameters and characteristic output parameters. The characteristic parameters are determined according to the accident acceptance criteria, accident response procedure table, accident sequence and nuclear power plant system response of the large break loss of coolant accident, including: Determining the characteristic output parameters according to the accident acceptance criteria; wherein the characteristic output parameters include the peak temperature of the fuel cladding, the core collapse liquid level, and the pressure of the main steam pipeline; The characteristic input parameters are determined according to the accident response procedure table, the accident sequence and the nuclear power plant system response; wherein the characteristic input parameters include breach size, blowdown coefficient, pipeline along-the-line resistance coefficient, initial reactor power and system pressure.

3. The method according to claim 2, characterized in that Based on the parameter range of the reactor type steady-state simulation model and the transient model, multiple groups of random samples are generated, and the multiple groups of random samples are used as input conditions, combined with the characteristic parameters, to construct an accident feature database covering the large break loss of coolant accident under various working conditions, including: Determining a distribution interval of characteristic input parameters based on parameter ranges of the reactor type steady-state simulation model and the transient model; Using the large break loss of coolant accident analysis procedure and combining with the Latin hypercube sampling method, data sampling is performed on the determined characteristic input parameters within their respective distribution intervals to generate multiple groups of random samples for simulation; Using a simulation program that simulates the behavior of a nuclear power plant under the large break loss of coolant accident condition, simulation calculations are performed on each group of random samples to obtain characteristic output parameters under corresponding working conditions for each group of random samples; The accident feature database is constructed according to the corresponding relationship between the feature input parameters and the feature output parameters.

4. The method according to claim 1, characterized in that: The response analysis based on the target proxy model analyzes the importance of characteristic parameters in the target proxy model and sorts them according to their influence on the accident response, including: The Sobol sensitivity analysis method based on variance decomposition and the correlation analysis method based on the accident database are adopted, and the target proxy model is used as an iterative tool to analyze the importance of the characteristic input parameters; Calculate the impact of each characteristic input parameter on the accident response output, and evaluate the importance of each characteristic input parameter through quantitative analysis; According to the result of the quantitative evaluation, the feature input parameters are sorted to generate an importance sequence of the feature input parameters.

5. An importance analysis device based on characteristic parameters of large break loss of coolant accidents, characterized in that: include: The first construction module is used to construct a reactor type steady-state simulation model of the target nuclear power plant and a transient model of a large break loss of coolant accident; A determination module, for determining characteristic parameters according to accident acceptance criteria, accident response procedure table, accident sequence and nuclear power plant system response of a large break loss of coolant accident; A second construction module is used to generate multiple groups of random samples based on the parameter range of the reactor type steady-state simulation model and the transient model, and use the multiple groups of random samples as input conditions and combine the characteristic parameters to construct an accident feature database covering the large break loss of coolant accident under various working conditions; A third construction module is used to construct a target proxy model between the characteristic parameters of the large break loss of coolant accident under different working conditions according to the simulation data of the reactor type steady-state simulation model and the transient model, combined with the characteristic parameter data under various working conditions stored in the accident characteristic database; The analysis module is used to analyze the importance of characteristic parameters in the target proxy model based on the response analysis of the target proxy model, and sort them according to their influence on the accident response.

6. The device according to claim 5, characterized in that The characteristic parameters include characteristic input parameters and characteristic output parameters. The determining module is used to determine the characteristic parameters according to the accident acceptance criteria, accident response procedure table, accident sequence and nuclear power plant system response of the large break loss of coolant accident, including: Determining the characteristic output parameters according to the accident acceptance criteria; wherein the characteristic output parameters include the peak temperature of the fuel cladding, the core collapse liquid level, and the pressure of the main steam pipeline; The characteristic input parameters are determined according to the accident response procedure table, the accident sequence and the nuclear power plant system response; wherein the characteristic input parameters include breach size, blowdown coefficient, pipeline along-the-line resistance coefficient, initial reactor power and system pressure.

7. The device according to claim 6, characterized in that The second construction module is used to generate multiple groups of random samples based on the parameter range of the reactor type steady-state simulation model and the transient model, and use the multiple groups of random samples as input conditions and combine the characteristic parameters to construct an accident feature database covering the large break loss of coolant accident under various working conditions, including: Determining a distribution interval of characteristic input parameters based on parameter ranges of the reactor type steady-state simulation model and the transient model; Using the large break loss of coolant accident analysis procedure and combining with the Latin hypercube sampling method, data sampling is performed on the determined characteristic input parameters within their respective distribution intervals to generate multiple groups of random samples for simulation; Using a simulation program that simulates the behavior of a nuclear power plant under the large break loss of coolant accident condition, simulation calculations are performed on each group of random samples to obtain characteristic output parameters under corresponding working conditions for each group of random samples; The accident feature database is constructed according to the corresponding relationship between the feature input parameters and the feature output parameters.

8. The device according to claim 5, characterized in that The analysis module is used to analyze the importance of characteristic parameters in the target proxy model based on the response analysis of the target proxy model, and rank them according to their influence on the accident response, including: The Sobol sensitivity analysis method based on variance decomposition and the correlation analysis method based on the accident database are adopted, and the target proxy model is used as an iterative tool to analyze the importance of the characteristic input parameters; Calculate the impact of each characteristic input parameter on the accident response output, and evaluate the importance of each characteristic input parameter through quantitative analysis; According to the result of the quantitative evaluation, the feature input parameters are sorted to generate an importance sequence of the feature input parameters.

9. An electronic device, characterized in that: include: at least one processor; as well as, a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 4.

10. A computer-readable storage medium having computer program instructions stored thereon, characterized in that: When the program instructions are executed by a processor, the method according to any one of claims 1 to 4 is implemented.

Images