Quantitative decision behavior evaluation method and system under nuclear emergency condition

Abstract

The invention discloses a quantitative decision behavior evaluation method and system under a nuclear emergency condition, and relates to the technical field of emergency management of emergencies, and the method comprises the steps: receiving a decision behavior scheme under the nuclear emergency condition, and carrying out the prediction and outputting a plurality of accompanying emergency events. And constructing a decision behavior prediction tree, performing risk assessment on the decision behavior scheme, and outputting a decision behavior risk index. And performing risk assessment on the plurality of accompanying emergency events, and outputting a plurality of accompanying risk indexes. And performing quantitative identification on the decision behavior prediction tree according to the decision behavior risk index and the plurality of accompanying risk indexes, and outputting the identified decision behavior prediction tree. And performing risk fitting on the identified decision behavior prediction tree to generate a decision behavior evaluation report. The technical problems that in the prior art, a nuclear emergency decision assessment method is difficult to carry out dynamic risk assessment on decision behaviors, so that the emergency decision behavior assessment accuracy is difficult to improve, and the emergency decision reliability is affected are solved.

Description

Technical Field

[0001] The present application relates to the technical field of emergency management of sudden incidents, and in particular to a method and system for evaluating quantitative decision-making behavior in nuclear emergency situations. Background Art

[0002] When a nuclear emergency occurs, quick and effective decision-making is crucial to mitigate the impact of the accident and ensure public safety. In actual operations, decision-making behavior plans usually trigger a series of accompanying emergency events, such as equipment failure, failure to evacuate personnel, or the spread of radioactive materials. The occurrence of these accompanying emergency events may significantly increase the difficulty and complexity of emergency response. Therefore, accurately predicting these accompanying emergency events and conducting risk assessments on them is a key link in optimizing decision-making behavior plans. Traditional risk assessment methods mainly rely on static risk assessments based on historical data, which cannot flexibly respond to real-time data changes, resulting in low prediction accuracy and insufficient decision reliability.

[0003] Therefore, in the existing nuclear emergency decision-making assessment method, it is difficult to conduct dynamic risk assessment of decision-making behavior, resulting in difficulty in improving the accuracy of emergency decision-making behavior assessment, which affects the technical problem of the reliability of emergency decision-making. Summary of the invention

[0004] This application provides a method and system for evaluating quantitative decision-making behavior in nuclear emergency situations, which solves the technical problem that the nuclear emergency decision-making evaluation method in the prior art is difficult to dynamically evaluate the risk of decision-making behavior, resulting in difficulty in improving the accuracy of emergency decision-making behavior evaluation and affecting the reliability of emergency decision-making. By constructing a decision-making behavior prediction tree and combining a feedback adjustment mechanism for the number of real-time accompanying emergency events, dynamic risk evaluation and optimization of accompanying events are achieved, the accuracy of risk evaluation of decision-making behavior in nuclear emergency events is improved, and the technical effect of improving the reliability of emergency decision-making is improved.

[0005] The present application provides a method for quantitative decision-making behavior assessment under nuclear emergency conditions, the method comprising: receiving a decision-making behavior plan under nuclear emergency conditions, predicting the decision-making behavior plan, and outputting multiple accompanying emergency events. Using the multiple accompanying emergency events as child nodes and the decision-making behavior plan under nuclear emergency conditions as a parent node to build a decision-making behavior prediction tree. Performing a risk assessment on the decision-making behavior plan and outputting a decision-making behavior risk index. Performing a risk assessment on the multiple accompanying emergency events respectively and outputting multiple accompanying risk indexes. Quantitatively marking the decision-making behavior prediction tree according to the decision-making behavior risk index and the multiple accompanying risk indexes, and outputting the marked decision-making behavior prediction tree. Generate a decision-making behavior assessment report by performing risk fitting on the marked decision-making behavior prediction tree.

[0006] In the implementation, the decision-making behavior scheme is predicted and multiple accompanying emergency events are output. The method includes: collecting historical nuclear emergency event samples. Constructing an accompanying emergency event prediction model, and performing simulation prediction on the historical nuclear emergency event samples and the accompanying emergency event samples according to the accompanying emergency event prediction model to obtain the prediction accuracy. The decision-making behavior scheme is predicted according to the accompanying emergency event prediction model, and an initial accompanying emergency event set and the accompanying probability of each initial accompanying emergency event are output. The initial accompanying emergency events with a probability greater than a preset accompanying probability are screened and output as the multiple accompanying emergency events.

[0007] In the implementation, a concomitant emergency event prediction model is constructed, and the method includes: constructing an emergency scenario simulation model, analyzing the evolution process of the historical nuclear emergency event samples with the emergency scenario simulation model, identifying the concomitant emergency event samples of each historical nuclear emergency event sample, and the concomitant factors of each concomitant emergency event sample, wherein the concomitant factor is the magnitude of the concomitant occurrence probability of the event. Training is performed based on the historical nuclear emergency event samples, the concomitant emergency event samples, and the concomitant factors of each concomitant emergency event sample, and if the prediction accuracy reaches a preset threshold, the concomitant emergency event prediction model is output.

[0008] In the implementation method, the emergency scenario simulation model is used to analyze the evolution process of the historical nuclear emergency event samples, including horizontal evolution analysis and vertical evolution analysis, wherein the horizontal evolution analysis is to simulate the diffusion scenario of the historical nuclear emergency event samples, and the vertical evolution analysis is to simulate the chain scenario of the historical nuclear emergency event samples.

[0009] In an implementation, the risk assessment of the decision-making behavior scheme is performed, and a decision-making behavior risk index is output. The method includes: performing a zoning simulation on the decision-making behavior scheme to obtain multiple areas. Identifying the personnel protection rate and the equipment protection rate of each of the multiple areas, and outputting multiple personnel protection rates and multiple equipment protection rates. Calculating according to the multiple personnel protection rates and the multiple equipment protection rates, and outputting the decision-making behavior risk index.

[0010] In an implementation, the risk of the multiple accompanying emergency events is evaluated respectively, and multiple accompanying risk indicators are output. The method includes: collecting accompanying emergency event samples and accompanying loss indicator samples of the accompanying emergency event samples according to the event attributes of the multiple accompanying emergency events. Establishing an accompanying event risk evaluation network according to the accompanying emergency event samples and the accompanying loss indicator samples. Performing risk evaluation on each accompanying emergency event according to the accompanying event risk evaluation network, and outputting multiple accompanying risk indicators.

[0011] In the implementation, by performing risk fitting on the identified decision behavior prediction tree, the method includes: dividing the identified decision behavior prediction tree according to its hierarchy, outputting multi-level child nodes, including first-level child nodes, second-level child nodes, third-level child nodes, ... Nth-level child nodes. Performing level identification on the multi-level child nodes, and outputting multi-level level indicators. Using the multi-level level indicators as weights, performing risk fitting with the decision behavior risk indicator and the multiple accompanying risk indicators as inputs, and outputting risk fitting indicators. Based on the risk fitting indicators, a decision behavior assessment report is generated.

[0012] In the implementation, multiple accompanying emergency events are output, and the method further includes: obtaining the real-time number of the multiple accompanying emergency events. According to the ratio of the real-time number to the preset number, an adjustment coefficient is generated, and when risk fitting is performed on the identified decision behavior prediction tree, feedback adjustment is performed according to the adjustment coefficient.

[0013] The present application also provides a quantitative decision-making behavior evaluation system in nuclear emergency situations, including: The accompanying event acquisition module is used to receive the decision-making behavior plan under the nuclear emergency situation, predict the decision-making behavior plan, and output multiple accompanying emergency events.

[0014] The behavior prediction tree construction module is used to construct a decision behavior prediction tree by taking the multiple accompanying emergency events as child nodes and the decision behavior scheme under the nuclear emergency situation as a parent node.

[0015] The decision-making behavior risk assessment module is used to conduct a risk assessment on the decision-making behavior plan and output a decision-making behavior risk index.

[0016] The accompanying emergency risk assessment module is used to conduct risk assessment on the multiple accompanying emergency events respectively and output multiple accompanying risk indicators.

[0017] The identification module is used to quantitatively identify the decision behavior prediction tree according to the decision behavior risk index and the multiple accompanying risk indicators, and output the identified decision behavior prediction tree.

[0018] The evaluation report acquisition module is used to generate a decision behavior evaluation report by performing risk fitting on the identified decision behavior prediction tree.

[0019] The invention proposes a quantitative decision-making behavior evaluation method and system under nuclear emergency situations. By receiving the decision-making behavior scheme under nuclear emergency situations, the decision-making behavior scheme is predicted and multiple accompanying emergency events are output. The multiple accompanying emergency events are used as child nodes, and the decision-making behavior scheme under nuclear emergency situations is used as a parent node to build a decision-making behavior prediction tree. The decision-making behavior scheme is risk-evaluated and the decision-making behavior risk index is output. The multiple accompanying emergency events are risk-evaluated respectively and multiple accompanying risk indexes are output. The decision-making behavior prediction tree is quantitatively identified according to the decision-making behavior risk index and the multiple accompanying risk indexes, and the identified decision-making behavior prediction tree is output. The decision-making behavior prediction tree is risk-fitted to the identified decision-making behavior prediction tree to generate a decision-making behavior evaluation report. The invention solves the technical problem that the nuclear emergency decision-making evaluation method in the prior art is difficult to dynamically evaluate the risk of decision-making behavior, which makes it difficult to improve the accuracy of emergency decision-making behavior evaluation and affects the reliability of emergency decision-making. By constructing a decision-making behavior prediction tree and combining the feedback adjustment mechanism of the number of real-time accompanying emergency events, the dynamic risk evaluation and optimization of accompanying events are realized, the accuracy of the risk evaluation of decision-making behavior in nuclear emergency events is improved, and the reliability of emergency decision-making is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solution of the embodiment of the present disclosure, the accompanying drawings of the embodiment of the present disclosure will be briefly introduced below. A flow chart is used in the present application to illustrate the operations performed by the system according to the embodiment of the present application. It should be understood that the preceding or following operations are not necessarily performed accurately in order. On the contrary, various steps can be processed in reverse order or simultaneously as needed. At the same time, other operations can also be added to these processes, or one or more operations can be removed from these processes.

[0021] Figure 1 A flowchart of a quantitative decision-making behavior evaluation method under nuclear emergency conditions provided in an embodiment of the present application; Figure 2 A schematic diagram of the structure of a quantitative decision-making behavior evaluation system for nuclear emergency situations provided in an embodiment of the present application.

[0022] Explanation of the accompanying symbols: accompanying event acquisition module 11, behavior prediction tree construction module 12, decision-making behavior risk assessment module 13, accompanying emergency risk assessment module 14, identification module 15, assessment report acquisition module 16. DETAILED DESCRIPTION

[0023] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below.

[0024] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings. The described embodiments should not be regarded as limiting the present application. All other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of this application.

[0025] In the following description, reference is made to "some embodiments", which describe a subset of all possible embodiments, but it is understood that "some embodiments" may be the same subset or different subsets of all possible embodiments, and may be combined with each other without conflict, and the terms "first\second" involved are merely to distinguish similar objects and do not represent a specific ordering of objects. The terms "including" and "having" and any variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, methods, products, or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those generally understood by technicians in the technical field of this application. The terms used herein are for the purpose of describing the embodiments of the present application only.

[0026] The present application embodiment provides a method and system for evaluating quantitative decision-making behavior in nuclear emergency situations, such as Figure 1 As shown, the method includes: Receive a decision-making behavior plan under a nuclear emergency, predict the decision-making behavior plan, and output multiple accompanying emergency events. Use the multiple accompanying emergency events as child nodes and the decision-making behavior plan under a nuclear emergency as a parent node to build a decision-making behavior prediction tree. Perform a risk assessment on the decision-making behavior plan and output a decision-making behavior risk index.

[0027] Receive a decision-making behavior plan under a nuclear emergency situation. The decision-making behavior plan refers to an emergency response action plan made by different emergency response units or managers to deal with nuclear accidents in nuclear accident emergency management. Each plan includes how to deal with accidents, how to evacuate people, how to mitigate the impact of accidents, etc. Based on the received decision-making behavior plan, emergency event prediction is performed. Each decision-making plan may bring a series of accompanying emergency events, and multiple accompanying emergency events with a higher probability of being sent after screening are obtained. Further, after completing the prediction of the accompanying emergency events, a decision-making behavior prediction tree is constructed. The prediction tree is a structured tool that can show the relationship between decision-making behavior and its accompanying emergency events. When constructing the decision-making behavior prediction tree, the current decision-making behavior plan is used as the parent node, indicating that this is the current action taken, and the predicted multiple accompanying emergency events are used as child nodes. These child nodes indicate the secondary emergency events that may occur under different decision-making plans. For example, if the decision-making behavior is to start the emergency shutdown of a nuclear power plant, possible accompanying emergency events (child nodes) include equipment overheating, radiation diffusion, etc., and then the construction of the decision-making behavior prediction tree is completed. Preferably, each accompanying emergency event can be further decomposed into smaller sub-events to form a complex prediction tree structure. Through this tree structure, the possible consequences of each decision behavior and the causal relationship between these consequences can be intuitively seen. Subsequently, the decision behavior plan is evaluated for risk and the decision behavior risk index is output.

[0028] The method provided in the embodiment of the present application also includes: collecting historical nuclear emergency event samples. Constructing an accompanying emergency event prediction model, and performing simulation prediction on the historical nuclear emergency event samples and the accompanying emergency event samples according to the accompanying emergency event prediction model to obtain the prediction accuracy. Predicting the decision-making behavior plan according to the accompanying emergency event prediction model, outputting an initial accompanying emergency event set and the accompanying probability of each initial accompanying emergency event. Screening initial accompanying emergency events with a probability greater than a preset accompanying probability, and outputting them as the multiple accompanying emergency events.

[0029] The decision-making behavior scheme is predicted and multiple accompanying emergency events are output, including: collecting historical nuclear emergency event samples, the nuclear emergency event samples are data records of nuclear accidents or emergency events that have occurred in history and the corresponding accompanying emergency events. These samples can be accident reports from the government or nuclear facilities, containing information such as the time, location, emergency response measures, and accident results of the accident. Subsequently, an accompanying emergency event prediction model is constructed, and the accompanying emergency event prediction model is used to predict the accompanying events that may occur under a specific decision-making behavior. According to the accompanying emergency event prediction model, the historical nuclear emergency event samples and the accompanying emergency event samples are simulated and predicted to obtain the prediction accuracy. The prediction accuracy is the ratio of the correct prediction result to the total prediction result. Further, according to the accompanying emergency event prediction model, the decision-making behavior scheme is predicted for accompanying emergency events, and an initial accompanying emergency event set is output. Each accompanying emergency event will be assigned an accompanying probability, that is, the possibility of the accompanying event occurring. The higher the value, the greater the possibility of the event occurring. For example, if the decision-making behavior is to shut down the reactor, the accompanying emergency event set may include a cooling system failure accompanying probability of 0.6, a radiation leakage accompanying probability of 0.4, etc. Finally, the initial accompanying emergency events with a probability greater than the preset accompanying probability are screened, and a preset accompanying probability threshold is set, for example, 0.5, which means that only accompanying emergency events with a probability of occurrence greater than 50% will be considered as high-probability events. When the initial accompanying emergency event is greater than the preset accompanying probability, it is considered to have a higher probability of occurrence, and then output as the multiple accompanying emergency events according to the screening results.

[0030] The method provided in the embodiment of the present application also includes: constructing an emergency scenario simulation model, analyzing the evolution process of the historical nuclear emergency event samples with the emergency scenario simulation model, identifying the accompanying emergency event samples of each historical nuclear emergency event sample, and the accompanying factors of each accompanying emergency event sample, wherein the accompanying factor is the magnitude of the probability of the event accompanying the occurrence. Training is performed based on the historical nuclear emergency event samples, the accompanying emergency event samples, and the accompanying factors of each accompanying emergency event sample, and if the prediction accuracy reaches a preset threshold, the accompanying emergency event prediction model is output.

[0031] Constructing a prediction model for accompanying emergency events, the method includes: constructing an emergency scenario simulation model, the emergency scenario simulation model is a mathematical model based on physical simulation, statistics or data-driven technology, and is used to simulate the scene evolution after the nuclear emergency event occurs. It will take into account the background conditions of the event (such as the operating status of the nuclear power plant, external environmental conditions, etc.), and predict the possible evolution path of the emergency event under these conditions. The evolution process of the historical nuclear emergency event sample is analyzed by the emergency scenario simulation model, including horizontal evolution analysis and vertical evolution analysis, wherein the horizontal evolution analysis is to simulate the diffusion scenario of the historical nuclear emergency event sample, such as the diffusion process of the nuclear emergency event, and analyze the propagation and expansion of radioactive substances, heat energy or harmful substances in space, and the vertical evolution analysis is to simulate the chain scenario of the historical nuclear emergency event sample, such as a mathematical model simulating the expansion behavior of radioactive substances or other emergency events in the air, soil or water. When constructing the emergency scenario simulation model, first collect and organize the historical nuclear emergency event data, including the initial state of the event, the accident handling process, the consequences and the impact of the surrounding environment. The data should include nuclear power plant design parameters, operation history, environmental conditions, etc. Through physical modeling, such as fluid dynamics, radioactive material diffusion model and statistical modeling, a simulation engine is established to simulate the evolution of emergency events. Historical events are parameterized, and the main parameters include the type, time, location, and meteorological conditions of the affected area.

[0032] Furthermore, the accompanying emergency event samples of each historical nuclear emergency event sample and the accompanying factors of each accompanying emergency event sample are identified according to the results of the evolution process analysis, wherein the accompanying factor is the magnitude of the probability of the event accompanying the occurrence. Finally, the neural network is trained according to the historical nuclear emergency event samples, the accompanying emergency event samples and the accompanying factors of each accompanying emergency event sample until the prediction accuracy of the model reaches a preset threshold, and the efficiency output accompanying emergency event prediction model is completed.

[0033] The method provided in the embodiment of the present application also includes: performing a zoning simulation on the decision-making behavior scheme to obtain multiple areas. Identifying the personnel protection rate and equipment protection rate of each of the multiple areas, outputting multiple personnel protection rates and multiple equipment protection rates. Calculating according to the multiple personnel protection rates and the multiple equipment protection rates, and outputting a decision-making behavior risk index.

[0034] The decision-making behavior scheme is subjected to risk assessment, and a decision-making behavior risk index is output. The method includes: performing a zoning simulation on the decision-making behavior scheme to obtain multiple areas. The goal of the zoning simulation is to divide the entire accident-affected area into several small areas so as to evaluate the risk of each area separately. Each area can be divided according to its physical location, function or degree of impact by the accident. It is divided according to specific functional areas, such as reactor area, control room area, cooling system area, surrounding community area, etc. After completing the zoning simulation, the personnel protection rate and equipment protection rate of each area in the multiple areas are identified. The personnel protection rate refers to the proportion of the number of people who can be protected from the impact of the accident in a certain area under a certain emergency decision-making behavior. The personnel protection rate obtains the final personnel protection rate mean under the corresponding emergency decision-making behavior of the corresponding area through nuclear emergency event big data. The equipment protection rate refers to the proportion of the number of equipment that can be protected from damage in a certain area under a certain emergency decision-making behavior. The equipment protection rate obtains the final equipment protection rate mean under the corresponding emergency decision-making behavior of the corresponding area through nuclear emergency event big data. Finally, according to the multiple personnel protection rates and the multiple equipment protection rates, calculations are performed. When performing the calculations, professional and technical personnel assign weights to each divided area according to the importance. Based on the weight assignment results, the multiple personnel protection rates and the multiple equipment protection rates are weighted and summed to output a decision-making behavior risk index. The decision-making behavior risk index comprehensively evaluates the impact of emergency decision-making behavior on personnel and equipment in nuclear emergency events, thereby providing a decision-making basis for subsequent decisions.

[0035] The multiple concomitant emergency events are respectively subjected to risk assessment, and multiple concomitant risk indicators are output. The decision behavior prediction tree is quantitatively labeled according to the decision behavior risk indicator and the multiple concomitant risk indicators, and the labeled decision behavior prediction tree is output. A decision behavior assessment report is generated by performing risk fitting on the labeled decision behavior prediction tree.

[0036] The risk of the multiple accompanying emergency events is evaluated respectively, and multiple accompanying risk indicators are output. Further, after all risk indicators are obtained, it is necessary to correspond these indicators to the prediction tree and quantify each node. The purpose of quantitative identification is to assign a specific risk value to each decision-making behavior and the accompanying emergency event, and output the decision-making behavior prediction tree after identification. Finally, by performing risk fitting on the decision-making behavior prediction tree after identification, a decision-making behavior evaluation report is generated, and the decision-making behavior evaluation report reflects the final risk parameter value of the decision-making behavior. When the risk value is higher, the corresponding decision risk is higher, and vice versa, the decision risk is lower. The technical problem that the nuclear emergency decision-making evaluation method in the prior art is difficult to perform dynamic risk evaluation on decision-making behavior, resulting in difficulty in improving the accuracy of emergency decision-making behavior evaluation and affecting the reliability of emergency decision-making is solved. By constructing a decision-making behavior prediction tree and combining the feedback adjustment mechanism of the number of real-time accompanying emergency events, the dynamic risk evaluation and optimization of accompanying events are realized, the accuracy of risk evaluation of decision-making behavior in nuclear emergency events is improved, and the technical effect of improving the reliability of emergency decision-making is improved.

[0037] The method provided in the embodiment of the present application further includes: collecting samples of accompanying emergency events and samples of accompanying loss indicators of the accompanying emergency events according to the event attributes of the multiple accompanying emergency events. Establishing an accompanying event risk assessment network according to the accompanying emergency event samples and the accompanying loss indicator samples. Performing risk assessment on each accompanying emergency event according to the accompanying event risk assessment network, and outputting multiple accompanying risk indicators.

[0038] The risk assessment of the multiple accompanying emergency events is respectively performed, and multiple accompanying risk indicators are output. The method includes: according to the event attributes of the multiple accompanying emergency events, the event attributes are the specific attribute categories of the multiple accompanying emergency events. Collecting samples of accompanying emergency events that are the same as the accompanying emergency events, and samples of accompanying loss indicators of the accompanying emergency event samples. The accompanying emergency event samples are event record samples with the same attributes as the multiple accompanying emergency events collected from historical nuclear emergency events. The accompanying loss indicator samples are loss data related to the accompanying emergency events. These loss data can be casualties, property losses, environmental pollution, etc. According to the accompanying emergency event samples and the accompanying loss indicator samples, an accompanying event risk assessment network is established. The accompanying event risk assessment network is constructed based on a neural network model, and the accompanying emergency event samples and the accompanying loss indicator samples are input into the model to supervise the model training until the output accuracy of the model meets the requirements, and an initial accompanying event risk assessment network is obtained. A risk score calculation layer is added to the initial accompanying event risk assessment network to obtain a final accompanying event risk assessment network. The computing layer in the incident risk assessment network is used to calculate the risk score of the incident loss indicators output by the initial incident risk assessment network. Different incident loss indicators have corresponding risk scoring parameters. After adding the risk scoring parameters corresponding to the incident loss indicators, multiple incident risk indicators are finally output.

[0039] The method provided in the embodiment of the present application also includes: dividing the hierarchy of the identified decision behavior prediction tree, outputting multiple levels of child nodes, including first-level child nodes, second-level child nodes, third-level child nodes, ... Nth-level child nodes. The multi-level child nodes are graded and multi-level grade indicators are output. Risk fitting is performed using the multi-level grade indicators as weights, the decision behavior risk indicators and the multiple accompanying risk indicators as inputs, and a risk fitting indicator is output. A decision behavior evaluation report is generated based on the risk fitting indicator.

[0040] By performing risk fitting on the identified decision behavior prediction tree, the method includes: dividing the identified decision behavior prediction tree according to the level, each level of the prediction tree corresponds to a first-level child node, and outputting multiple levels of child nodes, including first-level child nodes, second-level child nodes, third-level child nodes, ... N-th level child nodes, N is the same as the number of levels of the prediction tree. The multi-level child nodes are graded, and a risk level is assigned to the child nodes of each level according to the preset correspondence between the node level and the level. Each risk level corresponds to a specific level indicator, and a multi-level level indicator is output. Further, the multi-level level indicator is used as a weight, and the decision behavior risk indicator and the multiple accompanying risk indicators are used as input to perform risk fitting, that is, the multi-level level indicator is used as a weight, and the decision behavior risk indicator and the multiple accompanying risk indicators are weighted and summed to obtain the final risk fitting indicator. According to the risk fitting indicator, a decision behavior evaluation report is generated.

[0041] The method provided in the embodiment of the present application further includes: obtaining the real-time number of multiple accompanying emergency events, generating an adjustment coefficient according to the ratio of the real-time number to the preset number, and performing feedback adjustment according to the adjustment coefficient when risk fitting is performed on the identified decision behavior prediction tree.

[0042] Output multiple accompanying emergency events, the method also includes: obtaining the real-time number of multiple accompanying emergency events, the real-time number of the multiple accompanying emergency events is the output predicted number. According to the ratio of the real-time number to the preset number, that is, obtaining the ratio of the real-time number to the preset number, an adjustment coefficient is generated, and the preset number is the estimated number of accompanying emergency events preset under the current emergency situation. When risk fitting is performed on the identified decision behavior prediction tree, feedback adjustment is performed according to the adjustment coefficient, that is, the adjustment coefficient is multiplied by the risk fitting index, and the risk fitting index is optimized and adjusted to improve the accuracy of the risk fitting index acquisition.

[0043] In the above, refer to Figure 1 A method for evaluating quantitative decision-making behavior in a nuclear emergency situation according to an embodiment of the present invention is described in detail. Figure 2 A quantitative decision-making behavior evaluation system in a nuclear emergency situation according to an embodiment of the present invention is described.

[0044] According to an embodiment of the present invention, a quantitative decision-making behavior assessment system under nuclear emergency situations solves the technical problem that the nuclear emergency decision-making assessment method in the prior art is difficult to perform dynamic risk assessment on decision-making behavior, resulting in difficulty in improving the accuracy of emergency decision-making behavior assessment, and affecting the reliability of emergency decisions. By constructing a decision-making behavior prediction tree and combining a feedback adjustment mechanism of the number of real-time accompanying emergency events, dynamic risk assessment and optimization of accompanying events are achieved, the accuracy of risk assessment of decision-making behavior in nuclear emergency events is improved, and the technical effect of improving the reliability of emergency decisions is improved. A quantitative decision-making behavior assessment system under nuclear emergency situations includes: an accompanying event acquisition module 11, a behavior prediction tree construction module 12, a decision-making behavior risk assessment module 13, an accompanying emergency risk assessment module 14, an identification module 15, and an assessment report acquisition module 16.

[0045] The accompanying event acquisition module 11 is used to receive a decision-making behavior plan under a nuclear emergency situation, predict the decision-making behavior plan, and output a plurality of accompanying emergency events.

[0046] The behavior prediction tree construction module 12 is used to construct a decision behavior prediction tree by taking the multiple accompanying emergency events as child nodes and the decision behavior scheme under the nuclear emergency situation as a parent node.

[0047] The decision-making behavior risk assessment module 13 is used to conduct a risk assessment on the decision-making behavior scheme and output a decision-making behavior risk index.

[0048] The accompanying emergency risk assessment module 14 is used to perform risk assessment on the multiple accompanying emergency events respectively and output multiple accompanying risk indicators.

[0049] The identification module 15 is used to quantitatively identify the decision behavior prediction tree according to the decision behavior risk index and the multiple accompanying risk indexes, and output the identified decision behavior prediction tree.

[0050] The evaluation report acquisition module 16 is used to generate a decision behavior evaluation report by performing risk fitting on the identified decision behavior prediction tree.

[0051] The specific configuration of the accompanying event acquisition module 11 will be described in detail below. The accompanying event acquisition module 11 may further include: predicting the decision-making behavior scheme and outputting multiple accompanying emergency events, and the method includes: collecting historical nuclear emergency event samples. Constructing an accompanying emergency event prediction model, and performing simulation prediction on the historical nuclear emergency event samples and the accompanying emergency event samples according to the accompanying emergency event prediction model to obtain the prediction accuracy. Predicting the decision-making behavior scheme according to the accompanying emergency event prediction model, outputting an initial accompanying emergency event set, and the accompanying probability of each initial accompanying emergency event. Screening the initial accompanying emergency events that are greater than the preset accompanying probability, and outputting them as the multiple accompanying emergency events.

[0052] The specific configuration of the accompanying event acquisition module 11 will be described in detail below. The accompanying event acquisition module 11 further includes: constructing an accompanying emergency event prediction model, the method includes: constructing an emergency scenario simulation model, analyzing the evolution process of the historical nuclear emergency event samples with the emergency scenario simulation model, identifying the accompanying emergency event samples of each historical nuclear emergency event sample, and the accompanying factors of each accompanying emergency event sample, wherein the accompanying factor is the size of the probability of the event accompanying the occurrence. Training is performed based on the historical nuclear emergency event samples, the accompanying emergency event samples, and the accompanying factors of each accompanying emergency event sample. If the prediction accuracy reaches a preset threshold, the accompanying emergency event prediction model is output.

[0053] The specific configuration of the accompanying event acquisition module 11 will be described in detail below. The accompanying event acquisition module 11 may further include: analyzing the evolution process of the historical nuclear emergency event samples with the emergency scenario simulation model, including horizontal evolution analysis and vertical evolution analysis, wherein the horizontal evolution analysis is to simulate the diffusion scenario of the historical nuclear emergency event samples, and the vertical evolution analysis is to simulate the chain scenario of the historical nuclear emergency event samples.

[0054] The specific configuration of the decision-making behavior risk assessment module 13 will be described in detail below. The decision-making behavior risk assessment module 13 further includes: performing a risk assessment on the decision-making behavior scheme and outputting a decision-making behavior risk index, and the method includes: performing a partition simulation on the decision-making behavior scheme to obtain multiple areas. Identify the personnel protection rate and equipment protection rate of each of the multiple areas, and output multiple personnel protection rates and multiple equipment protection rates. Calculate according to the multiple personnel protection rates and the multiple equipment protection rates, and output the decision-making behavior risk index.

[0055] The specific configuration of the accompanying emergency risk assessment module 14 will be described in detail below. The accompanying emergency risk assessment module 14 further includes: performing risk assessments on the multiple accompanying emergency events respectively, and outputting multiple accompanying risk indicators, the method including: collecting accompanying emergency event samples and accompanying loss indicator samples of the accompanying emergency event samples according to the event attributes of the multiple accompanying emergency events. Establishing an accompanying event risk assessment network based on the accompanying emergency event samples and the accompanying loss indicator samples. Performing risk assessment on each accompanying emergency event according to the accompanying event risk assessment network, and outputting multiple accompanying risk indicators.

[0056] Below, the specific configuration of the evaluation report acquisition module 16 will be described in detail. The evaluation report acquisition module 16 further includes: by performing risk fitting on the identified decision behavior prediction tree, the method includes: dividing the hierarchy of the identified decision behavior prediction tree, and outputting multiple levels of child nodes, including first-level child nodes, second-level child nodes, third-level child nodes, ... N-th level child nodes. Performing level identification on the multi-level child nodes, and outputting multi-level level indicators. Using the multi-level level indicator as a weight, taking the decision behavior risk indicator and the multiple accompanying risk indicators as input, risk fitting is performed, and a risk fitting indicator is output. Based on the risk fitting indicator, a decision behavior evaluation report is generated.

[0057] The specific configuration of the evaluation report acquisition module 16 will be described in detail below. The evaluation report acquisition module 16 further includes: outputting multiple accompanying emergency events, and the method also includes: obtaining the real-time number of multiple accompanying emergency events. According to the ratio of the real-time number to the preset number, an adjustment coefficient is generated, and when the risk fitting is performed on the identified decision behavior prediction tree, feedback adjustment is performed according to the adjustment coefficient.

[0058] A quantitative decision-making behavior evaluation system under nuclear emergency situations provided by an embodiment of the present invention can execute a quantitative decision-making behavior evaluation method under nuclear emergency situations provided by any embodiment of the present invention, and has functional modules and beneficial effects corresponding to the execution method.

[0059] Although the present application makes various references to certain modules in the system according to the embodiments of the present application, any number of different modules can be used and run on the user terminal and / or the server, and the various units and modules included are only divided according to functional logic, but are not limited to the above divisions, as long as the corresponding functions can be achieved. In addition, the specific names of the functional units are only for the convenience of distinguishing from each other, and are not used to limit the scope of protection of the present invention.

[0060] The above specific implementations do not constitute a limitation on the protection scope of this application. It should be understood by those skilled in the art that various modifications, combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of this application should be included in the protection scope of this application.

Claims

1. A method for evaluating quantitative decision-making behavior in nuclear emergency situations, characterized in that: The method comprises: receiving a decision-making behavior plan under a nuclear emergency situation, predicting the decision-making behavior plan, and outputting a plurality of accompanying emergency events; The multiple accompanying emergency events are used as child nodes, and the decision-making behavior scheme under the nuclear emergency situation is used as a parent node to construct a decision-making behavior prediction tree; Conduct risk assessment on the decision-making behavior plan and output a decision-making behavior risk indicator; Perform risk assessment on the multiple accompanying emergency events respectively, and output multiple accompanying risk indicators; Quantitatively marking the decision behavior prediction tree according to the decision behavior risk index and the multiple accompanying risk indexes, and outputting the marked decision behavior prediction tree; By performing risk fitting on the identified decision behavior prediction tree, a decision behavior evaluation report is generated.

2. The method according to claim 1, characterized in that The decision-making behavior scheme is predicted and multiple accompanying emergency events are output, and the method includes: Collect samples of historical nuclear emergencies; Constructing a concomitant emergency event prediction model, and performing simulation prediction on the historical nuclear emergency event samples and the concomitant emergency event samples according to the concomitant emergency event prediction model to obtain a prediction accuracy rate; Predicting the decision-making behavior plan according to the accompanying emergency event prediction model, outputting an initial accompanying emergency event set and an accompanying probability of each initial accompanying emergency event; Initial accompanying emergency events with a probability greater than a preset accompanying probability are screened and output as the multiple accompanying emergency events.

3. The method according to claim 2, characterized in that Constructing a prediction model for accompanying emergency events, the method includes: Constructing an emergency scenario simulation model, analyzing the evolution process of the historical nuclear emergency event samples with the emergency scenario simulation model, identifying the accompanying emergency event samples of each historical nuclear emergency event sample, and the accompanying factors of each accompanying emergency event sample, wherein the accompanying factors are the magnitude of the accompanying probability of the event; Training is performed based on the historical nuclear emergency event samples, the accompanying emergency event samples and the accompanying factors of each accompanying emergency event sample. If the prediction accuracy reaches a preset threshold, an accompanying emergency event prediction model is output.

4. The method according to claim 3, characterized in that The emergency scenario simulation model is used to analyze the evolution process of the historical nuclear emergency event samples, including horizontal evolution analysis and vertical evolution analysis, wherein the horizontal evolution analysis is to simulate the diffusion scenario of the historical nuclear emergency event samples, and the vertical evolution analysis is to simulate the chain scenario of the historical nuclear emergency event samples.

5. The method according to claim 1, characterized in that Performing a risk assessment on the decision-making behavior plan and outputting a decision-making behavior risk index, the method includes: Performing a partition simulation on the decision-making behavior scheme to obtain multiple regions; Identify a personnel protection rate and a device protection rate in each of the plurality of regions, and output a plurality of personnel protection rates and a plurality of device protection rates; Calculation is performed according to the multiple personnel protection rates and the multiple equipment protection rates, and a decision-making behavior risk index is output.

6. The method according to claim 1, characterized in that Performing risk assessment on the multiple accompanying emergency events respectively and outputting multiple accompanying risk indicators, the method includes: According to the event attributes of the plurality of accompanying emergency events, collecting accompanying emergency event samples and accompanying loss indicator samples of the accompanying emergency event samples; Establishing an accompanying event risk assessment network based on the accompanying emergency event samples and the accompanying loss index samples; The risk assessment network for the accompanying events is used to assess the risk of each accompanying emergency event, and a plurality of accompanying risk indicators are output.

7. The method according to claim 1, characterized in that The risk fitting is performed on the decision behavior prediction tree after identification, and the method includes: According to the level of the decision behavior prediction tree after identification, multiple levels of child nodes are output, including first-level child nodes, second-level child nodes, third-level child nodes, ... N-th-level child nodes; Performing level identification on the multi-level sub-nodes and outputting multi-level level indicators; Taking the multi-level index as weight, taking the decision-making behavior risk index and the multiple accompanying risk indexes as input, performing risk fitting, and outputting a risk fitting index; A decision-making behavior assessment report is generated based on the risk fitting index.

8. The method according to claim 7, characterized in that Outputting a plurality of accompanying emergency events, the method further comprises: Get real-time numbers of multiple accompanying emergency events; An adjustment coefficient is generated according to the ratio of the real-time quantity to the preset quantity, and when risk fitting is performed on the identified decision behavior prediction tree, feedback adjustment is performed according to the adjustment coefficient.

9. A quantitative decision-making behavior evaluation system for nuclear emergency situations, characterized in that: The system comprises: An accompanying event acquisition module is used to receive a decision-making behavior plan under a nuclear emergency situation, predict the decision-making behavior plan, and output a plurality of accompanying emergency events; A behavior prediction tree construction module is used to construct a decision behavior prediction tree by taking the multiple accompanying emergency events as child nodes and the decision behavior scheme under the nuclear emergency situation as a parent node; A decision-making behavior risk assessment module is used to conduct a risk assessment on the decision-making behavior scheme and output a decision-making behavior risk index; An accompanying emergency risk assessment module is used to conduct risk assessments on the multiple accompanying emergency events respectively and output multiple accompanying risk indicators; An identification module, used for quantitatively identifying the decision behavior prediction tree according to the decision behavior risk index and the multiple accompanying risk indexes, and outputting the identified decision behavior prediction tree; The evaluation report acquisition module is used to generate a decision behavior evaluation report by performing risk fitting on the identified decision behavior prediction tree.

Images