Dynamic assessment method of extreme rainstorm waterlogging disaster risk for disaster prevention and mitigation

Abstract

The present invention discloses a method for dynamic assessment of extreme rainstorm waterlogging disaster risk for disaster prevention and mitigation, investigates urban system data and disaster prevention and mitigation data, uses GIS technology to perform refined risk unit division on disaster-prone bodies at the scale of urban buildings and road networks, and determines the spatial distribution of disaster-prone bodies; simulates the impact of the dynamic change process of flood water depth on disaster-prone bodies based on extreme rainstorm waterlogging scenarios; conducts refined dynamic assessment of waterlogging risks by combining waterlogging process simulation and index system methods; calculates the traffic capacity of the road network system and the accessibility of emergency services by using spatial complex networks and shortest path planning; on this basis, comprehensively considers the rational allocation of disaster prevention emergency drainage and emergency rescue services to high-risk areas, proposes a dynamic assessment technology for waterlogging risks that integrates disaster evolution and disaster prevention response processes, and finally realizes the dynamic assessment of waterlogging risks of each disaster-prone unit during the evolution of waterlogging disasters.

Description

Technical Field

[0001] The invention belongs to the technical field of urban disaster prevention and reduction, and relates to a dynamic assessment method for extreme rainstorm waterlogging disaster risk for disaster prevention and reduction. Background Art

[0002] Under the combined influence of global climate change and rapid urbanization, the problem of urban extreme rainstorm waterlogging disasters has become increasingly prominent. Urban waterlogging causes large-scale waterlogging, causing damage to infrastructure and paralysis of the transportation system. The obstructed emergency services are unable to meet the dynamic surge in emergency rescue needs, causing huge economic losses and social impacts, and even threatening people's lives. Risk assessment, as the basis and technical support for waterlogging disaster management and disaster prevention, mitigation and relief decision-making, has shifted from disaster assessment itself to disaster-bearing body assessment under a changing environment. Flooding of houses and roads, casualties and property losses have become important objects of urban waterlogging disaster risk assessment. However, the waterlogging process of rainstorms often has strong spatiotemporal variation characteristics. The existing risk assessment methods have problems in practical applications, such as unclear classification of disaster-bearing bodies and strong subjective dependence of risk assessment. In particular, they ignore the mutual dynamic impact of disaster prevention response on waterlogging disaster risks, which brings certain difficulties to urban disaster prevention and mitigation work. Therefore, it is urgent to adopt new technologies to accurately evaluate the dynamic risk changes of disaster-bearing bodies during the evolution of waterlogging disasters.

[0003] Based on the above background, in response to the difficulties faced in urban disaster prevention and mitigation, the present invention can improve the current rainstorm waterlogging risk assessment method and enhance the urban waterlogging disaster management capabilities. The research results can provide technical support for urban disaster management and emergency decision-making. Summary of the invention

[0004] The purpose of the present invention is to provide a dynamic assessment method for extreme rainstorm waterlogging disaster risks for disaster prevention and mitigation, which solves the problem that the existing waterlogging disaster risk assessment methods have strong subjective dependence on risk evaluation in practical applications and cannot dynamically assess the waterlogging risks of each disaster-bearing unit during the evolution of waterlogging disasters.

[0005] The technical scheme adopted by the present invention is a method for dynamic assessment of extreme rainstorm waterlogging disaster risk for disaster prevention and mitigation, which investigates urban system data and disaster prevention and mitigation data, and uses GIS technology to divide the disaster-bearing body into fine risk units at the scale of urban buildings and road networks and determine the spatial distribution of the disaster-bearing body; based on the extreme rainstorm waterlogging scenario, the dynamic change process of flood water depth is simulated to simulate the impact of the disaster on the disaster-bearing body; the urban complex system is regarded as consisting of three subsystems: regional space, road network system and disaster prevention emergency response, and the traffic capacity of the road network system and the accessibility of emergency services are calculated by using spatial complex network and shortest path planning; on this basis, the rational allocation of disaster prevention emergency drainage and emergency rescue services to high-risk areas is comprehensively considered, and two methods of waterlogging process simulation and index system are combined to propose a dynamic assessment technology for waterlogging risk that integrates disaster evolution and disaster prevention response process, dynamically assesses the waterlogging risk of each disaster-bearing unit in the process of waterlogging disaster evolution, constructs a risk database through scenario setting, optimizes the LSTM network by integrating Harris Eagle optimization algorithm and particle swarm optimization algorithm, and constructs a real-time analysis model for waterlogging risk, and finally realizes the dynamic assessment and calculation of extreme rainstorm waterlogging disaster risk. The specific steps are as follows:

[0006] Step 1, collect urban system data and urban disaster prevention and mitigation data; the urban system data includes road network system data, population density, land use, regional GDP, and urban lifeline engineering lines; the urban disaster prevention and mitigation data includes the number and location of flood control and drainage projects, and emergency flood control equipment, and the emergency flood control equipment includes the number and location of flood control and drainage vehicles and portable mobile pumps;

[0007] Step 2: Classify the key urban flood prevention targets and vulnerable areas into categories, including: important infrastructure (main roads, underpasses, urban subways, substations, etc.), public service facilities (government, hospitals, schools, fire stations, etc.), residential areas (old urban areas, high-density areas, etc.), economic functional areas (commercial centers, tourist attractions, etc.), vulnerable industries (bookstores, car dealerships, tobacco stores, furniture stores, etc.); using building units and road networks as the division scale, use GIS technology to refine the risk unit division of the disaster-prone body and determine the spatial distribution of the disaster-prone body;

[0008] Step 3: Build a high-precision waterlogging process model, collect high-resolution terrain elevation data for key areas with high risk (underpasses, urban subways, substations, and old urban areas), conduct detailed simulation of flood processes, and analyze the impact of the dynamic change process of flood water depth on the disaster-bearing body;

[0009] Step 4: Classify the disaster level into three levels: slight disaster, severe disaster and major disaster, and calculate the economic loss of the disaster-bearing body by comprehensively considering the flood depth, area and average economic value;

[0010] Step 5, calculate the traffic capacity of the road network and evaluate the road failure;

[0011] Step 6: Evaluate the accessibility of rescue services in combination with regional waterlogging emergency prevention and control strategies;

[0012] Step 7: Set the rainstorm waterlogging scenario and dynamically assess the waterlogging risk;

[0013] Step 8, constructing a waterlogging risk database according to the waterlogging risk dynamic change assessment results of step 7;

[0014] Step 9: Use the waterlogging risk database in step 8 to train the LSTM deep learning network, and use the Harris Eagle optimization algorithm and particle swarm optimization algorithm to optimize the number of hidden layer neurons, weights, and learning rate of the LSTM network to improve the prediction accuracy of the LSTM network and build a real-time analysis model for waterlogging risk.

[0015] Step 10, based on the real-time, forecasted or set rainfall conditions and disaster prevention level adjustment scenario conditions, use the real-time analysis model engine of waterlogging risk to perform real-time calculations to obtain the dynamic process and deduction results of the spatiotemporal changes of waterlogging risk.

[0016] The present invention is also characterized in that:

[0017] Step 4: The method for calculating the economic loss of the disaster-prone body is shown in formula (1):

[0018] (1)

[0019] In the formula, L To bear the economic losses of the disaster-stricken body, I and J Respectively represent the total number of hazard-bearing body types and the total number of inundation depths; A ij For the i Type of hazard-bearing body j The flooded area corresponding to the flooding depth is D ij for A ij Corresponding disaster level; Disaster level D ij Medium: 0.2 for slight damage, 0.3 for severe damage, and 0.5 for major damage; P i For the i The average economic value of the disaster-prone body type unit.

[0020] Step 5 is as follows:

[0021] The roads with service functions in the urban area are divided into main roads and secondary roads, and the road intersections are abstracted into nodes using spatial complex networks. , the road segments connected by the intersection are abstracted as a set of edges, , forming a road network diagram G(V p ,E p ) ; Adjacent intersection v i v j Required travel time T Construct a weight matrix for the weights , and finally form a road network topology M(G) ; In the process of urban waterlogging, if the depth of water accumulation is greater than 50 cm, the road function will fail, resulting in changes in the road network topology. Based on the idea of ​​the shortest path, the regional road network traffic capacity is quantitatively calculated, as shown in formula (2):

[0022] (2)

[0023] In the formula, Represents the traffic capacity of the road network, which is a node exist t Betweenness of moments; for t Connecting nodes at all times and The total number of shortest paths, , and All represent any node; for t Connecting nodes at all times The total number of shortest paths, where the shortest path is calculated using the artificial bee colony optimization algorithm;

[0024] If the depth of water on the road is greater than 50cm, the road is considered to be unavailable.

[0025] Step 6 is as follows:

[0026] Taking the facility unit that provides emergency services as the center, the radiation range of emergency facilities is calculated according to the current status of the road network topology structure and the response arrival time threshold in different scenarios of waterlogging. The emergency response demand of the disaster-bearing body in the high-risk area is statistically analyzed within the radiation range, and the supply-demand ratio of emergency services is calculated, as shown in formula (3):

[0027] (3)

[0028] In the formula, R j the supply-demand ratio for emergency services; S j Represents a spatial region The service coverage of the emergency service facilities within the city; is the number of high-risk units in the spatial area; The Gaussian equation that considers the effect of distance on the efficiency of emergency services;

[0029] Flood risk unit k As the center, search for a given spatial distance threshold d 0 rescue points, all risk units emergency service supply and demand ratio R j Gaussian equation is used for weighting, and weighted summation is used to obtain the overall emergency service accessibility. A k , as shown in formula (4):

[0030] (4).

[0031] Step 7 is as follows:

[0032] A refined assessment of urban waterlogging risk is carried out with regional space as the unit, and an assessment index system considering hazard, exposure, vulnerability and disaster prevention and mitigation capabilities is constructed by combining the analytic hierarchy process method and the entropy weight method. Scenario analysis is carried out in combination with the urban waterlogging process model, and the dynamic changes of urban waterlogging risk in disaster-bearing units are calculated by considering emergency drainage for road disaster prevention, emergency dispatch of flood control and drainage projects, and accessibility of emergency rescue services at different stages of the urban waterlogging process.

[0033] The specific construction steps of the dynamic assessment of waterlogging risk in step 7 are as follows:

[0034] Step 7.1: Build an evaluation indicator system

[0035] The evaluation index system is decomposed into the following 13 indicators: rainfall intensity, rainfall duration, flood depth, flood duration, flood range, surface elevation, land use, population density, economic losses, road network traffic capacity, monitoring and early warning capabilities, flood control and drainage capabilities, and emergency rescue service accessibility. The index weights are calculated using the combination of hierarchical analysis method and entropy weight method. The economic losses of buildings involved are calculated using formula (1) described in step 4.

[0036] a. The specific method of calculating the index weights by combining the analytic hierarchy process and the entropy weight method is as follows:

[0037] (1) Constructing a judgment matrix: Based on expert opinions or experience, use the 1-9 scale method to compare each indicator pairwise and generate a judgment matrix;

[0038] (2) Consistency test: Calculate the maximum eigenvalue of the judgment matrix and use the consistency ratio CR to determine whether the matrix meets the consistency requirements. When CR < 0.1, the matrix passes the consistency test.

[0039] (3) Calculation of subjective weight Wj AHP : By solving the eigenvector of the judgment matrix and normalizing it, the subjective weight of each indicator is obtained;

[0040] b. Calculate objective weights using entropy weight method

[0041] (1) Standardized data: All evaluation indicators are dimensionlessly standardized, such as minimum-maximum standardization, to ensure that the dimensions of each indicator are consistent.

[0042] (2) Calculate information entropy: Calculate the information entropy value of each indicator based on the standardized value of each indicator. Information entropy reflects the degree of discreteness of the indicator. The greater the degree of discreteness, the smaller the information entropy.

[0043] The information entropy formula is:

[0044]

[0045] in p ij For the j Indicator No. i The proportion of the standardized value of samples to the total, is a constant, =1 / ln( n ), is the total number of samples;

[0046] The objective weight is thus obtained:

[0047] ;

[0048] in, For the j Objective weight of each indicator; s is the total number of evaluation indicators;

[0049] c. Use the weighted average method to combine the subjective weight and the objective weight calculated by the entropy weight method.

[0050]

[0051] in, is the subjective weight ratio.

[0052] Step 7.2, dynamic calculation of the evolution process of extreme rainstorm waterlogging disaster:

[0053] According to the evolution process of waterlogging, the dynamic evolution of waterlogging disaster scenarios is divided into five stages: initial scenario, evolution scenario, peak scenario, recovery scenario and termination scenario. The waterlogging process model is used for simulation calculation to calculate the flooding depth, flooding duration and flooding range required by the indicator system in step 7.1. During the simulation, three factors that are conducive to reducing waterlogging are considered: temporary drainage by road portable pumps, rational resource allocation of emergency flood control and drainage vehicles to high-risk areas, and emergency dispatch mode of flood control and drainage projects. The rational allocation of emergency flood control and drainage vehicles is determined through the following three steps:

[0054] (1) Ranking of high-risk sections during waterlogging disasters: When the depth of water on the road is greater than 50 cm and the duration is greater than 15 minutes, it is confirmed that a flood emergency drainage vehicle is needed to carry out drainage operations; the high-risk sections are ranked in the following order: key protection area > vulnerable industry > main road > time of occurrence of high-risk sections;

[0055] The scope of key protection areas, vulnerable industries, trunk roads, and high-risk sections can be obtained through satellite image maps. The scope of key protection areas includes key protection objects and surrounding roads;

[0056] The occurrence time of high-risk sections is calculated using a two-dimensional hydrodynamic model simulation;

[0057] (2) Path planning for flood control and drainage vehicles: Based on the road conditions under waterlogging scenarios, an artificial bee colony optimization algorithm is used to calculate the shortest path for flood control and drainage vehicles to reach the work site and calculate the travel time. The new path needs to be re-planned and calculated after each drainage operation is completed.

[0058] (3) Calculation of drainage by flood control drainage vehicles: Select the amount of accumulated water and the amount of water discharged by flood control drainage vehicles according to the peak, and calculate the drainage time. When the depth of accumulated water in the area is less than 5 cm, the drainage operation is considered completed;

[0059] Step 7.3: Calculate the road network traffic capacity and emergency rescue service accessibility at each stage of the waterlogging disaster evolution process in step 7.2. The road network traffic capacity is calculated using the method in step 5, and the rescue service accessibility is calculated using formulas (3) and (4) in step 6. Considering the risk impact of emergency rescue service accessibility, calculate the waterlogging risk of different disaster-prone bodies at each scenario stage:

[0060] According to the combined weights, the comprehensive flood risk score of each area or sample is calculated. The sample in j The combined weight of the indicators is x ij , then the comprehensive risk score R i for:

[0061] ;

[0062] Step 7.4, based on the standard deviation classification method, the mean and standard deviation of the risk score are used as the basis for classification, and the mean of the comprehensive risk score is calculated. and standard deviation , the risk level is divided according to the standard deviation range of the comprehensive risk score above and below the mean:

[0063] Low risk: Score less than - ;

[0064] Medium risk: Score between - and between,

[0065] Higher risk: Score in arrive + between,

[0066] High risk: Score greater than + ;

[0067] On the basis of risk classification, experts are invited to optimize the risk level standards according to actual conditions and finally obtain the dynamic assessment results of urban waterlogging risk.

[0068] The specific steps for optimizing the LSTM network parameters in step 9 are as follows:

[0069] Step 9.1, taking the LSTM network prediction accuracy as the optimization target, construct the objective function, which is as shown in formula (5):

[0070] (5)

[0071] In the formula, For the Real data; is the average value of the real data; Predicted value for data; is the number of data;

[0072] Step 9.2: In the early stage of network parameter optimization iteration, the Harris Eagle optimization operator is integrated to improve the global search capability, the energy equation of the prey in the improved transition phase is used to determine whether to enter the local search phase, the particle swarm algorithm is used to accelerate convergence, and the mixed Cauchy-Gaussian mutation operator is introduced to jump out of possible premature. The details are as follows:

[0073] (1) In the early stage of the algorithm, the Harris Eagle algorithm is used for global search. The search process is as shown in formula (6):

[0074] (6)

[0075] Where, X t+1 and X t The individuals of the population are t+1 The iteration and t The position at the iteration; X rand,t For the t The population is randomly positioned at the iteration; X m,t For the t The average position of the population at the iteration; X prey,t For the t The prey position at the iteration; r 1, r 2, r 3. r 4 are random numbers between 0 and 1; ub and lb are the upper and lower bounds of the search space, respectively. is a random number between (0,1);

[0076] (2) Use the improved energy equation of prey in the transition phase to determine whether the algorithm has entered the local search phase; the formula is as follows:

[0077] (7)

[0078] In the formula, E Energy for prey to escape, when When , the algorithm performs a global search, otherwise it performs a local search; E 0 is the initial energy of the prey, , rand is a random number between 0 and 1; T max is the maximum number of iterations;

[0079] (3) In the local search phase, the fast search capability of the particle swarm algorithm is used to accelerate convergence. The search process is as shown in formula (8)-formula (9):

[0080] (8)

[0081] (9)

[0082] In the formula, X t+1 and V t+1 The particles are t+1 The position and speed of the generation; ω t is the weight; c 1 and c2 are the individual learning and social learning factors of particles respectively; r 1 and r 2 is a random number between 0 and 1; pbest t is the individual optimal solution of the particle; gbest t For all particles in t The global optimal solution of the generation;

[0083] In the later stage of the algorithm, the Cauchy-Gauss mutation strategy is introduced to improve the global search ability of the algorithm. If the optimal solution of the population does not change after 10 iterations, the current best individual is selected for mutation, as shown in formula (10):

[0084] (10)

[0085] In the formula, X newt is the individual position after mutation; and are random factors that obey Cauchy distribution and Gaussian distribution respectively; ζ 1 and ζ 2 are the adaptive parameters of Cauchy distribution and Gaussian distribution respectively.

[0086] The beneficial effects of the present invention are:

[0087] The present invention is a method for dynamically assessing the risk of waterlogging during extreme rainstorms for disaster prevention and reduction. The present invention has shown good results in the application of actual urban smart rain and flood management systems. The dynamic assessment results of waterlogging risk obtained by the present invention are obtained by jointly calculating a high-precision waterlogging process model and an index system, especially performing a refined simulation calculation of the risk of the disaster-bearing body, which is accurate and comprehensive. At the same time, the present invention takes into account the dynamic changes of the extreme rainstorm waterlogging process and the urban disaster prevention and reduction capabilities, and the risk results obtained are dynamic, serving the disaster prevention and rescue during the evolution of waterlogging disasters. In addition, the risk results are quickly predicted through machine learning technology, effectively meeting the timeliness of disaster prevention and rescue. The present invention is a precise, dynamic and real-time waterlogging risk assessment method. BRIEF DESCRIPTION OF THE DRAWINGS

[0088] Figure 1 It is an overall flow chart of the method for dynamic assessment of extreme rainstorm waterlogging disaster risk for disaster prevention and mitigation of the present invention;

[0089] Figure 2 It is a result diagram of the dynamic change of waterlogging risk of the extreme rainstorm waterlogging disaster risk dynamic assessment method used for disaster prevention and mitigation of the present invention;

[0090] Figure 3It is a path planning diagram of disaster prevention and emergency rescue services for the extreme rainstorm waterlogging disaster risk dynamic assessment method used for disaster prevention and mitigation of the present invention;

[0091] Figure 4 It is a dynamic evolution diagram of the waterlogging disaster scenario of the extreme rainstorm waterlogging disaster risk dynamic assessment method for disaster prevention and mitigation of the present invention;

[0092] Figure 5 It is an optimization flow chart of the extreme rainstorm waterlogging disaster risk dynamic assessment method for disaster prevention and mitigation of the present invention, which integrates the Harris Eagle optimization algorithm and the particle swarm optimization algorithm. DETAILED DESCRIPTION

[0093] The present invention is described in detail below in conjunction with the accompanying drawings and embodiments. This embodiment is implemented on the premise of the technical solution of the present invention, and a detailed implementation method and a specific operation process are given, but the protection scope of the present invention is not limited to the following embodiments.

[0094] Example 1

[0095] The method for dynamic assessment of extreme rainstorm waterlogging disaster risk for disaster prevention and mitigation of the present invention is as follows: Figure 1 As shown, the details are as follows:

[0096] Step 1, collect urban system data and urban disaster prevention and mitigation data; the urban system data includes road network system data, population density, land use, regional GDP, and urban lifeline engineering lines; the urban disaster prevention and mitigation data includes the number and location of flood control and drainage projects, and emergency flood control equipment, and the emergency flood control equipment includes the number and location of flood control and drainage vehicles and portable mobile pumps;

[0097] Step 2: Classify the key urban flood prevention targets and vulnerable areas as disaster-prone objects. The disaster-prone objects are classified into: important infrastructure, public service facilities, residential concentrated areas, economic functional areas, and vulnerable industries. Use GIS technology to divide the disaster-prone objects into refined risk units based on building units and road networks and determine their spatial distribution.

[0098] Step 3: Build a high-precision waterlogging process model, collect high-resolution terrain elevation data for key areas with high risk, conduct detailed simulation of flood processes, and analyze the impact of the dynamic change of flood water depth on the disaster-bearing body;

[0099] Step 4: Classify the disaster level into three levels: slight disaster, severe disaster and major disaster, and calculate the economic loss of the disaster-bearing body by comprehensively considering the flood depth, area and average economic value;

[0100] Minor damage includes people's movement being restricted, cars being unable to start, roads being flooded, and houses being flooded;

[0101] Severe damage included loss of mobility of people, loss of stability of vehicles, waterlogging of roads, disruption of traffic, and inundation of houses;

[0102] Major damage included people being drowned, cars being drowned, roads being flooded, and houses being damaged;

[0103] Step 5, calculating the road network traffic capacity and road failure;

[0104] Step 6: Evaluate the accessibility of rescue services in combination with regional waterlogging emergency prevention and control strategies;

[0105] Step 7: Set the rainstorm waterlogging scenario and dynamically assess the waterlogging risk;

[0106] Step 8, constructing a waterlogging risk database according to the waterlogging risk dynamic change assessment results of step 7;

[0107] Step 9: Use the waterlogging risk database in step 8 to train the LSTM deep learning network, and use the Harris Eagle optimization algorithm and particle swarm optimization algorithm to optimize the number of hidden layer neurons, weights, and learning rate of the LSTM network to improve the prediction accuracy of the LSTM network and build a real-time analysis model for waterlogging risk.

[0108] Step 10, based on the real-time, forecasted or set rainfall conditions and disaster prevention level adjustment scenario conditions, use the real-time analysis model engine of waterlogging risk to perform real-time calculations to obtain the dynamic process and deduction results of the spatiotemporal changes of waterlogging risk.

[0109] Example 2

[0110] Step 1: Collect urban system data and urban disaster prevention and mitigation data. Collect urban system data, including road network system data, population density, land use, regional GDP, and urban lifeline engineering lines; collect urban disaster prevention and mitigation data, including the number and location of flood control and drainage projects, and the number and location of emergency flood control equipment such as flood control and drainage vehicles and portable mobile pumps.

[0111] Step 2: Classify the key urban flood disaster prevention targets and vulnerable areas as disaster-prone bodies according to the following categories: important infrastructure (main roads, underpasses, urban subways, substations, etc.), public service facilities (government, hospitals, schools, fire stations, etc.), residential areas (old urban areas, high-density areas, etc.), economic functional areas (commercial centers, tourist attractions, etc.), vulnerable industries (bookstores, car dealerships, tobacco stores, furniture stores, etc.). Using building units and road networks as the division scale, use GIS technology to finely divide the disaster-prone bodies and clarify their spatial distribution.

[0112] Step 3: Build a high-precision model of urban waterlogging process, collect high-resolution terrain elevation data for the key areas with higher risks in step 1, including underpasses, urban subways, substations, and old urban areas; conduct detailed simulation of flood process, and analyze the impact of the dynamic change of flood water depth on disaster-prone objects (disaster-prone objects include people, vehicles, roads, houses, etc.).

[0113] Step 4: Classify and discuss the most unfavorable principle of flood disasters on each disaster-bearing body in steps 2 and 3, and divide the disaster-bearing level into three levels: slight disaster, severe disaster and major disaster. Consider the flooding depth, area and average economic value comprehensively, and calculate the economic loss of the disaster-bearing body, as shown in formula (1):

[0114] (1)

[0115] In the formula, I and J Respectively represent the total number of hazard-bearing body types and the total number of inundation depths; A ij For the i Type of hazard-bearing body j The flooded area corresponding to the flooding depth is D ij for A ij The corresponding disaster level: 0.2 for minor disaster, 0.3 for severe disaster, and 0.5 for major disaster; P i For the i The average economic value of the disaster-prone body type unit.

[0116] Step 5: Calculate the traffic capacity of the road network and evaluate the road failure. The roads with service functions in the urban area are mainly divided into main roads and secondary roads. The road intersections are abstracted into nodes using the spatial complex network. , the road segments connected by the intersection are abstracted as a set of edges, , forming a road network diagram G(V p ,E p ) . Adjacent intersection v i v j Required travel time T Construct a weight matrix for the weights , and finally form a road network topology M(G). In the process of urban waterlogging, if the depth of water accumulation is greater than 50 cm, the road function will fail, resulting in changes in the road network topology. Based on the idea of ​​the shortest path, the regional road network traffic capacity is quantitatively calculated, as shown in formula (2).

[0117] (2)

[0118] In the formula, Represents the traffic capacity of the road network, which is a node exist t Betweenness of moments; for t Connecting nodes at all times and The total number of shortest paths, , b and c All represent any node; for t Connecting nodes at all times The total number of shortest paths, where the shortest path is calculated using the artificial bee colony optimization algorithm;

[0119] Indicates that all shortest paths pass through the node a The number of paths accounts for the proportion of the total number of shortest paths, and the total number of nodes of the betweenness centrality of all nodes represents the traffic capacity;

[0120] If the depth of water on the road is greater than 50cm, the road is considered to be unavailable.

[0121] Step 6: Evaluate the accessibility of rescue services in combination with regional waterlogging emergency prevention and control strategies. Centered on the facility unit that provides emergency services, calculate the radiation range of emergency facilities based on the current status of the road network topology structure and the response arrival time threshold in different waterlogging scenarios. Statistically analyze the emergency response needs of disaster-stricken bodies in high-risk areas within the radiation range, and calculate the emergency service supply-demand ratio. The calculation method for the emergency service supply-demand ratio is as follows:

[0122] (3)

[0123] In the formula, R j the supply-demand ratio for emergency services; S j Represents a spatial region The service coverage of the emergency service facilities within the city; is the number of high-risk units in the spatial area; The Gaussian equation that considers the effect of distance on the efficiency of emergency services;

[0124] Flood risk unit k As the center, search for a given spatial distance threshold d 0 rescue points, all risk units emergency service supply and demand ratio R j Gaussian equation is used for weighting, and weighted summation is used to obtain the overall emergency service accessibility.A k , the emergency service accessibility is calculated as formula (4):

[0125] (4)

[0126] Step 7: Dynamic assessment of waterlogging risk. Combine the advantages of the index system method and model simulation to carry out refined assessment of waterlogging risk with regional space as the unit. A combination of analytic hierarchy process and entropy weight method is used to construct an assessment index system that considers hazard, exposure, vulnerability and disaster prevention and mitigation capabilities; scenario analysis is conducted in combination with the waterlogging process model, taking into account new reduced or increased risk influencing factors such as emergency drainage for road disaster prevention, emergency dispatch of flood control and drainage projects, and accessibility of emergency rescue services at different stages of the waterlogging process, and the dynamic changes in waterlogging risk in the disaster-bearing unit are calculated.

[0127] Step 8, constructing a waterlogging risk database according to the waterlogging risk dynamic change assessment results of step 7;

[0128] Step 9: Use the database in step 8 to train the LSTM deep learning network, and use the fusion of Harris Eagle optimization algorithm and particle swarm optimization algorithm to optimize the number of hidden layer neurons, weights and learning rate of the LSTM network to improve the prediction accuracy of the LSTM network and build a real-time analysis model for urban flooding risk.

[0129] Step 10, based on the real-time, forecasted or set rainfall conditions and disaster prevention level adjustment scenario conditions, use the real-time analysis model engine of waterlogging risk to perform real-time calculations to obtain the dynamic process and deduction results of the spatiotemporal changes of waterlogging risk.

[0130] Example 3

[0131] Based on Example 2,

[0132] The specific construction steps of the dynamic assessment of waterlogging risk in step 7 are as follows:

[0133] Step 7.1: Build an evaluation indicator system

[0134] The evaluation index system is decomposed into the following 13 indicators: rainfall intensity, rainfall duration, flood depth, flood duration, flood range, surface elevation, land use, population density, economic losses, road network traffic capacity, monitoring and early warning capabilities, flood control and drainage capabilities, and emergency rescue service accessibility. The index weights are calculated using the combination of hierarchical analysis method and entropy weight method. The economic losses of buildings involved are calculated using formula (1) described in step 4.

[0135] a. The specific method of calculating the index weights by combining the analytic hierarchy process and the entropy weight method is as follows:

[0136] (1) Constructing a judgment matrix: Based on expert opinions or experience, use the 1-9 scale method to compare each indicator pairwise and generate a judgment matrix;

[0137] (2) Consistency test: Calculate the maximum eigenvalue of the judgment matrix and use the consistency ratio CR to determine whether the matrix meets the consistency requirements. When CR < 0.1, the matrix passes the consistency test.

[0138] (3) Calculation of subjective weight W j AHP : By solving the eigenvector of the judgment matrix and normalizing it, the subjective weight of each indicator is obtained;

[0139] b. Calculate objective weights using entropy weight method

[0140] (1) Standardized data: All evaluation indicators are dimensionlessly standardized, such as minimum-maximum standardization, to ensure that the dimensions of each indicator are consistent.

[0141] (2) Calculate information entropy: Calculate the information entropy value of each indicator based on the standardized value of each indicator. Information entropy reflects the degree of discreteness of the indicator. The greater the degree of discreteness, the smaller the information entropy.

[0142] The information entropy formula is:

[0143]

[0144] in, p ij For the j Indicator No. i The proportion of the standardized value of samples to the total, is a constant, =1 / ln( n ), is the total number of samples;

[0145] The objective weight is thus obtained:

[0146] ;

[0147] in, For the j Objective weight of each indicator; s is the total number of evaluation indicators;

[0148] c. Use the weighted average method to combine the subjective weight and the objective weight calculated by the entropy weight method.

[0149]

[0150] in, is the subjective weight ratio.

[0151] Step 7.2: Dynamic calculation of the evolution process of extreme rainstorm waterlogging disaster. According to the evolution process of waterlogging, the dynamic evolution of waterlogging disaster scenarios is divided into five stages: initial scenario, evolution scenario, peak scenario, recovery scenario and termination scenario (e.g. Figure 2 and Figure 4 As shown), the circle represents the severity of waterlogging, the colorless part means no waterlogging, and the next circle color changes from light to dark, indicating that the waterlogging is getting more and more serious. The waterlogging process model is used for simulation calculation to calculate the flooding depth, flooding duration and flooding range required by the indicator system in step 7.1. During the simulation, three factors that are conducive to reducing waterlogging are considered: temporary drainage by road portable pumps, rational resource allocation of emergency flood control and drainage vehicles to high-risk areas, and emergency dispatch mode of flood control and drainage projects. The rational allocation of emergency flood control and drainage vehicles is determined through the following three steps:

[0152] (1) Ranking of high-risk sections during waterlogging disasters. When the depth of water on the road is greater than 50 cm and the duration is greater than 15 minutes, it is confirmed that a flood emergency drainage vehicle is needed to carry out drainage operations. High-risk sections are ranked in the following order: key protection area > vulnerable industry > main road > time of occurrence of high-risk sections;

[0153] The scope of key protection areas, vulnerable industries, trunk roads, and high-risk sections can be obtained through satellite image maps. The scope of key protection areas includes key protection objects and surrounding roads;

[0154] The occurrence time of high-risk sections is calculated using a two-dimensional hydrodynamic model simulation;

[0155] (2) Path planning for flood control and drainage vehicles. Based on the road conditions under waterlogging scenarios, an artificial bee colony optimization algorithm is used to calculate the shortest path for flood control and drainage vehicles to reach the work site and calculate the travel time. The new path needs to be re-planned and calculated after each drainage operation is completed.

[0156] (3) Calculation of drainage by flood control drainage vehicles. Select the amount of accumulated water and the amount of water discharged by flood control drainage vehicles according to the peak, and calculate the drainage time. When the depth of accumulated water in the area is less than 5 cm, the drainage operation is considered completed.

[0157] Step 7.3, calculate the road network traffic capacity and emergency rescue service accessibility at each stage of the waterlogging disaster evolution process in step 7.2, Figure 3 The path planning diagram of disaster prevention and emergency rescue services is shown. The boxes in the figure represent different risk areas. The traffic capacity of the road network is calculated using the method in step 5, and the accessibility of rescue services is calculated using the method in step 6. The risk impact brought by the accessibility of emergency rescue services is considered, and the waterlogging risk of different disaster-prone bodies is calculated at each stage.

[0158] According to the combined weights, the comprehensive flood risk score of each area or sample is calculated. The sample in j The combined weight of the indicators is x ij , then the comprehensive risk score R i for:

[0159] ;

[0160] Step 7.4, based on the standard deviation classification method, the mean and standard deviation of the risk score are used as the basis for classification, and the mean of the comprehensive risk score is calculated. and standard deviation , the scores are divided into grades according to the standard deviation range above and below the mean:

[0161] Low risk: Score less than - ,

[0162] Medium risk: Score between - and between,

[0163] Higher risk: Score in arrive + between,

[0164] High risk: Score greater than + ;

[0165] On the basis of risk classification, experts are invited to optimize the risk level standards according to actual conditions and finally obtain the dynamic assessment results of urban waterlogging risk.

[0166] The specific steps for optimizing the LSTM network parameters in step 9 are as follows:

[0167] Step 9.1, taking the LSTM network prediction accuracy as the optimization target, construct the objective function, that is, formula (5):

[0168] (5)

[0169] In the formula, For the Real data; is the average value of the real data; is the predicted value of the data; is the number of data.

[0170] Step 9.2, build an optimization framework that integrates the Harris Hawk optimization algorithm and the particle swarm optimization algorithm. The particle swarm optimization algorithm is suitable for solving nonlinear optimization problems and has a fast convergence speed, but it is limited by insufficient global search capabilities and is prone to premature maturity during the evolution process. The Harris Hawk optimization algorithm has a strong search capability in the global exploration stage. Therefore, the algorithm integrates the Harris Hawk optimization operator in the early stage of iteration to improve the global search capability, uses the improved energy equation of the prey in the transition stage to determine whether to enter the local search stage, uses the particle swarm algorithm to accelerate convergence, and then introduces the mixed Cauchy-Gaussian mutation operator to jump out of possible premature maturity. The specific algorithm is as follows Figure 5 As shown;

[0171] (1) In the early stage of the algorithm, the Harris Eagle algorithm is used for global search. The search process is as shown in formula (6):

[0172] (6)

[0173] Where, X t+1 and X t The individuals of the population are t+1 The iteration and t The position at the iteration; X rand,t For the t The population is randomly positioned at the iteration; X m,t For the t The average position of the population at the iteration; X prey,t For the t The prey position at the iteration; r 1, r 2, r 3. r 4 are random numbers between 0 and 1; ub and lb are the upper and lower bounds of the search space, respectively. is a random number between (0,1);.

[0174] (2) Use the improved energy equation of the prey in the transition phase to determine whether the algorithm has entered the local search phase. The energy equation is as follows:

[0175] (7)

[0176] In the formula, E Energy for prey to escape, when When , the algorithm performs a global search, otherwise it performs a local search; E 0 is the initial energy of the prey, , rand is a random number between 0 and 1; T max is the maximum number of iterations.

[0177] (3) In the local search phase, the fast search capability of the particle swarm algorithm is used to accelerate convergence. The search process is as shown in formula (8)-formula (9):

[0178] (8)

[0179] (9)

[0180] In the formula, X t+1 and V t+1 The particles are t+1 The position and speed of the generation; ω t is the weight; c 1 and c 2 are the individual learning and social learning factors of particles respectively; r 1 and r 2 is a random number between 0 and 1; pbest t is the individual optimal solution of the particle; gbest t For all particles in t The global optimal solution of the generation.

[0181] In the later stage of the algorithm, the Cauchy-Gauss mutation strategy is introduced to improve the global search ability of the algorithm. If the optimal solution of the population does not change after 10 iterations, the current best individual is selected for mutation, as shown in formula (10):

[0182] (10)

[0183] In the formula, X newt is the individual position after mutation; and are random factors that obey Cauchy distribution and Gaussian distribution respectively; ζ 1 and ζ 2 are the adaptive parameters of Cauchy distribution and Gaussian distribution respectively.

Claims

1. A dynamic assessment method for extreme rainstorm waterlogging disaster risk for disaster prevention and mitigation, characterized in that: Investigate urban system data and disaster prevention and mitigation data, use GIS technology to refine risk unit division of disaster-prone objects at the scale of urban buildings and road networks, and determine the spatial distribution of disaster-prone objects; simulate the impact of the dynamic change process of flood water depth on disaster-prone objects based on extreme rainstorm waterlogging scenarios; use spatial complex networks and shortest path planning to calculate the traffic capacity of the road network system and the accessibility of emergency services; Combining the two methods of waterlogging process simulation and indicator system, a dynamic waterlogging risk assessment technology integrating disaster evolution and disaster prevention response process is proposed. The waterlogging risk of each disaster-bearing unit in the process of waterlogging disaster evolution is dynamically assessed. A risk database is constructed through scenario setting. The Harris Eagle optimization algorithm and the particle swarm optimization algorithm are integrated to optimize the LSTM network, and a real-time waterlogging risk analysis model is constructed. Finally, the dynamic assessment and calculation of extreme rainstorm waterlogging disaster risk is realized. The specific operation steps are as follows: Step 1, collect urban system data and urban disaster prevention and mitigation data; the urban system data includes road network system data, population density, land use, regional GDP, and urban lifeline engineering lines; the urban disaster prevention and mitigation data includes the number and location of flood control and drainage projects, and emergency flood control equipment, and the emergency flood control equipment includes the number and location of flood control and drainage vehicles and portable mobile pumps; Step 2: Classify the key urban flood prevention targets and vulnerable areas as disaster-prone objects. The disaster-prone objects are classified into: important infrastructure, public service facilities, residential concentrated areas, economic functional areas, and vulnerable industries. Use GIS technology to divide the disaster-prone objects into refined risk units based on building units and road networks and determine their spatial distribution. Step 3: construct a high-precision waterlogging process model, collect high-resolution terrain elevation data for key areas with high risk, conduct detailed simulation of flood processes, and analyze the impact of the dynamic change of flood water depth on the disaster-bearing body; the key areas with high risk include underpasses, urban subways, substations, and old urban areas; Step 4: Classify the disaster level into three levels: slight disaster, severe disaster and major disaster according to different disaster-bearing bodies, and calculate the economic loss of the disaster-bearing body by comprehensively considering the flooding depth, flooding area and average economic value; Step 5, calculate the traffic capacity of the road network and evaluate the road failure; Step 6: Evaluate the accessibility of rescue services in combination with regional waterlogging emergency prevention and control strategies; Step 7: Set the rainstorm waterlogging scenario and dynamically assess the waterlogging risk; Step 8, constructing a waterlogging risk database according to the waterlogging risk dynamic change assessment results of step 7; Step 9: Use the waterlogging risk database in step 8 to train the LSTM deep learning network, and use the Harris Eagle optimization algorithm and particle swarm optimization algorithm to optimize the number of hidden layer neurons, weights, and learning rate of the LSTM network to improve the prediction accuracy of the LSTM network and build a real-time analysis model for waterlogging risk. Step 10, based on the real-time, forecasted or set rainfall conditions and disaster prevention level adjustment scenario conditions, use the real-time analysis model engine of waterlogging risk to perform real-time calculations to obtain the dynamic process and deduction results of the spatiotemporal changes of waterlogging risk.

2. The method for dynamic assessment of extreme rainstorm waterlogging disaster risk for disaster prevention and mitigation according to claim 1, characterized in that: Step 4: Classify the disaster level according to different disaster-bearing bodies: Minor damage: people's movements are restricted, cars cannot start, roads are flooded, and houses are flooded; Severe damage: people and vehicles become unstable, roads become flooded, traffic is interrupted, and houses are submerged; Major disaster: people were drowned, cars were drowned, roads were flooded, and houses were damaged.

3. The method for dynamic assessment of extreme rainstorm waterlogging disaster risk for disaster prevention and mitigation according to claim 2, characterized in that: Step 4: The method for calculating the economic loss of the disaster-prone body is shown in formula (1): （1） In the formula, L To bear the economic losses of the disaster-stricken body, I and J Respectively represent the total number of hazard-bearing body types and the total number of inundation depths; A ij For the i Type of hazard-bearing body j The flooded area corresponding to the flooding depth is D ij for A ij Corresponding disaster level; Disaster level D ij Medium: 0.2 for slight damage, 0.3 for severe damage, and 0.5 for major damage; P i For the i The average economic value of the disaster-prone body type unit.

4. The method for dynamic assessment of extreme rainstorm waterlogging disaster risk for disaster prevention and mitigation according to claim 3 is characterized in that: Step 5 is as follows: The roads with service functions in the urban area are divided into main roads and secondary roads, and the road intersections are abstracted as nodes using spatial complex networks. , the road segments connected by the intersection are abstracted as a set of edges , forming a road network diagram G(V p ,E p ) ; Adjacent intersection v i v j Required travel time T Construct a weight matrix for the weights , and finally form a road network topology M(G) ; During the evolution of urban waterlogging disasters, if the water depth is greater than 50 cm, the road functionality will fail, resulting in changes in the road network topology. Based on the idea of ​​the shortest path, the regional road network traffic capacity is calculated as shown in formula (2): （2） In the formula, Represents the traffic capacity of the road network, which is a node exist t Betweenness of moments; for t Connecting nodes at all times and The total number of shortest paths, , and represents any node; for t Connecting nodes at all times The total number of shortest paths, where the shortest path is calculated using the artificial bee colony optimization algorithm; If the depth of water on the road is greater than 50cm, the road is considered to be unavailable.

5. The method for dynamic assessment of extreme rainstorm waterlogging disaster risk for disaster prevention and mitigation according to claim 4, characterized in that: Step 6 is as follows: Taking the facility unit that provides emergency services as the center, the radiation range of emergency facilities is calculated according to the current status of the road network topology structure and the response arrival time threshold in different scenarios of waterlogging. The emergency response demand of the disaster-bearing body in the high-risk area is statistically analyzed within the radiation range, and the supply-demand ratio of emergency services is calculated. The calculation method of the supply-demand ratio of emergency services is as shown in formula (3): （3） In the formula, R j the supply-demand ratio for emergency services; S j Represents a spatial region The service coverage of the emergency service facilities within the city; is the number of high-risk units in the spatial area; The Gaussian equation that considers the effect of distance on the efficiency of emergency services; Flood risk unit k As the center, search for a given spatial distance threshold d 0 rescue points, all risk units emergency service supply and demand ratio R j Gaussian equation is used for weighting, and weighted summation is used to obtain the overall emergency service accessibility. A k , the emergency service accessibility is calculated as formula (4): （4）。 6. The method for dynamic assessment of extreme rainstorm waterlogging disaster risk for disaster prevention and mitigation according to claim 5, characterized in that: Step 7 is as follows: A refined assessment of urban waterlogging risk is carried out with regional space as the unit, and an assessment index system considering hazard, exposure, vulnerability and disaster prevention and mitigation capabilities is constructed by combining the analytic hierarchy process method and the entropy weight method. Scenario analysis is carried out in combination with the urban waterlogging process model, and the dynamic changes of urban waterlogging risk in disaster-bearing units are calculated by considering emergency drainage for road disaster prevention, emergency dispatch of flood control and drainage projects, and accessibility of emergency rescue services at different stages of the urban waterlogging process.

7. The method for dynamic assessment of extreme rainstorm waterlogging disaster risk for disaster prevention and mitigation according to claim 6, characterized in that: The specific steps of dynamic assessment of waterlogging risk in step 7 are as follows: Step 7.1: Build an evaluation indicator system The evaluation index system includes the following 13 indicators: rainfall intensity, rainfall duration, flood depth, flood duration, flood range, surface elevation, land use, population density, economic losses, road network traffic capacity, monitoring and early warning capabilities, flood control and drainage capabilities, and emergency rescue service accessibility. The index weights are calculated using the combination of hierarchical analysis method and entropy weight method. The economic losses of buildings involved are calculated using formula (1). a. The specific method of calculating the index weights by combining the analytic hierarchy process and the entropy weight method is as follows: (1) Construct a judgment matrix: Use the 1-9 scaling method to compare each indicator pairwise to generate a judgment matrix; (2) Consistency test: Calculate the maximum eigenvalue of the judgment matrix and use the consistency ratio CR to determine whether the matrix meets the consistency requirements. When CR < 0.1, the matrix passes the consistency test. (3) Calculation of subjective weight W j AHP : By solving the eigenvector of the judgment matrix and normalizing it, the subjective weight of each indicator is obtained; b. Calculate objective weights using entropy weight method (1) Standardized data: All evaluation indicators are dimensionlessly standardized to ensure that the dimensions of each indicator are consistent; (2) Calculate information entropy: Calculate the information entropy value of each indicator based on the standardized value of each indicator. The information entropy formula is: in, p ij For the j Indicator No. i The proportion of the standardized value of samples to the total, is a constant, =1 / ln( n ), is the total number of samples; The objective weight is thus obtained: ； in, For the j Objective weight of each indicator; s is the total number of evaluation indicators; c. Use the weighted average method to combine the subjective weight and the objective weight calculated by the entropy weight method. in, is the subjective weight ratio, 0< <1; W j AHP is the subjective weight; is information entropy; Step 7.2, dynamic calculation of the evolution process of extreme rainstorm waterlogging disaster: According to the evolution process of waterlogging, the dynamic evolution of waterlogging disaster scenarios is divided into five stages: initial scenario, evolution scenario, peak scenario, recovery scenario and termination scenario. The waterlogging process model is used to simulate and calculate the flooding depth, flooding duration and flooding range required by the indicator system in step 7.

1. During the simulation, three factors that are conducive to reducing waterlogging are considered: temporary drainage by road portable pumps, rational resource allocation of emergency flood control and drainage vehicles to high-risk areas, and emergency dispatch mode of flood control and drainage projects. The rational allocation of emergency flood control and drainage vehicles is determined through the following three steps: (1) Ranking of high-risk sections during waterlogging disasters: When the depth of water on the road is greater than 50 cm and the duration is greater than 15 minutes, it is confirmed that a flood emergency drainage vehicle is needed to carry out drainage operations; the high-risk sections are ranked in the following order: key protection area > vulnerable industry > main road > time of occurrence of high-risk sections; The scope of key protection areas, vulnerable industries, trunk roads, and high-risk sections can be obtained through satellite image maps. The scope of key protection areas includes key protection objects and surrounding roads; The occurrence time of high-risk sections is calculated using a two-dimensional hydrodynamic model simulation; (2) Path planning for flood control and drainage vehicles: Based on the road conditions under waterlogging scenarios, an artificial bee colony optimization algorithm is used to calculate the shortest path for flood control and drainage vehicles to reach the work site and calculate the travel time. The new path needs to be re-planned and calculated after each drainage operation is completed. (3) Calculation of drainage by flood control drainage vehicles: Select the amount of accumulated water and the amount of water discharged by flood control drainage vehicles according to the peak, and calculate the drainage time. When the depth of accumulated water in the area is less than 5 cm, the drainage operation is considered completed; Step 7.3, calculate the road network traffic capacity and emergency rescue service accessibility at each stage of the waterlogging disaster evolution process in step 7.2, where the road network traffic capacity is calculated using formula (2), and the rescue service accessibility is calculated using formulas (3) and (4) in step 6; calculate the waterlogging risk of different disaster-prone bodies at each scenario stage; According to the combined weights in step 7.1, calculate the comprehensive flood risk score for each area or sample. The sample in j The combined weight of the indicators is x ij , then the comprehensive risk score R i for: ； Step 7.4, based on the standard deviation classification method, the mean and standard deviation of the risk score are used as the basis for classification, and the mean of the comprehensive risk score is calculated. and standard deviation , the scores are divided into grades according to the standard deviation range above and below the mean: Low risk: score less than - , Medium risk: Score between - and between, Higher risk: Score in arrive + between, High risk: Score greater than + ; On the basis of risk classification, experts are invited to optimize the risk level standards according to actual conditions and finally obtain the dynamic assessment results of urban waterlogging risk.

8. The method for dynamic assessment of extreme rainstorm waterlogging disaster risk for disaster prevention and mitigation according to claim 1, characterized in that: The specific steps for optimizing the LSTM network parameters in step 9 are as follows: Step 9.1, taking the LSTM network prediction accuracy as the optimization target, construct the objective function, that is, formula (5): （5） In the formula, For the Real data; is the average value of the real data; Predicted value for data; is the number of data; Step 9.2: In the early stage of network parameter optimization iteration, the Harris Eagle optimization operator is integrated to improve the global search capability, the energy equation of the prey in the improved transition phase is used to determine whether to enter the local search phase, the particle swarm algorithm is used to accelerate convergence, and the mixed Cauchy-Gaussian mutation operator is introduced to jump out of premature, as follows: (1) Use the Harris Eagle algorithm to perform a global search. The search process is as shown in formula (6): （6） Where, X t+1 and X t The individuals of the population are t+1 The iteration and t The position at the iteration; X rand,t For the t The population is randomly positioned at the iteration; X m,t For the t The average position of the population at the iteration; X prey,t For the t The prey position at the iteration; r 1, r 2, r 3. r 4 are random numbers between 0 and 1; ub and lb are the upper and lower bounds of the search space respectively; is a random number between (0,1); (2) Using the improved energy equation of the prey in the transition phase, determine whether the algorithm has entered the local search phase; the energy equation is as follows: （7） In the formula, E Energy for prey to escape, when When , the algorithm performs global search, otherwise it performs local search; E0 is the initial energy of the prey, , rand is a random number between 0 and 1; T max is the maximum number of iterations; (3) In the local search phase, the fast search capability of the particle swarm algorithm is used to accelerate convergence. The search process is as shown in formula (8)-formula (9): （8） （9） In the formula, X t+1 and V t+1 The particles are t+1 The position and speed of the generation; ω t is the weight; c 1 and c 2 are the individual learning and social learning factors of particles respectively; r 1 and r 2 is a random number between 0 and 1; pbest t is the individual optimal solution of the particle; gbest t For all particles in t The global optimal solution of the generation; For particles in t The speed of generation; The Cauchy-Gauss mutation strategy is introduced to improve the global search capability of the algorithm. If the optimal solution of the population does not change after 10 iterations, the current best individual is selected for mutation, as shown in formula (10): （10） In the formula, X newt is the individual position after mutation; and are random factors that obey Cauchy distribution and Gaussian distribution respectively; ζ 1 and ζ 2 are the adaptive parameters of Cauchy distribution and Gaussian distribution respectively.

Images