115 results about "Accident analysis" patented technology

The invention relates to the technical field of hazardous chemical substance production, and provides a hazardous chemical substance safety production management and control system, in the aspect of data acquisition, all-around acquisition of equipment operation, environment and personnel operation data is realized, a high-precision sensor ensures data accuracy and far exceeds traditional finite dimension and precision acquisition, and during data analysis and processing, edge calculation is combined with deep learning, so that the safety production management and control of hazardous chemical substances is realized. A risk assessment model is dynamically adjusted, the limitation of a traditional fixed model is broken through, production change and risk early warning can be adapted in real time, risk levels are dynamically adjusted, multi-element early warning and visual display are achieved, compared with single early warning and simple display, risk perception is more timely and accurate, accurate reasons are found through a unique accident analysis model, and the risk assessment efficiency is improved. According to the method, the production management and operation improvement can be promoted, each module of the system can be optimized, a closed-loop lifting mechanism is formed, the safety production management and control level of the hazardous chemical substances is comprehensively improved from data acquisition, analysis, early warning and optimization, the safety risk is greatly reduced, and the production safety and stability are guaranteed.

The invention relates to the technical field of accident responsibility judgment, solves the problem that intelligent driving accident analysis and real-time responsibility judgment cannot be carried out in the prior art, and provides an accident responsibility judgment method, device and equipment in an intelligent driving scene and a storage medium. The method comprises the following steps: analyzing related parameters of an accident in an intelligent driving scene, and determining a plurality of key variables in the related parameters and a causal network corresponding to each key variable; according to a pre-collected traffic database and the causal network, the occurrence probability of each key variable is quantified, and a prior knowledge base related to an intelligent driving accident is determined; and according to the real-time data of the intelligent driving accident and the prior knowledge base, in combination with the Bayesian theorem, accident causes are analyzed, and an accident responsible party is determined. According to the method, man-machine responsibility division of the intelligent driving accident can be realized, and the emergency processing capability and the judgment efficiency of the intelligent driving system after the accident are remarkably improved.

The invention discloses an accident analysis and intelligent intervention method and system based on an intelligent networked automobile, and particularly relates to the technical field of accident analysis, which comprises the following steps: when the intelligent networked automobile approaches an accident-prone place, extracting important features from historical traffic data in the accident-prone place of the intelligent networked automobile by using a t-SNE dimension reduction method; acquiring real-time traffic data of the intelligent networked automobile, and determining similar information of the traffic data of the intelligent networked automobile; bayesian inference is carried out based on historical traffic data in an accident-prone place of the intelligent networked automobile and real-time traffic data of the intelligent networked automobile, and probability information of the traffic data of the intelligent networked automobile is determined by analyzing statistical data and constructing a machine learning mode; through comprehensive analysis of the similar information and the probability information of the traffic data, the risk that the intelligent networked automobile enters the accident-prone place is evaluated, the road traffic safety can be improved, and the accident occurrence rate is reduced.

The embodiment of the invention discloses a traffic accident data processing and analyzing method and device and electronic equipment. The method comprises the steps of performing data fusion on traffic accident data in various data formats based on a large-model heterogeneous field mapping method to obtain an accident data set, performing data cleaning on the accident data set according to a dynamic rule engine and a correction mechanism to obtain a target data set, and storing the target data set in a database. And finally, performing hierarchical analysis on the target data set based on the multi-dimensional accident analysis model to obtain a data analysis result, and performing visual display on the data analysis result. Through multi-source data intelligent fusion, data quality control and a multi-dimensional accident analysis model, the data quality of the multi-source data is improved, the purpose of efficiently and automatically processing different data formats is achieved, a large amount of human resources are saved, and meanwhile the accuracy and reliability of a data processing analysis result are improved.

The invention discloses a data alignment method and device, and relates to the technical field of computers. A specific embodiment of the method comprises the steps of obtaining target cabin sound data and target flight data corresponding to a target flight terminal; performing parameter analysis on the target flight data to obtain a plurality of air-ground dialogue moments; sorting the plurality of air-ground dialogue moments according to time to obtain a first time sequence corresponding to the plurality of air-ground dialogue moments; cutting the target cabin sound data to obtain a second time sequence corresponding to a plurality of cabin sound moments; and determining the alignment moment of the target cabin sound data and the target flight data according to the overlapping degree of the first time sequence and the second time sequence. According to the embodiment, the alignment moment between the target cabin sound data and the target flight data can be accurately determined, so that effective alignment between the target cabin sound data and the target flight data is realized, and the accuracy of data analysis in subsequent accident analysis and flight quality evaluation is greatly improved.

The invention relates to an intelligent generation method for a subway emergency disposal scheme. The method comprises the following steps: S1, constructing an emergency plan knowledge graph; s2, performing automatic accident analysis and information extraction; and S3, generating an emergency disposal scheme. The invention further relates to a subway emergency disposal scheme intelligent generation system and a computer readable storage medium. The method has the advantages of high efficiency, accuracy, intelligence and the like, intelligent generation of the disposal scheme is realized by performing automatic analysis on accident data and combining a knowledge graph RAG technology, and the scheme generation speed is remarkably improved. The semantic reasoning ability of the knowledge graph and the deep analysis ability of the large model are utilized to ensure the high matching degree of the generation scheme and the actual event. The knowledge extraction and relation recognition technology of a large model is combined, automatic generation and logic relation reasoning of the emergency task unit are achieved, and the intelligent level is improved.

The present invention relates to a method and system for analyzing and visualizing traffic accident data for autonomous vehicles. The method comprises: collecting raw data related to vehicle traffic accidents and standardizing and integrating the raw data; cleaning and verifying the standardized and integrated data, time-calibrating, and synchronizing the data to obtain processed data; obtaining the collision time point based on the speed and path of the accident vehicle; analyzing the driving mode at the time of collision, the vehicle steering before the collision, the vehicle pedals before the collision, the vehicle accessories before the collision, the vehicle fault before the collision, the traffic signals and road markings before the collision, and the vehicle status after the collision based on the processed data and the collision time point to obtain key time points; and visually displaying the analysis results based on the processed data and the key time points. The present invention can achieve key time point marking and automatically generate and save scientific and standardized accident analysis reports.

The invention relates to the technical field of artificial intelligence, and discloses a simple traffic accident liability intelligent affirmation system and method based on an AI large model, and the method comprises the steps: collecting an accident scene image and an accident description text of a simple traffic accident scene, and carrying out the feature extraction of the accident scene image and the accident description text, obtaining accident key parameters and accident semantics; analyzing the accident space-time field quantity of the simple traffic accident scene, and constructing an accident space-time panorama by using the accident space-time field quantity; constructing an accident association map of a simple traffic accident scene, and analyzing an accident logic chain by using the accident association map; performing accident liability analysis on the simple traffic accident scene based on the accident space-time panorama and the accident logic chain to obtain an accident analysis text; and performing accident judgment optimization and intelligent conclusion calibration on the accident liability text to obtain a target accident text, and constructing an accident liability report by using the target accident text. According to the invention, the efficiency of simple traffic accident liability determination can be improved.

The invention relates to the technical field of track defect detection, in particular to a detection system for an electromagnetic track surface coating and a wear failure test analysis method. The system comprises a mobile device, a laser, a galvanometer, a temperature measurement module, an analysis module, a control module and the like, and the method comprises the steps of macroscopic inspection, parameter setting of laser defect inspection, laser defect inspection, data processing, failure form analysis and the like. The temperature measuring module measures temperature and transmits data, and the surface of the whole track is detected through laser spots and movement of the moving device. The method can solve the problem that an existing detection technology cannot rapidly and accurately detect the coating abrasion defect of the electromagnetic track, can effectively standardize the defect, failure and even accident analysis process of the coating of the electromagnetic track, and has the advantages of avoiding track failure caused by coating abrasion failure of the electromagnetic track, improving the reliability of the track and improving the reliability of the track. It is of great significance to ensure safe and stable operation.

The invention discloses a shipping accident analysis method. The method comprises the following steps: constructing a shipping accident knowledge graph; inputting questions, retrieving the shipping accident knowledge graph by adopting a retrieval enhancement generation method, and generating answers; wherein the retrieval enhancement generation method is adopted to retrieve the shipping accident knowledge graph and generate the answer, and the method comprises the following steps of: analyzing a question by adopting a large language model to generate a query statement; retrieving in the shipping accident knowledge graph according to the query statement, outputting nodes and edges matched with the query statement from the shipping accident knowledge graph, and generating a Bayesian network according to the matched nodes and edges; generating a query result according to the conditional probability of a target node and a father node thereof and / or the posterior probability of a child node thereof in the Bayesian network, and inputting the query result into the large language model; and the large language model generates an answer according to the query result. The invention further discloses a shipping accident analysis device, computer equipment and a storage medium. The method comprises the following steps: extracting and storing shipping accident data by adopting a large language model in combination with a knowledge graph, and analyzing the shipping accident data in combination with a Bayesian network analysis model to obtain an occurrence probability of a complete causal chain from causes to accident results in an accident, so that objective and accurate accident causals are sorted out for complex shipping accidents, and the probability of occurrence of the complete causal chain is improved. And reliable conclusions and suggestions are provided for subsequent shipping businesses.

The invention discloses an accident analysis method and system based on digital twinning, a product and a medium. The method comprises the following steps of: calculating an actual stress value and a theoretical stress value by collecting deformation data of the protective fence and a vehicle driving record; the protective fence is divided into different stress areas according to the deformation degree, and the difference value proportion of the theoretical stress value and the actual stress value of each area is calculated; the reliability index of each area is determined by combining the collision angle, the collision part and the deformation characteristic of the vehicle, and a weight coefficient table is established; and combining a difference value proportion with a reliability weight by using a regional weighted integral method, calculating a final stress compensation value, and providing a more accurate accident analysis basis. By implementing the technical scheme provided by the invention, the accuracy of road traffic guardrail accident analysis is improved.

The invention provides a vehicle accident data processing method and device and a storage medium, and the method comprises the steps: S1, obtaining the vehicle state information of a vehicle within a preset time range before and after the accident time according to the accident time after a triggering event of an accident is received; s2, inputting the vehicle state information into a pre-trained vehicle accident analysis model, and judging whether the vehicle has an accident or not; s3, when it is judged that the vehicle has the accident, determining the latest effective parking time point; s4, according to the effective parking time point, judging whether at least one piece of alarm data of a predetermined type exists or not; if yes, determining the time corresponding to the first piece of alarm data of the pre-type as the accident occurrence time; otherwise, determining the time corresponding to the vehicle positioning record which is closest to the effective parking time point and has the vehicle speed greater than 0 as the accident occurrence time. By means of the technical scheme, the accident occurrence time can be determined more accurately.

The present application relates to a kind of EPR nuclear power unit accident initiation event list optimization method and system, method includes: collecting the initiation event list of each nuclear power unit;Each initiation event list is compared and analyzed, and the optimization object of the accident initiation event list of EPR nuclear power unit is determined according to comparison result;Frequency analysis is carried out to the accident initiation event in optimization object;EPR accident classification standard and frequency analysis result are combined to reclassify accident;According to the classification result, optimization initiation event list is carried out;Generation optimized initiation event list.Through implementation of the present application, after the optimization of the accident initiation event list of EPR nuclear power unit, optimization EPR accident analysis and EPR nuclear power unit operation technical specification are carried out, realize unit online maintenance, further improve the economic benefit of nuclear power plant under the premise of guaranteeing safety.

The invention discloses a nuclear power plant accident analysis method and device, and relates to the technical field of nuclear power safety analysis. The method includes: responding to user triggering to perform accident analysis of a first accident type on a nuclear power plant, and acquiring a first input card and a first reference card; the first input card is used for representing an initial analysis condition corresponding to accident analysis of a first accident type of the nuclear power plant, and the first reference card is used for representing an accident verification standard of the first accident type; based on the first input card, calling a first calculation configuration template corresponding to the first accident type to perform accident calculation to obtain a first accident calculation result; the first calculation configuration template is used for representing a calculation process rule of the first accident type; and determining an accident analysis result of the nuclear power plant in the first accident type based on the first accident calculation result and the first reference card. According to the invention, the accident analysis efficiency can be improved.

The application provides a control rod uncontrolled lifting accident analysis method of a reactor, including providing a first neutron dynamics model, and setting a shutdown protection signal, the shutdown protection signal including an over-power protection signal and a period protection signal; carrying out power spectrum analysis according to the first neutron dynamics model to obtain a transient peak power; obtaining a transient MDNBR based on the transient peak power and initial thermal parameters of the reactor; comparing the transient MDNBR with a safety analysis limit value, if the transient MDNBR is less than or equal to the safety analysis limit value, then carrying out a system optimization operation and returning to carry out the power spectrum analysis until the transient MDNBR is greater than the safety analysis limit value. The application only carries out neutron dynamics calculation and does not carry out thermal flow and heat transfer calculation, the calculation process is the most conservative, for example, if the accident analysis process only carries out a first analysis stage, the analysis process is the most simple, and the work efficiency of the accident analysis can be greatly improved.

The application discloses a vehicle safety belt device and a vehicle safety system, which comprise a safety belt, a winding device and a monitoring module. The monitoring module is used for monitoring the length of the pulling-out and winding of the safety belt, so as to judge whether the wearing mode of the safety belt is correct, for example, whether a passenger wears the safety belt and whether the safety belt is correctly worn. By monitoring the pulling-out length of the safety belt, the size of the passenger's body can be judged. When a collision occurs, corresponding safety belt burst points and airbag burst points can be burst, so that better protection is provided for the passenger. By monitoring the pulling-out length of the safety belt, the current sitting posture of the passenger can be judged. When a collision occurs, the posture and displacement of the passenger can be judged by monitoring the pulling-out and winding length of the safety belt, and whether the safety belt is normally actuated can be judged, so that a basis is provided for accident analysis.

The invention discloses a fine tuning method, system and equipment for an electric power intrinsic safety analysis model based on knowledge distillation, and a medium, and belongs to the technical field of electric power safety analysis. The method comprises the following steps: collecting professional knowledge data in the field of electric power intrinsic safety analysis, and performing professional knowledge supervision fine tuning to obtain a distillation model; and guiding an output thinking process and a root cause based on problem description through the distillation model, and introducing a super model and a causal knowledge graph for evaluation to obtain an evaluation result. Through combination of knowledge distillation and the causal knowledge graph, the accuracy and interpretability of an electric power intrinsic safety analysis inference model are remarkably improved, the thinking process and the root cause of problem description are generated through the distillation model, output is evaluated by using the super model and the causal knowledge graph, the causal inference ability is enhanced, and the accuracy and the interpretability of the electric power intrinsic safety analysis inference model are improved. The problem that the causal relationship of a traditional model is fuzzy in complex power accident analysis is effectively solved.

The invention discloses an intelligent fire-fighting management system based on region division and a model and an early warning method thereof, and belongs to the technical field of intelligent fire fighting, and the method specifically comprises the steps that a system initialization unit is responsible for recording all equipment information in a monitoring region, subdividing the monitoring region into sub-regions based on equipment distribution, and associating the sub-regions with equipment; the region defining unit identifies the related sub-regions as to-be-confirmed regions when a fire occurs, and marks to-be-confirmed devices; the data acquisition unit collects real-time monitoring data of the equipment, and preliminarily analyzes and judges whether a fire is an electrical fault or not; and if yes, further collecting historical power consumption data. The accident analysis unit normalizes the historical data, constructs a time sequence model, and analyzes the current intensity change; if the real-time current value cluster deviates, a fire disaster caused by abnormal behaviors of the equipment is deduced; otherwise, the aging is caused by the electrical insulating material; according to the invention, the electrical fault is identified through the power consumption data.

The invention discloses a domestic autonomous novel fuel assembly water loss accident analysis method and system and a medium, and the method comprises the steps: calculating the maximum cladding peak temperature for different life periods, obtaining the life period A corresponding to the maximum cladding peak temperature, calculating the maximum oxidation film thickness for different life periods, and obtaining the life period B corresponding to the maximum oxidation film thickness; taking the life period A as a target life period, and carrying out water loss accident analysis by changing the axial power distribution of the domestic novel fuel assembly to obtain the final maximum cladding peak temperature and the maximum oxidation film thickness; taking the life period B as a target life period, and carrying out water loss accident analysis by changing the axial power distribution of the domestic novel fuel assembly to obtain the maximum oxidation film thickness; and comparing the maximum oxide film thickness with the maximum oxide film thickness, and taking the larger value as the final maximum oxide film thickness. The method is suitable for domestic novel fuel assemblies, and the accuracy and efficiency of fuel assembly water loss accident analysis are improved.

This application provides a method, computing device, and storage medium for analyzing accident-resistant fuel core meltdown accidents, relating to the field of nuclear reactor technology. The method provided includes calculations of post-accident core temperature rise and oxidation, oxide layer thinning, fuel cladding damage and fuel collapse, fission product release, and molten pool interaction and heat transfer. This forms a safety analysis method for accident-resistant fuels in core meltdown accidents, supporting the demonstration of safety improvements after accident-resistant fuel core meltdown accidents and guiding the research and design of accident-resistant fuels.

The present application relates to the field of nuclear power unit accident analysis, and particularly relates to a coupling method of VVER unit system program and neutron dynamics program. The method is as follows: a reactor system program is compiled into a dynamic link library by adding an interface function in a three-dimensional neutron dynamics program of a reactor core, and the dynamic link library is accessed and called by the reactor system program in a plug-in mode; a neutron physics model of a specific loading scheme of a VVER type reactor is established; a simulation model of an accident analysis system of the VVER type pressurized water reactor is established; control logic of each main system and device of the primary loop and the secondary loop of the VVER type reactor is established; control logic and conservative condition settings for specific accidents are established; coupling calculation of the reactor system program and the three-dimensional neutron dynamics of the reactor core is performed; and key safety parameters of the VVER type reactor in specific accidents are obtained based on the results of the coupling calculation. The present application can simulate the changes of physical thermal parameters and the action responses of main systems in the primary loop and the secondary loop of the reactor after accidents, and is convenient for efficient and reliable accident analysis of the VVER type nuclear power unit.

According to the automobile electronic data forensics analysis method and device and the storage medium, EDR and VDR data are extracted through a portable automobile electronic data forensics device, and on the basis of the following analysis processes, two automobile driving track points with unified time and space are automatically generated in combination with field investigation data, so that quick reproduction analysis of accident tracks at a software side is realized; the analysis process comprises the steps that a Cartesian simulation coordinate system of the passenger car is established, and simulation track points are generated; based on Kruger-n series expansion of a WGS84 ellipsoid, mapping track points of a simulation coordinate system to a geographic coordinate system through a mapping relation between simulation coordinates corresponding to an anchor point, namely a passenger car collision point and corresponding GPS coordinates; performing affine transformation from a Cartesian simulation coordinate system to a UTM coordinate system; and back projection is carried out, i.e., the UTM coordinate system to the latitude and longitude. According to motor vehicle accident data evidence obtaining and accident analysis, the accident investigation evidence obtaining and analysis efficiency is improved through evidence obtaining tool innovation and accident track reconstruction analysis method innovation.

The present invention discloses a design method for an intelligent operation board. A MOSFET circuit is added to the internal circuit of a line protection box. When a circuit breaker fails, the MOSFET circuit can automatically cut off the control power supply of the operation circuit through a CPU control command, without generating arcing, thereby protecting the closing and opening coils of the circuit breaker from being burned. On the intelligent board, control output can be performed according to external information, and the circuit can be controlled according to feedback signals and an internally set opening and closing holding time. The design method of the intelligent operation board of the present invention can record various on-site operations, perform accident analysis, and protect the opening and closing coils of the circuit breaker and the opening and closing relay nodes on the measurement and control equipment, thereby solving the problem of only protecting the relay nodes and sacrificing the opening and closing coils of the circuit breaker.

A digital twin-based accident analysis method, system, product, and medium. The method includes: calculating the actual force value and theoretical force value by collecting guardrail deformation data and vehicle driving records; dividing the guardrail into different force areas according to the degree of deformation, and calculating the difference ratio between the theoretical and actual force values ​​in each area; combining the vehicle collision angle, collision location, and deformation characteristics to determine the reliability index of each area and establish a weight coefficient table; using the regional weighted integral method, combining the difference ratio with the reliability weight to calculate the final force compensation value, providing a more accurate basis for accident analysis. Implementation of the technical solution provided by this application improves the accuracy of highway traffic guardrail accident analysis.

The invention provides a method and a device for testing vehicle-mounted event data records. The method comprises the following steps that: a signal simulation system obtains field values of a plurality of fields recorded by vehicle-mounted event data, generates scene simulation data based on the plurality of field values, and transmits the scene simulation data to a signal reporting system; the signal reporting system uploads the scene simulation data to an Internet of Vehicles platform; the analysis system obtains a pull value of the scene simulation data from the Internet of Vehicles platform, and obtains an expected value of the scene simulation data from the signal simulation system; and comparing the expected value with the pull value to generate a comparison report. In the mode, all-around test support can be provided for research and development improvement, type authentication and quality control of the EDR product, the reliability and data recording quality of the EDR product can be improved, and a more reliable data basis is provided for automobile safety accident analysis and responsibility confirmation.

The present invention belongs to the field of accident analysis, and specifically discloses an analysis method and system for the influence of control defects in third-party construction accidents of gas pipelines. The analysis method includes the following steps: establishing system tasks and safety constraints, constructing the hierarchical structure of the STAMP model according to preset functional requirements and safety objectives, and analyzing in combination with the VSM model to identify control defects; digitally expressing the control defects obtained from the analysis of each third-party construction accident of gas pipelines, and obtaining the coefficient of control defects in third-party construction accidents of gas pipelines through Pearson correlation analysis; using the CRITIC weight method to process and calculate the coefficient of control defects in third-party construction accidents of gas pipelines obtained from the correlation analysis to obtain the weight of control defects in third-party construction accidents of gas pipelines; finally, according to the hierarchical structure and the weight of control defects, constructing a system dynamics model to determine the key control defects in third-party construction accidents of pipelines, so as to formulate targeted prevention and improvement measures.

The application discloses a shipping accident analysis method, comprising the following steps: constructing a shipping accident knowledge graph; inputting a question, searching the shipping accident knowledge graph by using a search enhancement generation method, and generating an answer; wherein the search enhancement generation method comprises the following steps: analyzing the question by using a large language model, generating a query statement, searching the shipping accident knowledge graph according to the query statement, outputting nodes and edges matched with the query statement from the shipping accident knowledge graph, generating a Bayesian network according to the matched nodes and edges, generating a query result according to the conditional probability of a target node and its parent nodes and / or the posterior probability of the target node and its child nodes in the Bayesian network, inputting the query result into the large language model, and generating an answer according to the query result by the large language model. The application further discloses a shipping accident analysis device, a computer device and a storage medium. By using a large language model combined with a knowledge graph to extract and store shipping accident data, and by using a Bayesian network analysis model to analyze the shipping accident data, the occurrence probability of a complete cause-and-effect chain from causes to results of an accident can be obtained, so that objective and accurate causes and effects of a complex shipping accident can be sorted out, and reliable conclusion opinions can be provided for subsequent shipping business.

This invention relates to the field of road management, specifically to a data-driven road traffic risk control system and method, comprising: a road monitoring module, a vehicle management module, an accident analysis module, a traffic focusing module, and a dispatching and allocation module. The road monitoring module is used to establish a road network model; the vehicle management module is used to plan the optimal driving route; the accident analysis module is used to determine the type of accident; the traffic focusing module is used to optimize patrol routes; and the dispatching and allocation module is used to build an exchange service platform for command and dispatch. This invention can improve traffic operation efficiency, reduce accident risks, build an intelligent traffic management system, enhance the perception and management level of urban traffic, improve the accuracy of traffic accident target detection, improve traffic infrastructure construction, enhance road network safety, optimize the allocation of human and material resources, and reduce traffic management costs.

The present invention provides a system and method for recording autonomous vehicle event data, wherein the system includes: a daemon thread unit for activating / deactivating a monitoring thread unit and a recording thread unit according to a set thread control rule based on a monitoring count and a recording count; a monitoring thread unit for storing the vehicle data, autonomous driving-related information, and camera data transmitted by a data transmission unit in chronological order and performing monitoring counts; and a recording thread unit for reading and parsing the data stored by the monitoring thread unit to generate a parsing result, initiating data recording when the parsing result meets a recording start condition, and storing the data recording result and performing a recording count at the end of data recording. The system and method achieve complete recording of autonomous vehicle collision events and collision risk events while taking into account the integrity and security of the data, providing an important basis for autonomous vehicle accident analysis and liability determination.

Provided is an accident sequence screening method based on a combination of a fully connected neural network (FCNN) and particle swarm optimization (PSO), relating to the technical field of accident sequence screening, comprising the following steps: S101, defining a research object and a target parameter, and completing deterministic and probabilistic modeling; S201, concurrently computing RELAP5 programs by using a concurrent computing method, to quickly construct a deep learning database; S301: constructing a deep learning surrogate model by using an FNCC analysis method, to replace RELAP5 for accident analysis; and S401: calling the deep learning surrogate model for accident analysis by using a PSO approach, quickly capturing an optimal solution for each accident sequence, and screening out sequences that require Best Estimate Plus Uncertainty (BEPU) analysis. In this method, a surrogate model is constructed based on a fully connected neural network to replace a conventional system simulation program, which improves the efficiency of single accident analysis; optimization calculations are performed for the constructed surrogate model by using a PSO algorithm, which reduces the amount of analysis calculations.