Nuclear accident emergency action planning system based on multi-source heterogeneous data processing

Abstract

The invention relates to the technical field of nuclear accident emergency processing, and discloses a nuclear accident emergency action planning system based on multi-source heterogeneous data processing, and the system comprises the steps: obtaining a geographic map of a nuclear accident location, and generating a directed graph used for representing a spatial relationship according to the geographic map and based on a graph theory method; calculating the sparsity of each rescue node in the directed graph, screening out a plurality of sparse rescue nodes in the directed graph according to the sparsity, and simplifying the directed graph according to the sparse rescue nodes to form a new directed graph; in the new directed graph, connecting directed edges between the accident source node and each rescue node to form a plurality of rescue paths; acquiring an optimal rescue path from the plurality of rescue paths by using a pre-configured genetic algorithm, and inputting the optimal rescue path for feedback; according to the method, redundancy of the planned rescue path can be avoided, and in a nuclear accident rescue scene, the safety of rescue task personnel is guaranteed while the rescue efficiency is guaranteed.

Description

Technical Field

[0001] The present invention relates to the technical field of nuclear accident emergency handling, and more specifically, the present invention relates to a nuclear accident emergency operation planning system based on multi-source heterogeneous data processing. Background Art

[0002] The occurrence of a nuclear accident is usually accompanied by the large-scale diffusion of radioactive substances, posing a serious threat to the surrounding environment and the safety of personnel; during the emergency response process, the rapid planning and optimization of the rescue path is the core issue; however, due to the uneven distribution of rescue nodes, as well as the factors such as the sparsity degree of nodes and the spatial topological structure in path planning not being fully considered, existing methods often have difficulty providing reliable solutions that adapt to the actual environment.

[0003] In existing technology for emergency path planning, it mainly relies on fixed geographical maps and simple path selection rules, ignoring the complex spatial relationships between nodes and the impact of the importance of different nodes on the overall planning results; for example, sparse nodes may become bottlenecks in path planning due to limited connections with other nodes, resulting in redundant paths or lack of flexibility; at the same time, existing methods mostly focus on path length or a single goal, failing to comprehensively consider the radiation dose, distance, and structural attributes of the path, and it is easy to have situations where the planning results are not applicable in dynamic rescue requirements. Further, it is difficult to ensure the safety of the personnel performing the rescue tasks as much as possible while ensuring the rescue efficiency. Summary of the Invention

[0004] In order to overcome the above-mentioned defects of the existing technology, an embodiment of the present invention provides a nuclear accident emergency operation planning system based on multi-source heterogeneous data processing.

[0005] To achieve the above object, the present invention provides the following technical solutions:

[0006] A nuclear accident emergency operation planning system based on multi-source heterogeneous data processing, the system includes:

[0007] A data processing module, configured to obtain a geographical map of the location of the nuclear accident, and generate a directed graph for representing spatial relationships based on the geographical map and using graph theory methods. The directed graph includes multiple directed edges and multiple nodes, and the nodes are divided into one accident source node, multiple rescue nodes, and multiple intermediate nodes;

[0008] A data update module, configured to calculate the sparsity of each rescue node in the directed graph, screen out multiple sparse rescue nodes in the directed graph according to the sparsity, and streamline the directed graph according to the sparse rescue nodes to form a new directed graph;

[0009] A path generation module, configured to connect the directed edges between the accident source node and each rescue node in the new directed graph to form multiple rescue paths;

[0010] An action planning module, configured to obtain the optimal rescue path from multiple rescue paths by using a pre-configured genetic algorithm, and input the optimal rescue path for feedback.

[0011] Further, calculating the sparsity of each rescue node in the directed graph includes:

[0012] Traverse the directed graph, record each rescue node and the neighbor set of each rescue node, where the neighbor set contains neighbor rescue nodes directly adjacent to the rescue node, and the number of neighbor rescue nodes is N(v);

[0013] Obtain the number of directed edges E(v) directly connected between the rescue node and each neighbor rescue node, and substitute the number of adjacent rescue nodes N(v) and the number of directed edges E(v) into the pre-constructed calculation model of the local clustering coefficient C(v) to calculate the local clustering coefficient C(v) of each rescue node;

[0014] Among them, the expression of the calculation model of the local clustering coefficient C(v) is:

[0015]

[0016] In the formula: μ represents the neighbor rescue node directly connected to the rescue node, ∑ μ∈ N(v) means counting once for each neighbor rescue node μ of the rescue node;

[0017] Substitute the local clustering coefficient C(v) of the rescue node into the sparsity calculation formula respectively: obtain the sparsity S(v) of each rescue node;

[0018] Among them, the calculation formula of the sparsity S(v) of each rescue node is as follows:

[0019]

[0020] In the formula: e represents the natural constant.

[0021] Further, screening out multiple sparse rescue nodes in the directed graph includes:

[0022] Compare the sparsity S(v) with a preset sparsity threshold S threshould for comparison;

[0023] If S(v)≥S threshould , then determine that the corresponding rescue node is a sparse rescue node;

[0024] If S(v)<S threshould , then determine that the corresponding rescue node is a non-sparse rescue node;

[0025] Count all rescue nodes where S(V) ≥ S threshould to obtain multiple sparse rescue nodes.

[0026] Further, the reduction of the directed graph according to the sparse rescue nodes includes:

[0027] Mark all sparse rescue nodes in the directed graph;

[0028] Remove all sparse rescue nodes from the directed graph and update the spatial relationship between the remaining nodes to obtain a new directed graph.

[0029] Further, the obtaining of the optimal rescue path from multiple rescue paths includes:

[0030] a1: Initialize the population: Generate an original population according to multiple rescue paths. The original population contains P individuals, and each individual represents a rescue path. P is an integer greater than zero;

[0031] a2: Fitness evaluation: For each individual, obtain the cumulative dose, path length, and cumulative sparsity of each rescue path; input the cumulative dose, path length, and cumulative sparsity into a pre-constructed fitness function to calculate the fitness of each individual;

[0032] a3: Selection: Use the roulette wheel method to select two individuals with high fitness in the original population as the male parent and the female parent;

[0033] a4: Crossover: Perform a crossover operation on the male parent and the female parent to generate new individuals;

[0034] a5: Mutation: Perform a mutation operation on the new individuals to obtain W new individuals. Combine the W new individuals into a new population, replace the original population with the new population, and return to step a2. W is an integer greater than zero;

[0035] a6: Repeat the above steps a2 - a5 until the fitness of the individuals in the original population or the new population is greater than or equal to a preset fitness threshold, or the number of iterations is greater than or equal to a preset maximum iteration threshold, and output the rescue path represented by the corresponding individual as the optimal rescue path.

[0036] Further, the acquisition logic of the cumulative dose is as follows:

[0037] At the time of a nuclear accident, obtain the on-site environmental data of the location of the nuclear accident and the on-site accident data of the accident source node within the location of the nuclear accident;

[0038] Input the on-site environmental data and the on-site accident data into a preset Gaussian plume model to obtain the concentration distribution of the radionuclides emitted by the nuclear accident. The concentration distribution refers to the concentration of the radionuclides at each node in the directed graph;

[0039] Obtain the basic data of the radionuclide, and calculate the dose rate at each node in the rescue path according to the basic data and concentration distribution of the radionuclide, and calculate the cumulative dose of the rescue path according to the dose rate.

[0040] Furthermore, the calculation formula of the dose rate is as follows:

[0041]

[0042] In the formula: S r The calculation formula of is as follows:

[0043] S r = C r × λ r × Y r ;

[0044] In the formula: S r is the source strength of the r-th radionuclide in the node; k r is the dose conversion factor of the r-th radionuclide; λ r is the decay constant of the r-th radionuclide in the node, and its calculation formula is: In the formula: T 1 / 2 is the half-life of the radionuclide; Y r is the radiation particle release yield of the r-th radionuclide in the node;

[0045] Among them, the calculation formula of the cumulative dose is as follows:

[0046]

[0047] In the formula: Δd is the path distance of a single node in the rescue path; D i is the dose rate of the i-th node; Δt is the residence time; Δd is the spatial distance of the i-th node on the path; v is the average speed of the personnel.

[0048] Furthermore, the calculation formula of the pre-constructed fitness function is: In the formula: Fitness is the fitness, D total is the cumulative dose, L total is the path length, S(v) total is the cumulative sparsity, ω1, ω2 and ω3 are adjustment factors greater than zero, ω1 > ω2 > ω3, D0, L0 and S(v)0 are the reference values of the cumulative dose, path length and cumulative sparsity respectively.

[0049] A method for nuclear accident emergency operation planning based on multi-source heterogeneous data processing, which is implemented based on the nuclear accident emergency operation planning system based on multi-source heterogeneous data processing described in any one of the above, the method includes:

[0050] Obtain the geographical map of the location of the nuclear accident, and generate a directed graph for representing spatial relationships based on the geographical map and the graph theory method. The directed graph contains multiple directed edges and multiple nodes, and the nodes are divided into an accident source node, multiple rescue nodes and multiple intermediate nodes;

[0051] Calculate the sparsity of each rescue node in the directed graph, screen out multiple sparse rescue nodes in the directed graph according to the sparsity, and streamline the directed graph according to the sparse rescue nodes to form a new directed graph;

[0052] In the new directed graph, connect the directed edges between the accident source node and each rescue node to form multiple rescue paths;

[0053] Use the pre-configured genetic algorithm to obtain the best rescue path from multiple rescue paths and input the best rescue path for feedback.

[0054] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0055] The present application discloses a nuclear accident emergency operation planning system based on multi-source heterogeneous data processing, including: obtaining a geographical map of the location of the nuclear accident, and generating a directed graph representing spatial relationships based on the geographical map and using graph theory methods; calculating the sparsity of each rescue node in the directed graph, screening out multiple sparse rescue nodes in the directed graph according to the sparsity, and streamlining the directed graph according to the sparse rescue nodes to form a new directed graph; in the new directed graph, connecting the directed edges between the accident source node and each rescue node to form multiple rescue paths; using a pre-configured genetic algorithm to obtain the best rescue path from the multiple rescue paths and inputting the best rescue path for feedback; based on the above technical features, the present invention effectively reduces computational redundancy and optimizes the overall structure of the graph by calculating the sparsity of rescue nodes and streamlining the directed graph, thereby significantly reducing the complexity of path planning, while retaining key network characteristics and ensuring the connectivity and reachability of the graph structure; secondly, the present invention dynamically optimizes the rescue path using a pre-configured genetic algorithm, and can quickly generate the optimal rescue path by comprehensively considering multi-dimensional factors such as path length, cumulative radiation dose, and sparsity, enabling the system to effectively avoid problems such as path unavailability and significantly improving the adaptability and fault tolerance of the planning; in addition, by combining the calculation of the concentration distribution of radionuclides and the radiation dose assessment of the rescue path in path planning, through the effective integration of multi-source data, the comprehensive quantification and optimization of path safety are realized; while ensuring the rescue efficiency, the radiation exposure risk of rescue personnel is minimized to further enhance the practical feasibility of the planning scheme. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] Figure 1 It is a module structure diagram of a nuclear accident emergency operation planning system based on multi-source heterogeneous data processing provided by the present invention;

[0057] Figure 2 It is a flowchart of a nuclear accident emergency operation planning method based on multi-source heterogeneous data processing provided by the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0058] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0059] Embodiment 1

[0060] Please refer to Figure 1 as shown, this embodiment discloses and provides a nuclear accident emergency operation planning system based on multi-source heterogeneous data processing. The system includes:

[0061] A data processing module 101 is configured to obtain a geographical map of the location of a nuclear accident, generate a directed graph representing spatial relationships based on the geographical map and using graph theory methods. The directed graph includes multiple directed edges and multiple nodes, and the nodes are divided into one accident source node, multiple rescue nodes, and multiple intermediate nodes;

[0062] It should be understood that there are several geographical maps, all of which are pre-stored in the system database. Each geographical map is used to reveal relevant geographical data about nuclear sites (such as nuclear power plants, etc.) and their surroundings, including but not limited to road networks, terrain features, building distributions, rescue node locations, and the specific location of the nuclear site (where the nuclear accident occurs). Among them, an intermediate node refers to a node in the directed graph that is located between the accident source node and the rescue nodes. They are neither the accident source node (the place where the accident occurs) nor the direct rescue nodes (the end points of the rescue tasks), but they play a bridging or transitional role in path connection and optimization. For example, the intermediate node is an intersection in the road network;

[0063] It should be noted that generating a directed graph representing spatial relationships based on the geographical map and using graph theory methods is a prior art. The generation process is as follows: According to the specific location of the nuclear accident, mark it as the accident source node; mark the rescue emergency sites related to the nuclear accident in the geographical map, and define the locations of these rescue emergency sites as rescue nodes; extract the key intersections and turning points in the road network, and use these points as intermediate nodes; establish edges between the nodes to represent the spatial connection relationship; assign directions to each edge according to the actual situation to make it directional, indicating the path accessibility from one node to another node. At the same time, assign weights and attributes to each edge according to information such as the actual length of the path; generate the topological structure of the directed graph according to the connection relationships of all nodes and edges to ensure the connectivity and reachability of the graph.

[0064] A data update module 102 is configured to calculate the sparsity of each rescue node in the directed graph, screen out multiple sparse rescue nodes in the directed graph according to the sparsity, and streamline the directed graph according to the sparse rescue nodes to form a new directed graph;

[0065] In implementation, calculating the sparsity of each rescue node in the directed graph includes:

[0066] Traverse the directed graph, record each rescue node and the neighbor set of each rescue node. The neighbor set includes neighbor rescue nodes directly adjacent to the rescue node, and the number of neighbor rescue nodes is N(v);

[0067] It should be understood that the neighbor set refers to the set of all (original) rescue nodes directly connected to a specific (original) rescue node;

[0068] Obtain the number of directed edges E(v) directly connected between the rescue node and each neighbor rescue node, substitute the number of adjacent rescue nodes N(v) and the number of directed edges E(v) into the pre-constructed calculation model of the local clustering coefficient C(v), and calculate the local clustering coefficient C(v) of each rescue node;

[0069] Among them, the expression of the calculation model of the local clustering coefficient C(v) is:

[0070]

[0071] In the formula: μ represents the neighbor rescue node directly connected to the rescue node, ∑ μ∈ N(v) means counting once for each neighbor rescue node μ of the rescue node, in other words, summing up the number of these neighbor rescue nodes;

[0072] Substitute the local clustering coefficient C(v) of the rescue node into the sparsity calculation formula respectively: Obtain the sparsity S(v) of each rescue node;

[0073] Among them, the calculation formula of the sparsity S(v) of each rescue node is as follows:

[0074]

[0075] In the formula: e represents the natural constant;

[0076] In implementation, the screening out of multiple sparse rescue nodes in the directed graph includes:

[0077] Compare the sparsity S(V) with the preset sparsity threshold S threshould ;

[0078] If S(V)≥S threshould , then determine that the corresponding rescue node is a sparse rescue node;

[0079] If S(v)<S threshould , then determine that the corresponding rescue node is a non-sparse rescue node;

[0080] Count all rescue nodes with S(v)≥S threshould , and obtain multiple sparse rescue nodes;

[0081] It can be understood that: the larger the sparsity S(v) is, the lower the local clustering coefficient C(v) of the corresponding rescue node means, which further indicates that the number of connections between the corresponding rescue node and its directly connected neighbor rescue nodes is smaller. Therefore, it shows that the rescue node is relatively isolated in the directed graph; on the contrary, the smaller the sparsity S(V) is, the larger the local clustering coefficient C(v) of the corresponding rescue node means, which further indicates that the number of connections between the corresponding rescue node and its directly connected neighbor rescue nodes is larger. Therefore, it shows that the rescue node is relatively close to other rescue nodes in the directed graph;

[0082] Specifically, the refinement of the directed graph according to sparse rescue nodes includes:

[0083] Mark all sparse rescue nodes in the directed graph;

[0084] Remove all sparse rescue nodes from the directed graph and update the spatial relationship between the remaining nodes to obtain a new directed graph;

[0085] It should be understood that: after removing all sparse rescue nodes from the directed graph, there will be some directed edges that are not connected to any node. Therefore, at the same time, when updating the spatial relationship between the remaining nodes, these directed edges that are not connected to any node will also be removed;

[0086] Furthermore, it can be understood that: by obtaining the magnitude of the sparsity of rescue nodes, it is beneficial to provide important data support for subsequent refinement of the directed graph; in addition, by refining the directed graph, the computational complexity can be reduced while retaining key structural information. Further, path planning and selection are performed based on the refined directed graph, so that in actual situations, the safety and efficiency of rescue tasks can be improved to prevent the situation where when the planned rescue path becomes unavailable in actual situations (such as sudden road damage or road blockage, etc.), rescue personnel cannot find an alternative path, thereby effectively improving the fault tolerance of the optimal rescue path in actual situations, and further being able to ensure the safety of nuclear accident rescue personnel as much as possible.

[0087] The path generation module 103 is used to connect the directed edges between the accident source node and each rescue node in the new directed graph to form multiple rescue paths;

[0088] Among them, each rescue path includes an accident source node, a rescue node, multiple intermediate nodes, and multiple directed edges;

[0089] It should be understood that: in the process of connecting the directed edges from the accident source node to each rescue node, the system takes the rescue node as the starting point, the accident source node as the end point, and the intermediate nodes as transfer points. Therefore, when taking the rescue node as the starting point, connect the directed edge between the starting point and the intermediate node, the directed edge between the intermediate nodes until the connection of the directed edge between the intermediate node and the accident source node is completed, then a complete rescue path is formed.

[0090] The action planning module 104 is used to obtain the best rescue path from multiple rescue paths by using a pre-configured genetic algorithm and input the best rescue path for feedback;

[0091] In implementation, obtaining the best rescue path from multiple rescue paths includes:

[0092] a1: Initialize the population: Generate the original population according to multiple rescue paths. The original population contains P individuals, and each individual represents a rescue path, where P is an integer greater than zero;

[0093] a2: Fitness evaluation: For each individual (i.e., each rescue path in the original population), obtain the cumulative dose, path length, and cumulative sparsity of each rescue path; input the cumulative dose, path length, and cumulative sparsity into a pre-constructed fitness function to calculate the fitness of each individual;

[0094] The cumulative dose refers to the sum of the dose rates of all nodes along the rescue path multiplied by the residence time (path segment time), which reflects the total radiation dose received by personnel in the entire rescue path;

[0095] In implementation, the acquisition logic of the cumulative dose is as follows:

[0096] At the time of a nuclear accident, obtain the on-site environmental data of the location of the nuclear accident and the on-site accident data of the accident source node within the location of the nuclear accident;

[0097] Among them, the on-site environmental data includes but is not limited to temperature value, humidity value, wind speed, and air pressure, etc.; the on-site accident data includes but is not limited to release rate and emission height, etc.;

[0098] It should be noted that: the on-site environmental data and on-site accident data are collected based on various sensors arranged in advance, and various sensors include but are not limited to wind speed sensors, temperature and humidity sensors, ranging sensors, and gas sensors, etc.;

[0099] Input the on-site environmental data and on-site accident data into a preset Gaussian plume model to obtain the concentration distribution of the radionuclides emitted by the nuclear accident, and the concentration distribution refers to the concentration of the radionuclides at each node in the directed graph;

[0100] Among them, the expression of the Gaussian plume model is as follows:

[0101]

[0102] In the formula: C r is the concentration of the radionuclide at the position (x, y, z); (x, y, z) represents the node coordinates; Q is the emission rate of the radionuclide; η is the wind speed; σ y and σ z are diffusion coefficients (determined by atmospheric stability); H is the height of the emission source;

[0103] Obtain the basic data of the radionuclide, and calculate the dose rate at each node in the rescue path according to the basic data of the radionuclide and the concentration distribution, and calculate the cumulative dose of the rescue path according to the dose rate; the basic data includes but is not limited to the type of radionuclide and the radiation particle release yield, etc.;

[0104] Among them, the calculation formula of the dose rate is as follows:

[0105]

[0106] In the formula: S r The calculation formula of is as follows:

[0107] S r = C r × λ r × Y r ;

[0108] In the formula: S r is the source strength of the r-th radionuclide in the node, with the unit of becquerel per second (Bq / s), indicating the number of radiation particles released per second; k r is the dose conversion factor of the r-th radionuclide, with the unit of millisievert per becquerel (msv / Bq), which is preset by technicians after experiments; λ r is the decay constant of the r-th radionuclide in the node, and its calculation formula is: In the formula: T 1 / 2 is the half-life of the radionuclide, with the unit of second, which refers to the time required for the number of nuclides to be reduced to half of the initial number during the radioactive decay process of the nucleus of a radionuclide, and it is preset by technicians after experiments; Y r is the radiation particle release yield of the r-th radionuclide in the node, with the unit of particle / decay, indicating the number of neutrons, gamma photons or other particles released per decay of the radionuclide;

[0109] Among them, the calculation formula of the cumulative dose is as follows:

[0110]

[0111] Where: Δd is the path distance of a single node in the rescue path; D i is the dose rate of the i-th node, in millisieverts per hour (msv / h), indicating the radiation dose received per unit time within the node; Δt is the residence time, representing the time spent by the personnel when passing through the i-th node on the path, which is artificially set in advance by the technical personnel after the experiment; Δd is the spatial distance of the i-th node on the path, that is, the spatial span of each node, which is artificially set in advance by the technical personnel after the experiment; v is the average speed of the personnel, in meters per second (m / s), which is artificially set in advance by the technical personnel after the experiment;

[0112] It should be noted that: the path length of each rescue path is obtained by accumulating the lengths of all directed edges in the rescue path; correspondingly, the cumulative sparsity of each rescue path is obtained by accumulating the sparsities of all nodes in the rescue path. The calculation process of the sparsity of each node refers to the relevant content above and will not be repeated here;

[0113] Among them, the calculation formula of the pre-constructed fitness function is: Where: Fitness is the fitness, D total is the cumulative dose, L total is the path length, S(v) total is the cumulative sparsity, ω1, ω2, and ω3 are adjustment factors greater than zero, ω1>ω2>ω3, and D0, L0, and S(v)0 are the reference values of the cumulative dose, path length, and cumulative sparsity respectively;

[0114] a3: Selection: Use the roulette wheel method to select two individuals with high fitness in the original population as the father and mother;

[0115] The roulette wheel method is a commonly used selection method, which is used in genetic algorithms to select individuals with higher fitness to enter the next generation; it simulates the process of roulette, and each individual obtains the corresponding "roulette" area according to its fitness; the higher the fitness of an individual, the larger its corresponding area and the higher the probability of being selected;

[0116] a4: Crossover: Perform a crossover operation on the father and mother to generate new individuals;

[0117] It should be noted that: the crossover operation on the father and mother is implemented based on the crossover operation. The crossover operation includes but is not limited to one of single-point crossover, uniform crossover, or order crossover, etc.;

[0118] a5: Mutation: Perform mutation operation on the new individuals to obtain W new individuals, combine the W new individuals into a new population, and replace the original population with the new population, and return to step a2, W is an integer greater than zero;

[0119] In genetic algorithms, mutation operations are used to introduce genetic diversity and prevent the algorithm from falling into a local optimum. The mutation operation on new individuals is implemented by uniform mutation or Gaussian mutation.

[0120] a6: Repeat steps a2 to a5 above until the fitness of the individuals in the original population or the new population is greater than or equal to the preset fitness threshold, or the number of iterations is greater than or equal to the preset maximum number of iterations threshold, and output the rescue path represented by the corresponding individual as the optimal rescue path;

[0121] For example: Assume that the maximum number of iterations is 100, and record the individual with the highest fitness in the current population and its fitness value after each iteration; if it is found that the fitness value has not changed significantly in a certain generation, it is considered that the convergence condition is met, the iteration is stopped, and the rescue path represented by the corresponding individual is output as the optimal rescue path;

[0122] The accuracy and reliability of path planning have been improved through scientific design. The solution constructs a directed graph based on the geographic map to accurately depict the spatial relationship between the accident source, rescue nodes, and intermediate nodes. Combined with the analysis of node sparsity, the graph structure is optimized, the computational complexity caused by redundant information is reduced, and key network characteristics are retained, laying the foundation for planning more efficient rescue paths.

[0123] In addition, the solution comprehensively considers multi-dimensional factors such as path length, cumulative dose and sparsity, and introduces genetic algorithms to achieve dynamic optimization, effectively balancing the safety and time cost of the rescue path. In a dynamic environment, the system can adjust the graph structure and path planning results based on real-time data to ensure the adaptability and execution of the planning scheme, thereby providing more efficient support in sudden nuclear accident scenarios.

[0124] On the whole, this plan not only improves the scientific nature of emergency planning, but also enhances the fault tolerance and adaptability in actual operations, providing a robust and effective technical support for nuclear accident emergency rescue tasks; this method reflects the systematic nature of the planning process and its high degree of fit with actual needs, significantly optimizing the overall efficiency and safety of nuclear accident emergency operations.

[0125] Example 2

[0126] See also Figure 2 As shown, this embodiment discloses a nuclear accident emergency action planning method based on multi-source heterogeneous data processing, the method comprising:

[0127] S201: Obtain the geographical map of the location of the nuclear accident, and generate a directed graph for representing spatial relationships based on the geographical map and the graph theory method. The directed graph contains multiple directed edges and multiple nodes, and the nodes are divided into one accident source node, multiple rescue nodes, and multiple intermediate nodes;

[0128] S202: Calculate the sparsity of each rescue node in the directed graph, screen out multiple sparse rescue nodes in the directed graph according to the sparsity, and streamline the directed graph according to the sparse rescue nodes to form a new directed graph;

[0129] S203: In the new directed graph, connect the directed edges between the accident source node and each rescue node to form multiple rescue paths;

[0130] S204: Use the pre-configured genetic algorithm to obtain the best rescue path from multiple rescue paths and input the best rescue path for feedback.

[0131] The above formulas are all calculated by taking the numerical values after dimensionless. The formula is a formula obtained by collecting a large amount of data for software simulation to get the closest to the real situation. The selection of the preset parameters, weights, and thresholds in the formula is set by those skilled in the art according to the actual situation.

[0132] The above embodiments can be implemented in whole or in part by software, hardware, firmware, or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on the computer, the processes or functions described in the embodiments of the present invention are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via a wired network or a wireless network. The computer-readable storage medium can be any available medium that the computer can access or a data storage device such as a server or a data center that contains one or more sets of available media. The available media can be magnetic media (such as floppy disks, hard disks, magnetic tapes), optical media (such as DVDs), or semiconductor media. The semiconductor media can be a solid-state drive.

[0133] Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed in the present invention can be implemented by electronic hardware or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present invention.

[0134] Those skilled in the art can clearly understand that for the convenience and conciseness of description, the specific working processes of the systems, devices, and units described above can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein.

[0135] In several embodiments provided by the present invention, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is only one type, and there can be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces. The indirect couplings or communication connections of the devices or units can be in electrical, mechanical, or other forms.

[0136] The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0137] In addition, the functional units in each embodiment of the present invention can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit.

[0138] As mentioned above, the above is only the specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of changes or substitutions, which should all be covered by the protection scope of the present invention. Therefore, the protection scope of the present invention should be subject to the protection scope of the claims.

[0139] Finally: The above is only the preferred embodiment of the present invention and is not used to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention should all be included in the protection scope of the present invention.

Claims

1. A nuclear accident emergency action planning system based on multi-source heterogeneous data processing, characterized in that: The system comprises: A data processing module is used to obtain a geographical map of the location of the nuclear accident, and generate a directed graph for representing spatial relationships based on the geographical map and a graph theory method, wherein the directed graph includes a plurality of directed edges and a plurality of nodes, and the nodes are divided into an accident source node, a plurality of rescue nodes, and a plurality of intermediate nodes; A data updating module is used to calculate the sparsity of each rescue node in the directed graph, select multiple sparse rescue nodes in the directed graph according to the sparsity, and simplify the directed graph according to the sparse rescue nodes to form a new directed graph; A path generation module is used to connect the directed edges between the accident source node and each rescue node in a new directed graph to form multiple rescue paths; The action planning module is used to obtain the best rescue path from multiple rescue paths using a preconfigured genetic algorithm and input the best rescue path for feedback.

2. The nuclear accident emergency action planning system based on multi-source heterogeneous data processing according to claim 1 is characterized in that: The calculation of the sparsity of each rescue node in the directed graph includes: Traverse the directed graph and record each rescue node and the neighbor set of each rescue node, wherein the neighbor set includes the neighbor rescue nodes directly adjacent to the rescue node, and the number of neighbor rescue nodes is N(v); Obtain the number of directed edges E(v) directly connecting the rescue node to each neighboring rescue node, substitute the number of adjacent rescue nodes N(v) and the number of directed edges E(v) into the pre-constructed calculation model of the local clustering coefficient C(v), and calculate the local clustering coefficient C(v) of each rescue node; The calculation model of the local clustering coefficient C(v) is expressed as follows: Where: μ represents the neighboring rescue node directly connected to the rescue node, ∑ μ∈ N(v) means that each neighbor rescue node μ of the rescue node is counted once; Substitute the local clustering coefficient C(v) of the rescue node into the sparsity calculation formula respectively: Obtain the sparsity S(v) of each rescue node; The calculation formula of the sparsity S(v) of each rescue node is as follows: Where: e represents a natural constant.

3. The nuclear accident emergency action planning system based on multi-source heterogeneous data processing according to claim 2 is characterized in that: The step of screening out a plurality of sparse rescue nodes in the directed graph includes: The sparsity S(v) is compared with the preset sparsity threshold S threshould Make comparisons; If S(v)≥S threshould , then the corresponding rescue node is determined to be a sparse rescue node; If S(v)<S threshould , then the corresponding rescue node is determined to be a non-sparse rescue node; Count all S(v)≥S threshould rescue nodes, and obtain multiple sparse rescue nodes.

4. The nuclear accident emergency action planning system based on multi-source heterogeneous data processing according to claim 3 is characterized in that: The step of simplifying the directed graph according to the sparse rescue nodes includes: Mark all sparse rescue nodes in the directed graph; All sparse rescue nodes are removed from the directed graph, and the spatial relationships between the remaining nodes are updated to obtain a new directed graph.

5. The nuclear accident emergency action planning system based on multi-source heterogeneous data processing according to claim 4 is characterized in that: The obtaining of the best rescue path from multiple rescue paths includes: a1: Initialize the population: Generate an original population according to multiple rescue paths, wherein the original population contains P individuals, each individual represents a rescue path, and P is an integer greater than zero; a2: Fitness evaluation: Under each individual, the cumulative dose, path length and cumulative sparsity of each rescue path are obtained; the cumulative dose, path length and cumulative sparsity are input into the pre-built fitness function to calculate the fitness of each individual; a3: Selection: Use the roulette method to select two individuals with high fitness in the original population as the father and mother; a4: Crossover: Perform crossover operation on the father and mother to produce new individuals; a5: Mutation: Perform mutation operation on the new individuals to obtain W new individuals, combine the W new individuals into a new population, and replace the original population with the new population, and return to step a2, W is an integer greater than zero; a6: Repeat steps a2 to a5 above until the fitness of the individuals in the original population or the new population is greater than or equal to the preset fitness threshold, or the number of iterations is greater than or equal to the preset maximum number of iterations threshold, and output the rescue path represented by the corresponding individual as the optimal rescue path.

6. The nuclear accident emergency action planning system based on multi-source heterogeneous data processing according to claim 5 is characterized in that: The logic for obtaining the cumulative dose is as follows: When a nuclear accident occurs, obtain on-site environmental data at the location of the nuclear accident, as well as on-site accident data at the accident source node within the location of the nuclear accident; Inputting the on-site environmental data and the on-site accident data into a preset Gaussian plume model to obtain the concentration distribution of radionuclides emitted by the nuclear accident, wherein the concentration distribution refers to the concentration of radionuclides at each node in the directed graph; The basic data of radionuclides are obtained, and based on the basic data and concentration distribution of radionuclides, the dose rate at each node in the rescue path is calculated, and the cumulative dose of the rescue path is calculated based on the dose rate.

7. The nuclear accident emergency action planning system based on multi-source heterogeneous data processing according to claim 6 is characterized in that: The dose rate is calculated as follows: Where: S r The calculation formula is as follows: S r =C r ×λ r ×Y r ; Where: S r is the source intensity of the rth radionuclide in the node; k r is the dose conversion factor of the rth radionuclide; r is the decay constant of the rth radionuclide in the node, and its calculation formula is: Where: T 1 / 2 is the half-life of the radionuclide; Y r is the radiation particle release yield of the rth radionuclide in the node; The calculation formula of the cumulative dose is as follows: Where: Δd is the path distance of a single node in the rescue path; D i is the dose rate of the i-th node; Δt is the residence time; Δd ​​is the spatial distance of the i-th node on the path; v is the average speed of the personnel.

8. The nuclear accident emergency action planning system based on multi-source heterogeneous data processing according to claim 7 is characterized in that: The calculation formula of the pre-constructed fitness function is: In the formula: Fitness is fitness, D total is the cumulative dose, L total is the path length, S(v) total is the cumulative sparsity, ω1, ω2 and ω3 are adjustment factors greater than zero, ω1>ω2>ω3, D0, L0 and S(v)0 are the reference values ​​of cumulative dose, path length and cumulative sparsity, respectively.

9. A nuclear accident emergency action planning method based on multi-source heterogeneous data processing, characterized in that: The method is implemented based on the nuclear accident emergency action planning system based on multi-source heterogeneous data processing according to any one of claims 1 to 8, and the method comprises: Obtaining a geographical map of the location of the nuclear accident, and generating a directed graph for representing spatial relationships based on the geographical map and a graph theory method, wherein the directed graph includes a plurality of directed edges and a plurality of nodes, and the nodes are divided into an accident source node, a plurality of rescue nodes, and a plurality of intermediate nodes; Calculate the sparsity of each rescue node in the directed graph, select multiple sparse rescue nodes in the directed graph according to the sparsity, and simplify the directed graph according to the sparse rescue nodes to form a new directed graph; In the new directed graph, the directed edges connecting the accident source node to each rescue node form multiple rescue paths; The preconfigured genetic algorithm is used to obtain the best rescue path from multiple rescue paths, and the best rescue path is input for feedback.

Images