Decision-making Method for Protection Scheme Based on Multi-dimensional Composite Weapon Strike

Abstract

The present invention discloses a decision-making method for a protection plan based on multi-dimensional composite weapon strikes, including the following steps: extracting regional geographical information from a geographical information system, combining the location information of key nodes, and establishing an urban system function model; integrating the damage effect data of multi-dimensional multi-target weapon strikes and the protection technology data to establish a weapon strike damage effect database; establishing a subsystem function association model, integrating multi-dimensional system state information, and establishing a multi-layer system function model; quantifying the protection measures for key nodes of the system to obtain the quantified protection measures for key nodes; generating protection plans for the functions of urban key nodes under multiple random strike events, and evaluating the cost-effectiveness ratios of each protection plan; and forming an optimal protection plan according to a multi-objective constraint and multi-criteria analysis model. The decision-making method for the protection plan of the present invention can achieve a more comprehensive and accurate decision-making for the protection plan.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent decision-making for battlefield protection, and particularly to a decision-making method for protection schemes based on multi-dimensional composite weapon strikes. Background Art

[0002] The decision-making for protection schemes against multi-dimensional composite weapon strikes refers to the construction and optimal selection of overall protection schemes for urban areas under weapon strike scenarios with multiple random factors such as multiple stages and multiple scenarios.

[0003] With the acceleration of urbanization and the improvement of industrialization level, modern cities and industrial areas are facing increasingly complex explosion threats. Their suddenness, high destructiveness and unpredictability pose significant hazards to personnel safety, buildings and infrastructure. Intelligent decision-making for protection schemes under multi-dimensional composite weapon strikes is the basis for establishing an emergency response system and accumulating safety protection technologies, and is the prerequisite for urban engineering safety and protection.

[0004] Currently, for the design of facility protection schemes, such as the Chinese invention patent "A research method for the protection of oil storage facilities" (Application No.: CN202310644969.1, Publication Date: 2023-09-29), this patent takes vertical steel oil tanks as the application scenario, faces the protection of oil storage facilities and the problem of bottom corrosion of the tanks, and improves the anti-corrosion performance of the oil tanks through the macro and micro multi-scale structure design of materials. Similarly, the Chinese invention patent "Method, device, equipment and medium for determining the protection range of line fire protection facilities" (Application No.: CN202210999049.7, Publication Date: 2022-10-21) provides a method for determining the protection range of line fire protection facilities, and determines the protection range by calculating the movement time of high-temperature objects and the influence of wind speed on their horizontal acceleration. Among these disclosed protection decision-making technologies, valuable applications are provided in their respective technical fields, but to form a decision-making method for protection schemes under multi-dimensional weapon strikes, a more comprehensive and result-evaluation-oriented decision-making method is still needed.

[0005] In addition, the impact of multi-dimensional strike events on the effectiveness of protection schemes has not been evaluated in existing work; the evaluation of protection effectiveness has only been carried out for single-target fields such as protective clothing ("A fire-proof, nuclear-radiation-proof, neutron-ray-proof, biochemical split protective clothing", application number: CN202122451234.6, publication date: 2022-04-05), ships ("A method for evaluating the explosion protection effectiveness of anti-ship missiles", application number: CN202211568672.3, publication date: 2023-04-18), facility security ("A substation security protection system based on multi-level intelligence", application number: CN202210203419.1, publication date: 2022-07-22), cyber warfare (authorization number: CN113228713B, publication date: 2022-09-16), etc. There is a lack of research on the protection effectiveness of regional targets such as building complexes and system function cascades under explosive shock fire strikes.

[0006] In summary, the problems existing in the prior art are as follows: Limited by the simulation calculation speed, it is impossible to dynamically provide protection basis according to the regional damage results in real time, and there is a lack of a highly flexible and adaptable protection scheme decision-making method for explosive shock fire strikes; at the same time, for the protection decision-making of complex strikes and a large number of targets, a comprehensive and accurate protection scheme cannot be provided, and there is a lack of a generalization method for protection scheme decision-making under multi-stage and multi-scenario strikes. Summary of the Invention

[0007] The purpose of the present invention is to provide a protection scheme decision-making method based on multi-dimensional composite weapon strikes, which comprehensively considers the system damage mode and the loss degree of system key nodes, and can realize a more comprehensive and accurate protection scheme decision-making.

[0008] The technical solution to achieve the purpose of the present invention is as follows:

[0009] A protection scheme decision-making method based on multi-dimensional composite weapon strikes, comprising the following steps:

[0010] Establishment of the urban system function model: Extract the regional geographical information from the geographic information system, and combine the position information of key nodes to establish an urban system function model;

[0011] Establishment of the weapon strike damage effect database: Integrate the multi-dimensional multi-target weapon strike damage effect data collected from multiple channels and the protection technology data collected from multiple channels to establish a weapon strike damage effect database;

[0012] Establishment of the system function multi-layer model: According to the system function components, establish a subsystem function correlation model, and integrate multi-dimensional system state information to establish a system function multi-layer model;

[0013] Quantification of protection measures for key nodes of the system: According to the operational requirements of the system functions and in combination with the impact of weapon strikes on key nodes of the system on the entire system, quantify the protection measures for key nodes of the system to obtain the quantified protection measures for key nodes;

[0014] Evaluation of the cost-effectiveness of protection schemes: Based on the multi-layer model of the system functions and in combination with the quantified protection measures for key nodes, generate protection schemes for the functions of key nodes in the city under multiple random strike events, and evaluate the protection effectiveness and protection costs of each protection scheme to obtain the cost-effectiveness ratios of each protection scheme;

[0015] Decision-making on the optimal protection scheme: According to the cost-effectiveness ratios of each protection scheme, and comprehensively considering the protection scheme in which all key nodes of the system meet the set protection indicators under protection measures and their corresponding protection costs, establish a multi-objective constraint and multi-criterion analysis model to form the optimal protection scheme.

[0016] Compared with the prior art, the significant advantages of the present invention are as follows:

[0017] 1. Strong flexibility and good adaptability: The present invention adopts Monte Carlo simulation and multi-objective optimization algorithms, and can adjust and optimize protection strategies in real time under complex and changeable strike scenarios. Compared with traditional static protection designs, the present invention improves the flexibility and adaptability of protection measures and can more effectively respond to emergencies;

[0018] 2. More comprehensive damage assessment: By establishing a database of blast shock damage effects, the present invention can comprehensively analyze the impact of multi-dimensional weapon strike events on the system. Different from traditional methods that only focus on single damage effects, the present invention covers a comprehensive assessment of physical damage, functional loss and their cascading effects, providing more comprehensive protection decision-making support;

[0019] 3. Comprehensive and accurate data: Through a unified management system for multi-type data, the present invention significantly improves the efficiency in data collection, storage and analysis. This efficient data management system supports the integration of multi-source data, ensuring the comprehensiveness and accuracy of data, thereby enhancing the scientific nature of protection scheme decision-making;

[0020] 4. Wide application and effectiveness: The method of the present invention is applicable to the protection of infrastructure in complex environments such as cities and industrial areas. It not only provides protection for single facilities, but also can comprehensively protect against the cascading effects of multiple systems. This overall and detailed protection ability greatly improves the wide application and effectiveness in actual applications.

[0021] The present invention will be further described in detail below in conjunction with the accompanying drawings and specific embodiments. Description of the Drawings

[0022] Figure 1It is the main flowchart of the protection plan decision-making method based on multi-dimensional composite weapon strikes of the present invention.

[0023] Figure 2 Is Figure 1 The flowchart of the steps for establishing the weapon strike damage database in

[0024] Figure 3 Is Figure 1 The flowchart of the steps for establishing the multi-layer model of the system functions in

[0025] Figure 4 Is Figure 1 The flowchart of the steps for quantifying the protection measures of the key nodes of the system in

[0026] Figure 5 Is Figure 1 The flowchart of the steps for evaluating the cost-effectiveness of the protection plan in

[0027] Figure 6 Is Figure 1 The flowchart of the steps for making decisions on the optimal protection plan in Detailed implementation manner

[0028] As Figure 1 shown, the protection plan decision-making method based on multi-dimensional composite weapon strikes of the present invention includes the following steps:

[0029] Establishing the urban system function model 10: Extracting regional geographical information from the Geographic Information System (GIS), and combining it with the location information of key nodes to establish an urban system function model.

[0030] The key nodes include roads, bridges, power stations, oil depots, and reservoirs.

[0031] The virtualized urban system function model is used for subsequent simulation and evaluation.

[0032] Establishing the urban system function model is prior art and will not be elaborated herein.

[0033] Establishing the weapon strike damage effect database 20: Integrating the multi-dimensional multi-target weapon strike damage effect data collected from multiple channels and the protection technology data collected from multiple channels to establish a weapon strike damage effect database.

[0034] The weapon strike damage database includes the weapon strike damage data of multi-functional nodes at the urban system level with or without protection measures.

[0035] The weapon strike damage database is used for querying the function loss situation of each subsequent node.

[0036] As Figure 2 shown, the steps of establishing the weapon strike damage database 20 include:

[0037] Damage effect data collection 21: Collect weapon strike damage effect data covering various weapon types and various damage modes, including experimental data, historical accident data, and computer simulation data.

[0038] By collecting data from multiple channels such as experimental data, historical accident data, and computer simulation data, and these data cover various weapon types and various damage modes, comprehensively obtain weapon strike damage effect data from multi-dimensional strikes and multi-target attacks;

[0039] For example, the source of experimental data can be explosion tests, etc., the source of historical accident data can be industrial explosion records, etc., and the source of computer simulation data can be Abaqus simulation results, etc.

[0040] Weapon types, such as various ammunition types like fuel-air explosive bombs, armor-piercing projectiles, high-explosive fragmentation bombs, thermobaric bombs, etc.;

[0041] Target damage modes, different weapon types cause direct damage such as collapse, deformation, penetration, etc. to the components of urban core nodes such as buildings, bridges, tunnel shelters, etc.; and secondary damage such as electromagnetic pulses and high-temperature combustion to functional nodes such as electronic devices and communication facilities.

[0042] Protection technology data collection 22: Collect protection technology data from test data, historical materials, and simulation data.

[0043] Protection technology data involves three-dimensional desensitization cascade structures, high-temperature and high-resistance structures, camouflage protection technologies; it also includes various advanced protection materials and structural designs, such as high-performance composite materials like fiber-reinforced polymers, ultra-high-performance concrete, etc., energy-absorbing protection structures, specifically designed walls, foundations, and support structures, using metal grids and energy-absorbing layers, establishing protective walls and isolation barriers, etc.;

[0044] Database establishment 23: Preprocess, classify, and fuse the damage effect data and protection technology data, and input them into the database system to establish a weapon strike damage effect database.

[0045] Before inputting into the database system, first unify the ambiguity, difference, and heterogeneity of the data in terms of structure and semantics.

[0046] The steps of the database establishment 23 include:

[0047] Data preprocessing: Remove or correct outliers, standardize feature values, and normalize the data;

[0048] Extract the feature vector X = [x1, x2, …, xn] from the original data, standardize the feature values to be on the same scale, using Min-Max or Z-score normalization, and select according to the data type and distribution as appropriate;

[0049] Data feature classification and fusion: Use a convolutional neural network to classify and fuse data features;

[0050] Data entry: Enter data into the database system to establish a database of weapon strike damage effects.

[0051] The present invention collects and integrates multi-source and multi-type data, including historical data, experimental data, and numerical simulation data, covering various ammunition types and target damage effects, comprehensively evaluates physical damage, functional loss, and their cascading effects on the system, and improves the accuracy of the strike plan and the comprehensiveness of decision support.

[0052] Establish a multi-layer model of system functions 30: According to the system function components, establish a subsystem function association model, integrate multi-dimensional system state information, and establish a multi-layer model of system functions.

[0053] Based on the node function loss data in the database and comprehensively considering multi-dimensional strike damage effects, establish the logical relationships and linkage effects between different systems, such as the function associations between key infrastructures such as power systems, water supply systems, fuel / gas systems, transportation systems, and communication systems. Adopt an aggregation method based on information, physics, and applications to quantify the overall blast resistance of the system.

[0054] Such as Figure 3 As shown, the steps of establishing the multi-layer model of system functions 30 include:

[0055] Confirm system function components 31: Confirm the mutual influence and linkage effects between system function components, including physical associations, geographical associations, network associations, and logical associations between subsystems;

[0056] The steps of confirming system function components 31 include:

[0057] Identify physical associations: Identify the physical connections between systems and evaluate their relevance;

[0058] Identify and evaluate the physical connections between systems, such as the energy supply relationship between the power system and the dispatching control center. Collect and organize the physical connection data of the facilities to ensure the integrity and accuracy of the data;

[0059] Identify key positions: According to the layout and mutual dependence of each node in the urban system in terms of geographical location, identify the key node positions in the urban system function model;

[0060] Network association identification: Identify critical communication nodes and control centers based on the information between systems and the role of the control network in emergency situations;

[0061] Evaluate the information and control network between systems, especially its role in emergency situations. Identify critical communication nodes and control centers, and analyze their importance in maintaining system functions;

[0062] Logical association establishment: Establish a logical association model based on the logical relationships and linkage effects between different systems.

[0063] Analyze the logical relationships and linkage effects between different systems, such as the dependence of the water supply system on the power system. By converting various objects into relationships, such as one-to-one recursive relationships, one-to-two binary relationships, one-to-many binary relationships, etc., establish a logical association model to simulate the linkage reactions between systems under different conditions.

[0064] Sub-system function association model establishment: Based on the mutual influence and linkage effects between sub-systems, use system dynamics modeling to establish a sub-system function association model for each key node.

[0065] Sub-systems include power systems, water supply systems, fuel / gas systems, transportation systems, and communication systems.

[0066] Multi-dimensional system state information integration: Map the multi-dimensional system state information of the evaluation object to each system layer, and simulate the interaction and function transfer between system layers.

[0067] The multi-dimensional system state information of the evaluation object includes geographical information and node information.

[0068] Multi-dimensional system state information integration can provide a comprehensive view of the system state and support function evaluation under complex conditions;

[0069] System function multi-layer model establishment and evaluation: Establish a system function multi-layer model with inter-layer connections, and evaluate and determine the key impact chains and system resilience.

[0070] This step quantifies the impact of explosion shock events on each critical infrastructure and provides accurate quantitative indicators for loss assessment;

[0071] The step of system function multi-layer model establishment and evaluation includes:

[0072] Multi-layer model construction: Establish a system function multi-layer model including the integrity of system nodes and the integrity of functions;

[0073] As described above, the system function multi-layer model can be comprehensively evaluated by combining physical damage data and function loss data;

[0074] Determination of the resilience of the critical influence chain system: Determine the critical influence chain and system resilience according to the functional interactions and influence paths between the system layers in the multi-layer model of the system function.

[0075] By analyzing the dependencies of each system, establish physical, geographical, and network association models to achieve the purpose of evaluating system resilience. This method accurately evaluates the damage of individual subsystems, reveals the linkage effects between systems, helps to more comprehensively understand the resilience and critical nodes of the overall system, and thus optimizes the protection plan.

[0076] Quantification of the protection measures for the critical nodes of the system 40: According to the operational requirements of the system function and combined with the impact of weapon strikes on the critical nodes of the system on the entire system, quantify the protection measures for the critical nodes of the system to obtain the quantified protection measures for the critical nodes;

[0077] As Figure 4 shown, the steps of quantifying the protection measures for the critical nodes of the system 40 include:

[0078] Confirmation of protection indicators 41: Refer to industry specifications or standards (such as ISO, ASTM, etc.) to determine the protection performance benchmarks for each critical node, and set specific protection indicators for each critical node according to the functional attributes of the critical nodes of the system;

[0079] The protection indicators include anti-explosion level (PSI), impact resistance, fire resistance performance, etc.;

[0080] Quantification of protection measures 42: According to the protection indicators of each critical node, match the structural response of the node according to the attributes such as the morphology and materials of the critical node from the weapon strike damage effect database. At the same time, according to the protection characteristic data recorded in the database, that is, the damage results of the node under different weapon strike methods after introducing protection technologies, evaluate the quantified protection measures required for the critical nodes of the system to reach the specified protection standard under the protection of existing protection measures;

[0081] The quantified protection measures include information such as the protection area and protection location;

[0082] Utilize the protection effects that can be achieved by existing protection technologies in the database to quantify the protection measures required for the target critical nodes to reach the protection indicators.

[0083] Evaluation of the cost-effectiveness of the protection plan 50: Based on the multi-layer model of the system function, combined with the quantified protection measures for the critical nodes, generate protection plans for the functions of the critical nodes in the city under multiple random strike events, and evaluate the protection effectiveness and protection costs of each protection plan to obtain the cost-effectiveness ratios of each protection plan;

[0084] As Figure 5 shown, the steps of evaluating the cost-effectiveness of the protection plan 50 include:

[0085] Protection plan generation 51: By means of Monte Carlo simulation analysis, according to the multi-layer model of system functions, combined with the quantitative protection measures of key nodes in the target area after multi-dimensional weapon strikes, multiple protection plans are generated.

[0086] Based on the key nodes in the target area, such as substations, water treatment plants, major transportation hubs, etc.

[0087] The steps of the protection plan generation 51 include:

[0088] Monte Carlo simulation analysis: Using Monte Carlo simulation to analyze the loss distribution under different combinations of strike events;

[0089] Define input parameters: According to the basic characteristics of weapons and ammunition, determine the range of strike event parameters that serve as input variables for the decision-making model. The strike event parameters include the number of strikes, strike equivalent, and strike order of weapons and ammunition;

[0090] Determine the range of strike event parameters, including the number of strikes (such as 1 time, 2 times, 5 times, etc.), strike equivalent (ton level), strike order, and set the protection budget level (such as low, medium, high) as input variables for the decision-making model;

[0091] Random strike event generation: Using the Monte Carlo method, the decision-making model randomly samples the number of strikes, equivalent, and order to generate multiple possible strike events. Using the iterative calculation method, run multiple simulations for each strike event and statistically calculate the potential losses and protection effectiveness in each case.

[0092] Protection target selection strategy: According to the importance of key nodes and their roles in the system, set priorities to determine each node in the urban system and high-priority protection targets;

[0093] Set priorities for each node to ensure the rationality and effectiveness of resource allocation and improve the overall effectiveness of protection measures;

[0094] Formulate a protection resource allocation strategy: According to the influence of key nodes in the multi-layer model of system functions and the set protection index level, formulate a protection resource allocation strategy.

[0095] Including establishing an influence evaluation model:

[0096] ,

[0097] In the formula, is the influence of node , is its priority, is its dependence degree in the system function layer, is its connectivity in the system.

[0098] In addition, it also includes determining the protection requirements according to the protection index level of each node:

[0099] ,

[0100] In the formula, is the protection requirement of node , is the protection index level, is the building standard level of the node.

[0101] The protection resource allocation strategy is to prioritize the protection of critical nodes and allocate more resources to areas with high protection requirements (high risks);

[0102] Obtain different protection plans: For each strike event, system critical nodes, and protection resource allocation strategy, combine quantitative protection measures to formulate protection plans;

[0103] The protection plan includes the protection area, protection location, different combinations of protection measures, and implementation order, etc.

[0104] Evaluation of the effectiveness of the protection plan 52: According to the multiple protection plans, simulate and deploy protection measures at the critical nodes of the urban system function model, and use the protection characteristics recorded in the explosion damage database again to deduce the damage situation of the nodes under the protection of each protection plan. Further evaluate the impact on the overall urban system function through the multi-layer model of system functions, and unify the final protection effect with the data of system function retention, loss reduction ratio, and recovery speed. Screen out all feasible plans that achieve the same protection effect, and evaluate the protection effectiveness of each plan according to the degree of influence.

[0105] The smaller the impact on the urban system function, the higher the effectiveness of the protection plan.

[0106] Evaluation of protection cost 53: Determine the main cost elements in the protection plan, including material cost, construction cost, and maintenance and renewal cost. Use decision tree neural network to establish a relationship model between cost elements and total cost, and evaluate the cost element that has the greatest impact on the total cost.

[0107] The specific steps of the protection cost evaluation 53 are as follows:

[0108] Estimation of material cost: Estimate the market price of protection materials, such as high-strength concrete, steel bars, explosion-proof glass, etc.;

[0109] Estimation of construction cost: According to the project plan, refine the schedule and resource allocation of each work. Estimate construction costs such as civil engineering, equipment installation, and labor costs;

[0110] Maintenance and Update Cost Estimation: Based on the service life of the facility, environmental conditions, and the life cycle of the facility, estimate the costs of daily maintenance and regular updates, including regular inspections, repairs, and upgrades.

[0111] Establishment of the Relationship Model between Cost Elements and Total Cost: Use a decision tree neural network to establish a relationship model between cost elements and total cost. By recursively splitting the data set, select the features that can minimize the cost variance to the greatest extent as the splitting points, retain the feature splitting points that contribute the most to cost prediction, evaluate the importance of each cost element in the decision tree, and obtain the cost elements that have the greatest impact on the total cost.

[0112] Decision-making on the Optimal Protection Plan 60: According to the cost-effectiveness ratios of the respective protection plans, comprehensively consider the protection plans in which all key nodes of the system reach the set protection indicators under protection measures and their corresponding protection costs, establish a multi-objective constraint and multi-criteria analysis model, and form an optimal protection plan.

[0113] According to the type of the target (such as power supply station, oil storage depot, command center, transportation hub, etc.) and the requirements of protection indicators, select appropriate protection measures, optimize the emergency response mechanism, etc., so as to enhance the anti-explosion toughness and recovery ability of the overall system.

[0114] Such as Figure 6 As shown, the steps of the decision-making on the optimal protection plan 60 include:

[0115] Multi-objective Optimization 61: Define a multi-objective function, maximizing protection effectiveness and minimizing protection cost. According to the implementation costs of different protection plans, use budget constraints, implementation events, and the availability of materials and human resources as model constraint conditions. Obtain multiple protection strategy combinations through random generation or heuristic methods, sort each solution in the solution set, identify the solutions that cannot be dominated by other solutions, form the Pareto front, further sort the solutions on the Pareto front, and label the non-dominated levels of each solution to obtain the Pareto solution set;

[0116] Considering that the optimal protection plan does not mean finding extreme values, that is, there are cases where there is no upper limit on the protection budget and extreme protection of key nodes is required. Set multiple standard criteria into the optimization model to achieve the purpose of optimal decision-making according to needs.

[0117] Multi-criteria Decision-making 62: Based on the Pareto solution set, set the weights of each criterion according to the goals or resources of the decision-maker;

[0118] Such as giving priority to protection effectiveness, giving priority to cost control, etc. Ensure that the values of different criteria are compared on the same scale;

[0119] Optimal protection plan selection 63: Use multi-criteria decision analysis to dynamically evaluate the weighted ratio scores of each plan under different criteria, and decide the optimal protection plan according to the actual protection requirements.

[0120] Through the above steps, it is possible to systematically evaluate the anti-explosion resilience of the urban comprehensive system function under multiple strike events, and provide scientific protection and recovery suggestions to ensure the safety and reliability of key infrastructure.

[0121] The core advantages of the present invention lie in its flexibility and adaptability. Through Monte Carlo simulation and multi-objective optimization algorithms, it can adjust and optimize the protection strategy in real time to effectively respond to complex and changeable strike scenarios. In terms of technical implementation, the present invention first establishes a urban system function model and a weapon strike damage effect database, then constructs a multi-layer model of system functions, and quantifies the protection measures for key nodes of the system. On this basis, the present invention further evaluates the effectiveness and cost of the protection plan, and determines the optimal protection plan through multi-objective optimization and multi-criteria decision analysis.

[0122] The implementation of the present invention not only improves the scientificity and accuracy of the protection plan, but also ensures the efficient use of resources through precise cost element analysis. It can provide overall and detailed protection plan decisions for urban key node facilities, significantly improving the ability and efficiency of urban engineering safety and protection.

Claims

1. A decision-making method for a protection scheme based on multi-dimensional composite weapon strikes, characterized in that: The steps include: Establishment of urban system functional model: Extract regional geographic information from the geographic information system, combine it with key node location information, and establish an urban system functional model; Establishment of weapon strike damage effect database: Integrate multi-dimensional and multi-target weapon strike damage effect data collected from multiple channels, as well as protection technology data collected from multiple channels, to establish a weapon strike damage effect database; Establishment of multi-layer model of system function: According to the system function components, establish the subsystem function association model, integrate the multi-dimensional system status information, and establish the multi-layer model of system function; Quantification of protection measures for key nodes of the system: Based on the system functional operation requirements and the impact of weapon strikes on the entire system, the protection measures for key nodes of the system are quantified to obtain quantitative protection measures for key nodes; Protection scheme cost-effectiveness evaluation: Based on the multi-layer model of system functions and combined with the quantitative protection measures of key nodes, generate protection schemes for key urban node functions under multiple random attack events, and evaluate the protection effectiveness and cost of each protection scheme to obtain the cost-effectiveness ratio of each protection scheme; Decision on the optimal protection plan: Based on the cost-effectiveness ratio of each protection plan, the protection plan and its corresponding protection cost of the key nodes of the comprehensive system that all achieve the set protection indicators under the protection measures are established, and a multi-objective constraint and multi-standard analysis model is established to form the optimal protection plan; The protection scheme cost-effectiveness evaluation steps include: Protection plan generation: Using Monte Carlo simulation analysis, based on the multi-layer model of system functions and combined with quantitative protection measures for key nodes in the target area after multi-dimensional weapon strikes, multiple protection plans are generated; Evaluation of the effectiveness of protection schemes: Based on the multiple protection schemes, simulate the deployment of protection measures at the key nodes of the urban system function model, and again use the protection characteristics recorded in the explosion damage database to deduce the damage of the nodes under the protection of each protection scheme. Through the multi-layer model of system functions, further evaluate the impact on the functions of the entire urban system. Unify the final protection effect with the data of system function retention, loss reduction ratio, and recovery speed, screen out all feasible schemes that achieve consistent protection effects, and evaluate the protection effectiveness of each scheme according to the degree of impact; Protection cost assessment: determine the main cost elements in the protection plan, including material cost, construction cost and maintenance and update cost, use decision tree neural network to establish the relationship model between cost elements and total cost, and evaluate the cost elements that have the greatest impact on total cost; The protection scheme generating step comprises: Monte Carlo simulation analysis: Monte Carlo simulation is used to analyze the loss distribution under different combinations of attack events; Defining input parameters: According to the striking characteristics of weapons and ammunition, determining the range of striking event parameters as input variables of the decision model, wherein the striking event parameters include the striking quantity, striking equivalent, and striking sequence of weapons and ammunition; Random strike event generation: Using the Monte Carlo method, the decision model generates multiple strike events by randomly sampling the number of strikes, strike equivalents, and strike sequences. It uses an iterative calculation method to run multiple simulations for each strike event and calculate the potential losses and protection effectiveness in each case. Protection target strategy selection: according to the importance of key nodes and their role in the system, set priorities and determine the nodes and high-priority protection targets of the urban system; Formulate protection resource allocation strategy: formulate protection resource allocation strategy according to the impact of key nodes in the multi-layer model of system functions and the set protection indicator level; Protection plan acquisition: formulate a protection plan for each attack event, key system nodes, and protection resource allocation strategy, combined with quantitative protection measures; the protection plan includes protection area, protection location, different combinations of protection measures, and implementation sequence; The optimal protection solution decision-making steps include: Multi-objective optimization: define multi-objective functions, maximize protection effectiveness and minimize protection costs. According to the implementation costs of different protection schemes, use budget constraints, implementation events, and the availability of materials and human resources as model constraints. Obtain multiple protection strategy combinations through random generation or heuristic methods. Sort each solution in the solution set, identify solutions that cannot be dominated by other solutions, and form a Pareto frontier. Further sort the solutions on the Pareto frontier, identify the non-dominated level of each solution, and obtain the Pareto solution set. Multi-criteria decision-making: Based on the Pareto solution set, the weight of each criterion is set according to the decision maker's goals or resources; Selection of the optimal protection plan: Multi-criteria decision analysis is used to dynamically evaluate the weighted ratio scores of each plan under different standards, and the optimal protection plan is determined based on actual protection needs.

2. The protection scheme decision-making method according to claim 1, characterized in that: The steps of establishing the weapon strike damage database include: Damage effect data collection: Collect weapon damage effect data covering multiple weapon types and multiple damage modes, including experimental data, historical accident data and computer simulation data; Protection technology data collection: Collect protection technology data from test data, historical data, and simulation data; Database establishment: pre-process, classify and integrate the damage effect data and protection technology data, enter them into the library system, and establish a weapon strike damage effect database.

3. The protection scheme decision method according to claim 2, characterized in that: The database establishment step comprises: Data preprocessing: remove or correct outliers, standardize feature values, and normalize data; Data feature classification and fusion: Use convolutional neural networks to classify and fuse data features; Data entry: Data entry system, to establish database of weapon strike damage effects.

4. The protection scheme decision-making method according to claim 1, characterized in that: The system function multi-layer model establishment step includes: Confirmation of system functional components: Confirm the mutual influence and linkage effects between system functional components, including the physical, geographical, network and logical connections between subsystems; Establishment of subsystem functional association model: Based on the mutual influence and linkage effect between subsystems, the system dynamics modeling method is used to establish a subsystem functional association model for each key node; Multi-dimensional system status information integration: Map the multi-dimensional system status information of the evaluation object to each system layer, and simulate the interaction and function transfer between each system layer; Functional multi-layer model establishment and evaluation: Establish a system functional multi-layer model with inter-layer connections to evaluate and determine the key impact chain and system resilience.

5. The protection scheme decision method according to claim 4, characterized in that: The system functional component confirmation step comprises: Physical association identification: Identify the physical connections between systems and assess their association; Key location identification: Based on the geographical layout and interdependence of the nodes in the urban system, key node locations are identified in the functional model of the urban system; Network association identification: Identify key communication nodes and control centers based on the role of information and control networks between systems in emergency situations; Establishing logical associations: Establishing logical association models based on the logical relationships and linkage effects between different systems.

6. The protection scheme decision method according to claim 5, characterized in that: The functional multi-layer model establishment and evaluation steps include: Multi-layer model construction: Establish a multi-layer model of system functions that includes system node integrity and functional integrity; Determination of key impact chain system resilience: Determine the key impact chain and system resilience based on the functional interactions and impact paths between the system layers in the system function multi-layer model.

7. The protection scheme decision method according to claim 1, characterized in that: The quantification steps of the key node protection measures of the system include: Confirmation of protection indicators: Refer to industry specifications or standards to determine the protection performance benchmark of each key node, and set specific protection indicators for each key node based on the functional attributes of the key nodes of the system; Quantification of protective measures: Based on the protection indicators of each key node, the structural response of the node is matched according to the key node morphology and material properties from the weapon strike damage effect database. Based on the protection feature data recorded in the database, the quantitative protective measures required to ensure that the key nodes of the system can meet the specified protection standards when hit by weapons under the protection of existing protective measures are evaluated.

Images