Method, device and electronic equipment for optimizing the layout of life-saving facilities in subway station floods

Abstract

The present invention relates to the field of subway station safety management and disaster emergency technology, and provides a method, device, and electronic device for optimizing the layout of life-saving facilities in subway stations during floods. The method comprises: obtaining passenger location distribution data and flood disaster data for a target subway station; modeling the passenger density information using a density-based spatial clustering algorithm with noise to identify high-density passenger areas; using a Bayesian network to divide areas within the subway station into different hazard levels based on the passenger location distribution data and disaster data; constructing a robust optimization problem based on the high-density passenger areas and hazard levels; and solving the robust optimization problem to determine the location and quantity of life-saving equipment. The method determines the optimized location and quantity of life-saving equipment by constructing and solving the robust optimization problem. Arranging life-saving facilities based on this robust optimization problem can improve the subway station's ability to rescue passengers in flood situations.

Description

Technical Field

[0001] The present invention relates to the field of subway station safety management and disaster emergency technology, and in particular to a method, device and electronic equipment for optimizing the layout of life-saving facilities in subway stations during floods. Background Art

[0002] With the acceleration of urbanization, subway stations have become an essential component of urban transportation systems. However, the frequent occurrence of floods poses a safety threat to subway station passengers. Currently, the layout of life-saving facilities in subway stations often lacks scientific and rational planning, suffering from issues such as insufficient coverage, excessive costs, and inadequate consideration of passenger distribution and disaster situations. In the event of a flood, this inability to effectively protect passenger safety leads to inefficient rescue operations, potentially causing significant casualties and property damage. Therefore, a method is urgently needed to optimize the layout of life-saving facilities in subway stations during flooding, taking into account multiple factors. Summary of the Invention

[0003] The present invention provides a method, device and electronic equipment for optimizing the layout of life-saving facilities in subway stations during floods, which are used to solve the problem in the prior art that the layout of life-saving facilities in subway stations often lacks scientific and reasonable planning. By constructing and solving a robust optimization problem, the setting location and quantity of optimized life-saving equipment are determined. The layout of life-saving facilities based on this can improve the subway station's ability to rescue passengers in the event of a flood.

[0004] The present invention provides a method for optimizing the layout of life-saving facilities in subway stations during floods, comprising: obtaining passenger location distribution data and disaster data during floods at a target subway station, wherein the disaster data includes water depth and water flow velocity information; using a density-based spatial clustering algorithm with noise to model the passenger density information and identify high-density passenger areas; using a Bayesian network to divide areas within the subway station into different hazard levels based on the passenger location distribution data and the disaster data; constructing a robust optimization problem based on the high-density passenger areas and the hazard levels; and solving the robust optimization problem to determine the location and quantity of life-saving equipment.

[0005] According to the method for optimizing the layout of life-saving facilities in flood-prone subway stations provided by the present invention, the passenger location distribution data includes a data set containing N passenger locations, and the density-based spatial clustering algorithm with noise is used to model the passenger density information to identify high-density passenger areas, including: extracting the specific location information of each passenger from the data set containing N passenger locations and expressing it as two-dimensional coordinates; determining the number of other passengers within the area of ​​each passenger based on the two-dimensional coordinates and a preset area radius; determining passengers whose locations are core points based on the number of other passengers within the area of ​​each passenger and a preset number threshold; for each passenger whose location is a core point, classifying all passengers within its neighborhood into the same cluster; and determining passengers whose locations are neither core points nor belonging to any cluster as noise points. Calculate the centroid coordinates of each cluster; use the centroid coordinates to set the density threshold based on the cluster area and the number of passengers in the cluster , filter out areas with density greater than the threshold as key high-density areas. The specific screening conditions are:

[0006] ;

[0007] in, represents the number of cluster regions, It is The density of cluster areas, It is The area of ​​the cluster region, It is The number of passengers in each cluster area; using the linear normalization method based on the minimum value, according to the pre-set maximum density value , for the filtered high-density areas , and normalize it by mapping it to the interval [0, 1] in a linear proportional manner. The specific calculation formula is:

[0008] ;

[0009] in, It is a normalized value, representing the passenger density weight of the area.

[0010] According to the method for optimizing the layout of life-saving facilities in subway stations during flooding provided by the present invention, the method divides areas within the subway station into different danger levels using a Bayesian network based on the passenger location distribution data and the disaster data, including: determining variables that affect the division of dangerous areas, establishing dependencies between the variables, and forming a directed graph structure of the Bayesian network:

[0011] ;

[0012] Where R represents the risk of the area, H represents the water depth, V represents the water velocity, D represents the degree of obstruction of the evacuation channel, and P represents the passenger density. Based on the combination of pre-collected historical data and expert opinions, the conditional probability distribution of the following nodes is defined:

[0013] P(H): prior probability of water depth;

[0014] P(V): prior probability of water velocity;

[0015] P(P): prior probability of passenger density;

[0016] P(D|P): conditional probability between the degree of evacuation channel obstruction and passenger density;

[0017] P(R|H,V,D,P): conditional probability of risk in the scenario area;

[0018] Use Bayes’ theorem to calculate the posterior probability of the scene area risk:

[0019] ;

[0020] in, The joint probability of water depth, water velocity, evacuation channel obstruction and passenger density for a given area risk; is the prior probability of regional risk, which represents the basic probability of regional risk when there is no observation data; is the joint probability of water depth, water velocity, evacuation channel obstruction degree and passenger density; according to the chain rule, the joint probability It can be expressed as:

[0021] ;

[0022] Based on the posterior probability of each area obtained from the inference results, the risk level of each area is divided according to the preset risk probability threshold:

[0023] ;

[0024] in, and Risk thresholds are set based on historical data and safety standards.

[0025] According to the method for optimizing the layout of life-saving facilities in subway stations during flooding provided by the present invention, the objective function of the robust optimization problem includes:

[0026] ;

[0027] in, A collection of all possible disaster scenarios. For different disaster scenarios The posterior probability of the lower risk reflects the actual situation that the subway station may face due to flooding; Represents the set of filtered high-density clustered areas; For disaster scenes Lower area Passenger density weight; For disaster scenes Lower area Value at Risk; For disaster scenes Next, area The distance to the nearest lifesaving device, which depends on where the lifesaving device is located and placement quantity , The maximum distance that passengers can be rescued is calculated by comparing the area The Euclidean distance between the center coordinates of and the positions of each life-saving equipment is selected as the minimum distance The value of Representatives at the disaster scene Next, for the area Costs incurred in equipping life-saving equipment; Budget for the maximum cost allowed; Used to normalize the cost, when the cost Approaching When , this term approaches 0, so as to balance the coverage effect and cost of life-saving equipment in the optimization process; It is a region Life-saving equipment in disaster scene The use efficiency of the following.

[0028] According to the method for optimizing the layout of life-saving facilities in subway stations during flooding provided by the present invention, the constraints that need to be met during the optimization of the robust optimization problem include: a constraint on the number of life-saving equipment, a constraint on the layout area of ​​life-saving equipment, a requirement for area coverage, a minimum distance limit for life-saving equipment, a constraint on the efficiency of life-saving equipment use, and a constraint on risk value;

[0029] The life-saving equipment quantity constraint includes the quantity of life-saving equipment satisfy:

[0030] ;

[0031] in, The maximum number of life-saving appliances allowed to be deployed;

[0032] The life-saving equipment deployment area constraint includes the position of each life-saving equipment satisfy:

[0033] ;

[0034] in, is a set of spatial areas where life-saving equipment can be arranged; the area coverage requirement includes that each area is covered by at least one life-saving equipment, and the coverage distance must meet certain requirements. To ensure the maximum distance for passengers to be rescued in time, for each area ,exist:

[0035] ;

[0036] in, In disaster scenes Next, area To distance to life-saving equipment;

[0037] The minimum distance limit of the life-saving equipment includes is the minimum distance between life-saving equipment. For any two life-saving equipment and , whose locations are and ,have:

[0038] ;

[0039] in, and Respectively represent and The components of the position of each lifesaving device in two-dimensional coordinates;

[0040] The efficiency constraint of the life-saving equipment includes introducing an efficiency index to measure the efficiency of the life-saving equipment. , the efficiency index is reflected in the disaster scene Next, area The efficiency of life-saving equipment in the interior of the building to serve passengers is is the prescribed minimum efficiency threshold, then: ;

[0041] The risk value constraints include the risk size of different regions meeting the following requirements:

[0042] ;

[0043] in, To adjust the disturbance variable For the control coefficient of regional risk impact, is the regional risk uncertainty set; is the regional risk function within the subway station, calculated using the following formula:

[0044] ;

[0045] in, is the critical speed of passenger instability, which is calculated by the following formula :

[0046] ;

[0047] ;

[0048] in, is the coefficient of static friction; is the passenger weight; is the acceleration due to gravity; is the slope of the ground; It is a preset constant related to the passenger shape characteristics and water flow characteristics; is the flow velocity of the flood; the regional risk uncertainty set is defined as:

[0049] ;

[0050] in, represents the I-dimensional real space, and is the disturbance variable Upper and lower bounds, is the risk volatility budget level, Used for calculation Its most likely value The deviation is defined as:

[0051] .

[0052] According to the method for optimizing the layout of life-saving facilities in subway stations under flood conditions provided by the present invention, solving the robustness optimization problem and determining the location and quantity of life-saving equipment include: Transformed into a finite system with clear convex constraints, the transformed regional risk volatility set The cone representation of is defined as:

[0053] ;

[0054] in, is the disturbance variable, , , Expressed as A zero matrix with 1 row and 1 column, is the linear transformation matrix, is the offset vector, is a convex set, and , belong dimensional real number space vector, is the regional risk value, so The corresponding dual cone is ; , for The diagonal matrix of represents the standard deviation of the regional risk volatility parameter, , express The inverse matrix of , is the risk volatility budget level and , is the linear transformation matrix, is the offset vector, and , so the corresponding dual cone is ;make , ,in, , ; and is an I-dimensional variable, and is a one-dimensional variable, so the semi-infinite constraint is:

[0055] ;

[0056] For each feasible solution of the semi-infinite constraint system, and Eliminate, be able to obtain , Similarly, if the system is used and replace and , the solution obtained is still a feasible solution; set the most likely value of the deviation Take the median of the upper and lower bounds of the deviation, and let , then converted into the formula:

[0057] ;

[0058] By introducing auxiliary variables , , which can be expressed as:

[0059] ;

[0060] in, and are corresponding auxiliary variables.

[0061] According to the method for optimizing the layout of life-saving facilities in a subway station during flooding provided by the present invention, solving the robustness optimization problem and determining the location and quantity of the life-saving equipment includes:

[0062] Determine the initial parameters and boundary conditions of the starfish optimization algorithm and set the population size to , the maximum number of iterations is , the switching probability between exploration and development phase is , the problem dimension is B. According to the actual area and constraints of the subway station where life-saving equipment can be arranged, the x-axis range of the plane is determined to be , the y-axis range is , and at the same time clarify the parameters in the constraint conditions; based on the initial parameters and the boundary conditions, randomly generate The position of the starfish individuals, the size of the composition is The position matrix:

[0063] ;

[0064] in, , indicating the The starfish individuals in dimension( Corresponding to the x-axis, corresponding to the y-axis), is At the same time, a random number between 1 and The integers between are used as the initial number of life-saving equipment to form a quantity vector ,in, Indicates the The number of life-saving equipment corresponding to each starfish individual;

[0065] The solver is used to solve the undetermined variables in the starfish optimization algorithm, and the fitness value of each starfish individual is calculated based on the solution results. The fitness function in the starfish optimization algorithm is as follows: ;

[0066] According to the robust optimization problem and the constraints, a solution model of a solver is constructed, and the solver solves the unresolved variables according to the constraints. , ensuring that the objective function value maintains optimal robustness under all disturbance conditions; substituting the result of the solver into the fitness function, calculating the fitness value of each starfish individual, so that the starfish optimization algorithm adjusts the equipment layout position and quantity according to the calculated fitness value and generates the next round of candidate solutions until the termination condition is met.

[0067] The present invention also provides a device for optimizing the layout of life-saving facilities in subway stations during floods, which is characterized by including: an acquisition unit, configured to acquire passenger location distribution data of a target subway station and disaster data during floods, wherein the disaster data includes water depth and water flow velocity information; an identification unit, configured to use a density-based spatial clustering algorithm with noise to model the passenger density information and identify areas with high passenger density; a division unit, configured to use a Bayesian network to divide areas within the subway station into different danger levels based on the passenger location distribution data and the disaster data; a construction unit, configured to construct a robust optimization problem based on the passenger high-density areas and the danger levels; and a solution unit, configured to solve the robust optimization problem and determine the location and quantity of the life-saving equipment.

[0068] The present invention provides a method, device, and electronic device for optimizing the layout of life-saving facilities in subway stations during flooding. By collecting passenger location information within the subway station and using a density-based spatial clustering algorithm with noise to accurately model passenger density, the method can efficiently identify key areas with high evacuation pressure, providing a scientific basis for the deployment of life-saving facilities. A Bayesian network is used to comprehensively consider the influence of multiple factors and accurately divide areas of different danger levels, providing reliable scientific guidance for facility layout. In terms of uncertainty management, a robust optimization problem is constructed by combining information on high-density areas and dangerous areas to determine the optimized location and quantity of life-saving equipment. Arranging life-saving facilities based on this problem can improve the subway station's ability to rescue passengers in flood situations. BRIEF DESCRIPTION OF THE DRAWINGS

[0069] In order to more clearly illustrate the technical solutions in the present invention or the prior art, a brief introduction is given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0070] Figure 1 It is a flow chart of the method for optimizing the layout of life-saving facilities in flood-prone subway stations provided by the present invention.

[0071] Figure 2 The present invention provides a flowchart for solving a robustness optimization problem and determining the optimal location and quantity of life-saving equipment by combining the Gurobi solver and the Starfish optimization algorithm.

[0072] Figure 3 It is a structural schematic diagram of the method for optimizing the layout of life-saving facilities in flood-prone subway stations provided by the present invention.

[0073] Figure 4 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0074] To make the objectives, technical solutions, and advantages of the present invention more clear, the technical solutions of the present invention will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the embodiments described are only some of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts shall fall within the scope of protection of the present invention.

[0075] Unless otherwise defined, the technical or scientific terms used in the present invention shall have the usual meaning understood by persons of ordinary skill in the field to which the present invention belongs. The words "first", "second" and similar terms used in the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. Similarly, words such as "one", "an" or "the" do not indicate a quantity limitation, but rather indicate the presence of at least one. Words such as "include" or "comprise" mean that the elements or objects preceding the word include the elements or objects listed after the word and their equivalents, without excluding other elements or objects. Words such as "connect" or "connected" are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect.

[0076] The following combination Figure 1-Figure 4 The present invention describes a method, device and electronic equipment for optimizing the layout of life-saving facilities in subway stations during flooding.

[0077] Figure 1 FIG. 1 is a flow chart of a method for optimizing the layout of life-saving facilities in a subway station during a flood provided by the present invention. Figure 1 As shown, the method includes the following:

[0078] Step 101: Obtain passenger location distribution data of a target subway station and disaster data during flooding.

[0079] In this embodiment, passenger location data can be acquired through high-precision monitoring equipment installed in subway stations, such as cameras with personnel location capabilities, to collect real-time passenger location information or extract a dataset containing all passenger location information within a specific time period from a system database. Disaster data includes water depth and flow velocity information, and other relevant information can be added as needed. Historical flood data for subway stations can be collected, which can be obtained from local hydrological departments, meteorological departments, and municipal management departments. The data content includes detailed information such as water depth, flow velocity, and duration at different locations within the subway station during previous floods. Alternatively, professional simulation software such as Ansys Fluent can be used to simulate subway station flooding scenarios. During the simulation process, a model is constructed based on parameters such as the actual building structure of the subway station, the surrounding terrain, and possible flood sources. By setting different boundary conditions such as flood flow and water level, various possible flooding scenarios are simulated to obtain corresponding environmental parameters such as water depth and flow velocity.

[0080] Step 102: Use a density-based spatial clustering algorithm with noise to model the passenger density information and identify high-density passenger areas.

[0081] In this embodiment, the Density-Based Spatial Clustering of Applications with Noise (DBSCAN) algorithm is a powerful unsupervised learning algorithm used to cluster data points based on density. DBSCAN does not require a predefined number of clusters and can identify clusters of varying shapes and sizes, making it particularly effective when working with complex datasets containing noise and outliers. Alternatively, it can be combined with the K-means clustering algorithm or by modeling passenger location data. By setting an initial number of cluster centers, iteratively optimizing cluster divisions, and setting a density threshold based on the ratio of the number of passengers within a cluster to the area of ​​the region, high-density areas can be identified.

[0082] Step 103: Based on the passenger location distribution data and the disaster data, the area within the subway station is divided into different danger levels using a Bayesian network.

[0083] In this embodiment, a Bayesian network is a powerful probabilistic graphical model used to describe the probabilistic dependencies between random variables. Furthermore, a fuzzy logic-based risk assessment model can be used to calculate regional risk values ​​using a fuzzy rule base and categorize them into low, medium, and high risk levels.

[0084] Step 104: Construct a robust optimization problem based on the high-density passenger area and the hazard level.

[0085] In this embodiment, there are many uncertain factors in the actual subway station flood scene, such as large fluctuations in passenger flow in real time, and the difficulty in accurately predicting the scale of the flood. In order to ensure that the life-saving equipment layout plan can ensure passenger safety in all possible disaster scenarios and achieve efficient resource allocation, a robust optimization method can be used. The core goal of robust optimization can be to comprehensively consider the passenger distribution and regional hazard level, determine the optimal placement position and quantity of life-saving equipment, so that in all possible disaster scenarios, the life-saving equipment can best protect passengers. The objective function of the robust optimization problem can be set according to actual needs, such as minimizing the comprehensive value of weighted risk and cost in all disaster scenarios, or comprehensively considering the passenger distribution and regional hazard level, determining the optimal placement position and quantity of life-saving equipment, so that in all possible disaster scenarios, the life-saving equipment can best protect passengers.

[0086] Step 105: Solve the robustness optimization problem to determine the location and quantity of life-saving equipment.

[0087] In this embodiment, the robustness optimization problem can be solved by using a genetic algorithm, or by combining a simulated annealing algorithm with a linear programming solver.

[0088] In some optional implementations, the passenger location distribution data includes a data set containing N passenger locations, and a density-based spatial clustering algorithm with noise is used to model the passenger density information to identify high-density passenger areas, including: extracting specific location information of each passenger from the data set containing the N passenger locations and expressing it as two-dimensional coordinates; determining the number of other passengers within the area of ​​each passenger based on the two-dimensional coordinates and a preset area radius; determining passengers whose locations are core points based on the number of other passengers within the area of ​​each passenger and a preset number threshold; for each passenger whose location is a core point, grouping all passengers within its neighborhood into the same cluster; and determining passengers whose locations are neither core points nor belonging to any cluster as noise points. Calculate the centroid coordinates of each cluster; use the centroid coordinates to set the density threshold based on the cluster area and the number of passengers in the cluster , filter out areas with density greater than the threshold as key high-density areas. The specific screening conditions are:

[0089] ;

[0090] in, represents the number of cluster regions, It is The density of cluster areas, It is The area of ​​the cluster region, It is The number of passengers in each cluster area; using the linear normalization method based on the minimum value, according to the pre-set maximum density value , for the filtered high-density areas , and normalize it by mapping it to the interval [0, 1] in a linear proportional manner. The specific calculation formula is:

[0091] ;

[0092] in, It is a normalized value, representing the passenger density weight of the area.

[0093] In this implementation, the number of other passengers within each passenger's area is determined based on the two-dimensional coordinates and the preset area radius. This can be determined based on Euclidean distance or other distances. For example, for each passenger position, , its position with other passengers can be calculated The Euclidean distance of:

[0094] ;

[0095] If the distance , then the passenger Located in the passenger In the neighborhood of , Represents the preset neighborhood radius; if a passenger The neighborhood of contains at least passengers, then the passenger's position is considered as a core point, specifically, point The point set contained in the neighborhood of satisfies the conditions:

[0096] ;

[0097] in, Indicates passengers Neighborhood; represents the number of passengers in the neighborhood; Indicates that to be a core point, the neighborhood must contain a minimum number of passengers.

[0098] For every passenger who can serve as a core point , all passengers in its neighborhood can be classified into the same cluster. As an example, for a core point passenger , the clustering process is as follows:

[0099] If the passenger If it is a core point, all passengers in its neighborhood are added to the cluster;

[0100] This process is repeated for each new core point in the neighborhood until all expandable passengers have been added.

[0101] If a passenger location is neither a core point nor belongs to any cluster, then the passenger will be considered a noise point. Noise points do not have enough neighbors to form a cluster, so they will be excluded from the cluster.

[0102] After processing with the DBSCAN algorithm, several density-connected clusters and some noise points are obtained. The cluster corresponds to a densely populated area with high evacuation pressure, which is a key area for the deployment of life-saving equipment. To accurately locate the center of the high-density area, first, the formula and Calculate the centroid coordinates of each cluster.

[0103]

[0104]

[0105] in, Indicates the clusters; It is clustering the number of passengers; and represent the abscissa and ordinate of the cluster centroid respectively; and It is The coordinates of the passengers.

[0106] In some optional implementations, based on passenger location distribution data and disaster data, a Bayesian network is used to divide areas within a subway station into different hazard levels. This includes determining variables that affect the hazard zone division, building dependencies between the variables, and forming a directed graph structure of the Bayesian network:

[0107] ;

[0108] Here, R represents the risk of the area, H represents the water depth, V represents the water velocity, D represents the degree of obstruction of the evacuation route, and P represents the passenger density. Based on the combination of pre-collected historical data and expert opinions, which may include water depth, water velocity, obstruction of evacuation routes, and passenger density data at different locations within the subway station during flooding, the conditional probability distribution of the following nodes is defined:

[0109] P(H): prior probability of water depth;

[0110] P(V): prior probability of water velocity;

[0111] P(P): prior probability of passenger density;

[0112] P(D|P): conditional probability between the degree of evacuation channel obstruction and passenger density;

[0113] P(R|H,V,D,P): conditional probability of risk in the scenario area;

[0114] Use Bayes’ theorem to calculate the posterior probability of the scene area risk:

[0115] ;

[0116] in, The joint probability of water depth, water velocity, evacuation channel obstruction and passenger density for a given area risk; is the prior probability of regional risk, which represents the basic probability of regional risk when there is no observation data; is the joint probability of water depth, water velocity, evacuation channel obstruction degree and passenger density; according to the chain rule, the joint probability It can be expressed as:

[0117] ;

[0118] Based on the posterior probability of each area obtained from the inference results, the risk level of each area is divided according to the preset risk probability threshold:

[0119] ;

[0120] in, and Risk thresholds are set based on historical data and safety standards.

[0121] In this implementation, variables that affect the division of dangerous areas may include water depth, water flow velocity, degree of blockage of evacuation channels, and passenger density. Variables may also be increased or decreased according to actual needs.

[0122] In some optional implementations, the objective function of the robustness optimization problem includes:

[0123] ;

[0124] in, A collection of all possible disaster scenarios. For different disaster scenarios The posterior probability of the lower risk reflects the actual situation that the subway station may face due to flooding; Represents the set of filtered high-density clustered areas; For disaster scenes Lower area Passenger density weight; For disaster scenes Lower area Value at Risk; For disaster scenes Next, area The distance to the nearest lifesaving device, which depends on where the lifesaving device is located and placement quantity , The maximum distance that passengers can be rescued is calculated by comparing the area The Euclidean distance between the center coordinates of and the positions of each life-saving equipment is selected as the minimum distance The value of Representatives at the disaster scene Next, for the area Costs incurred in equipping life-saving equipment; Budget for the maximum cost allowed; Used to normalize the cost, when the cost Approaching When , this term approaches 0, so as to balance the coverage effect and cost of life-saving equipment in the optimization process; It is a region Life-saving equipment in disaster scene The use efficiency of the following.

[0125] In some optional implementations, the constraints that need to be met when optimizing the robust optimization problem include: life-saving equipment quantity constraints, life-saving equipment layout area constraints, area coverage requirements, minimum distance restrictions for life-saving equipment, life-saving equipment utilization efficiency constraints, and risk value constraints;

[0126] In order to prevent the life-saving equipment from being too concentrated, it is necessary to ensure that a certain minimum distance is maintained between each life-saving equipment to improve the coverage and utilization efficiency of the equipment. Therefore, a life-saving equipment quantity constraint can be established. The life-saving equipment quantity constraint includes the number of life-saving equipment satisfy:

[0127] ;

[0128] in, The maximum number of life-saving appliances allowed to be deployed;

[0129] Lifesaving equipment can only be placed in the allowed areas within the subway station, so the lifesaving equipment placement area constraint can include the location of each lifesaving equipment satisfy:

[0130] ;

[0131] in, A collection of space areas where life-saving equipment can be arranged;

[0132] To ensure that passengers in the area can be rescued in time, the area coverage requirement includes that each area is covered by at least one life-saving device, and the coverage distance must meet certain requirements. To ensure the maximum distance for passengers to be rescued in time, for each area ,exist:

[0133] ;

[0134] in, In disaster scenes Next, area To distance to life-saving equipment;

[0135] In order to prevent the life-saving equipment from being too concentrated, it is necessary to ensure that a certain minimum distance is maintained between each life-saving equipment to improve the coverage and efficiency of the equipment. is the minimum distance between life-saving equipment. For any two life-saving equipment and , whose locations are and ,have:

[0136] ;

[0137] in, and Respectively represent and The components of the position of each lifesaving device in two-dimensional coordinates;

[0138] The efficiency constraint of life-saving equipment includes the introduction of efficiency indicators to measure the efficiency of life-saving equipment. , efficiency indicators are reflected in disaster scenarios Next, area The efficiency of life-saving equipment in the interior of the building to serve passengers is is the prescribed minimum efficiency threshold, then:

[0139] ;

[0140] Risk value constraints include the risk size of different regions meeting the following requirements:

[0141] ;

[0142] in, To adjust the disturbance variable For the control coefficient of regional risk impact, is the regional risk uncertainty set; is the regional risk function within the subway station, calculated using the following formula:

[0143] ;

[0144] Among them, when a flood occurs, when the life-saving equipment is being used for rescue, the passengers are very likely to slip or even fall down during the rescue. Set the critical speed for passenger instability , calculated by the following formula :

[0145] ;

[0146] ;

[0147] in, is the coefficient of static friction; is the passenger weight; is the acceleration due to gravity; is the slope of the ground; It is a preset constant related to the passenger shape characteristics and water flow characteristics; is the flow velocity of the flood; the regional risk uncertainty set is defined as:

[0148] ;

[0149] in, represents the I-dimensional real space, and is the disturbance variable Upper and lower bounds, is the risk volatility budget level, Used for calculation Its most likely value The deviation is defined as:

[0150] .

[0151] In some optional implementations, since most common uncertainty sets are continuous sets rather than discrete sets, the original model can be transformed to a certain extent, transforming it into a finite system with clear convex constraints, so that the transformed model can be solved directly. Solve the robust optimization problem to determine the location and quantity of life-saving equipment, including: transforming the regional risk uncertainty set into a finite system with clear convex constraints. Transformed into a finite system with clear convex constraints, the transformed regional risk volatility set The cone representation of is defined as:

[0152] ;

[0153] in, is the disturbance variable, , , Expressed as A zero matrix with 1 row and 1 column, is the linear transformation matrix, is the offset vector, is a convex set, and , belong dimensional real number space vector, is the regional risk value, so The corresponding dual cone is ; , for The diagonal matrix of represents the standard deviation of the regional risk volatility parameter, , express The inverse matrix of , is the risk volatility budget level and , is the linear transformation matrix, is the offset vector, and , so the corresponding dual cone is ;make , ,in, , ; and is an I-dimensional variable, and is a one-dimensional variable, so the semi-infinite constraint is:

[0154] ;

[0155] For each feasible solution of the semi-infinite constraint system, and Eliminate, be able to obtain , Similarly, if the system is used and replace and , the solution obtained is still a feasible solution; set the most likely value of the deviation Take the median of the upper and lower bounds of the deviation, and let , then converted into the formula:

[0156] ;

[0157] By introducing auxiliary variables , , which can be expressed as:

[0158] ;

[0159] in, and are corresponding auxiliary variables.

[0160] This implementation combines information about high-density and hazardous areas to formulate a robust optimization problem. To address issues such as passenger flow fluctuations and uncertainty in flood scale in flood scenarios, the optimization objective function comprehensively considers passenger distribution and regional risk, incorporating multiple constraints such as the number of life-saving devices, deployment area, coverage requirements, device spacing, utilization efficiency, and risk value. Through model transformation, the optimization problem is formulated as a solvable robust equivalence, ensuring the solution's effectiveness under a variety of uncertain scenarios, thereby maximizing passenger safety.

[0161] In some optional implementations, solving the robustness optimization problem and determining the location and quantity of life-saving equipment include: determining the initial parameters and boundary conditions of the starfish optimization algorithm, setting the population size to , the maximum number of iterations is , the switching probability between exploration and development phase is , the problem dimension is B. According to the actual area and constraints of the subway station where life-saving equipment can be arranged, the x-axis range of the plane is determined to be , the y-axis range is , and specify the parameters in the constraints, for example, 、 、 、 as well as ; Based on the initial parameters and boundary conditions, randomly generate The position of the starfish individuals, the size of the composition is The position matrix:

[0162] ;

[0163] in, , indicating the The starfish individuals in dimension( Corresponding to the x-axis, corresponding to the y-axis), is At the same time, a random number between 1 and The integers between are used as the initial number of life-saving equipment to form a quantity vector ,in, Indicates the The number of life-saving equipment corresponding to each starfish individual; the solver is used to solve the undetermined variables in the starfish optimization algorithm, and the fitness value of each starfish individual is calculated based on the solution results. The fitness function in the starfish optimization algorithm is as follows:

[0164] ;

[0165] According to the robust optimization problem and constraints, a solver model is constructed, and the solver solves the undetermined variables according to the constraints. , ensuring that the objective function value maintains optimal robustness under all disturbance conditions; substituting the solver's results into the fitness function, calculating the fitness value of each starfish individual, so that the starfish optimization algorithm adjusts the equipment layout position and quantity according to the calculated fitness value and generates the next round of candidate solutions until the termination condition is met.

[0166] In this implementation, if the passenger distribution and regional hazard level are comprehensively considered, and the constraints on the number of life-saving equipment, the area where the life-saving equipment is placed, the area coverage requirements, the minimum distance limit for the life-saving equipment, the efficiency constraint of the life-saving equipment, and the risk value constraint are met at the same time, the robust equivalent model form that can be converted from the robust optimization model to determine the optimal placement position and number of life-saving equipment is:

[0167] ;

[0168] The StarFish Optimization Algorithm (SFOA) is a new meta-heuristic algorithm inspired by the exploration, predation, and regeneration behaviors of starfish. When solving the robust optimization problem of the layout of flood-related life-saving equipment in subway stations, the StarFish Optimization Algorithm uses a global search by randomly generating an initial population, a diversified strategy in the development phase to avoid local optimality, and the advantages of the Gurobi solver. It can also dynamically adapt to uncertain factors. It can efficiently determine the optimal location and quantity of life-saving equipment that takes into account both coverage and cost. As an example, its optimization process is as follows: Figure 2 As shown in Figure 1, the following steps are included: Substituting the solver results into the fitness function, calculating the fitness value of each starfish individual, and feeding it back to the starfish optimization algorithm. The starfish optimization algorithm adjusts the device layout and quantity based on the fitness value and proceeds to step 1 to generate the next round of candidate solutions. The above process is repeated until the termination condition is met.

[0169] Step 1: Determine the conditions and enter the iteration phase. The specific contents include:

[0170] Step 1-1: If , the starfish individual enters the exploration phase and updates its position using the following formula:

[0171] ;

[0172] in, and Respectively represent the horizontal and vertical coordinates of the updated position; Indicates the current iteration number; and Respectively represent the horizontal and vertical coordinates of the current optimal position, which guides the starfish individual to move to a possible better position; is with Mutually independent random numbers; and By the following formulas respectively Perform the calculation:

[0173] ;

[0174] .

[0175] After updating the location, ,like Out of bounds (i.e. or ),but ,otherwise This ensures that the position of each starfish is always within the deployable area. After completing the exploration phase for that individual, the algorithm moves on to the next starfish, or enters the development phase after all individuals have completed the exploration phase.

[0176] Step 1-2: If , then the starfish enters the development stage. The development stage includes two strategies: predation and regeneration.

[0177] Predation strategy: Calculate the five distances between each starfish individual and the current global optimal position :

[0178] ;

[0179] in, It is from Five individuals are randomly selected from the starfish individuals, and each selection is independent of each other. For each starfish individual, two distances are randomly selected. and , update its position:

[0180] ;

[0181] in, and is The random number within is independent of other random numbers.

[0182] In this way, As the updated position vector, combined with the current position With two randomly selected distance vectors and By updating the position, the starfish individuals have the opportunity to move to a better guidance solution, while some individuals may also move backward, which helps to escape the local optimum. ,like If it exceeds the boundary, ,otherwise .

[0183] Regeneration strategy: The regeneration phase is only in the last starfish individual in the population ( ), the position update formula is:

[0184]

[0185] Step 2: Iteration and termination:

[0186] Iteration process: Each iteration, first according to the random number and The comparison results determine whether to proceed to the exploration phase or the exploitation phase. After updating the positions of the starfish individuals and the corresponding number of life-saving devices, the Gurobi solver is re-invoked to solve for the unresolved variables and calculate the fitness values ​​of all starfish individuals. The optimal solution is found, which is the position and number of starfish individuals with the highest fitness value. The optimal fitness value, position, and number of each iteration are recorded.

[0187] Termination condition: set a smaller threshold , when continuous The change in the optimal fitness value of the iteration is less than When , the algorithm is considered to have converged and the iteration stops. , then stop the iteration and output the optimal position at this time and the corresponding optimal number of life-saving equipment ,in, It is The optimal fitness value of the iteration, It is The optimal fitness value of the iteration.

[0188] The following describes the device for optimizing the layout of life-saving facilities in subway stations during floods provided by the present invention. The device for optimizing the layout of life-saving facilities in subway stations during floods described below and the method for optimizing the layout of life-saving facilities in subway stations during floods described above can be referenced to each other.

[0189] Figure 3 The schematic diagram of the structure of the device for optimizing the layout of life-saving facilities in flood-prone subway stations provided in the embodiment of the present application is as follows: Figure 3 As shown, it specifically includes: an acquisition unit 301, which is configured to obtain the passenger location distribution data of the target subway station and the disaster data during the flood, and the disaster data includes water depth and water flow velocity information; an identification unit 302, which is configured to use a density-based spatial clustering algorithm with noise to model the passenger density information and identify high-density passenger areas; a division unit 303, which is configured to use a Bayesian network to divide the area in the subway station into different danger levels according to the passenger location distribution data and the disaster data; a construction unit 304, which is configured to construct a robust optimization problem based on the high-density passenger areas and the danger levels; a solution unit 305, which is configured to solve the robust optimization problem and determine the location and quantity of the life-saving equipment.

[0190] The device for optimizing the layout of life-saving facilities in subway stations during floods provided by the present invention determines the optimized location and quantity of life-saving equipment by constructing and solving a robust optimization problem. The layout of life-saving facilities based on this can improve the subway station's ability to rescue passengers in flood situations.

[0191] Figure 4 An example of a physical structure diagram of an electronic device is shown below. Figure 4 As shown, the electronic device may include: a processor 410, a communications interface 420, a memory 430, and a communications bus 440, wherein the processor 410, the communications interface 420, and the memory 430 communicate with each other via the communications bus 440. The processor 410 may call logic instructions in the memory 430 to execute a method for optimizing the placement of life-saving facilities in a subway station during a flood. The method includes: obtaining passenger location distribution data and flood disaster data at a target subway station, the disaster data including water depth and water velocity information; modeling the passenger density information using a density-based spatial clustering algorithm with noise to identify high-density passenger areas; using a Bayesian network to divide areas within the subway station into different hazard levels based on the passenger location distribution data and the hazard data; constructing a robust optimization problem based on the high-density passenger areas and hazard levels; and solving the robust optimization problem to determine the placement and quantity of life-saving equipment.

[0192] Furthermore, the logic instructions in the aforementioned memory 430 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the portion that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product, stored in a storage medium, includes instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as a USB flash drive, a mobile hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0193] On the other hand, the present invention also provides a computer program product, which includes a computer program, which can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the method for optimizing the layout of life-saving facilities in subway stations under floods provided by the above methods. The method includes: obtaining passenger location distribution data of the target subway station and disaster data during floods, the disaster data including water depth and water flow velocity information; using a density-based spatial clustering algorithm with noise to model passenger density information and identify high-density passenger areas; using a Bayesian network to divide areas within the subway station into different danger levels based on passenger location distribution data and disaster data; constructing a robust optimization problem based on high-density passenger areas and danger levels; solving the robust optimization problem to determine the location and quantity of life-saving equipment.

[0194] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to execute the method for optimizing the layout of life-saving facilities in subway stations during floods provided by the above-mentioned methods, the method comprising: obtaining passenger location distribution data of the target subway station and disaster data during floods, the disaster data including water depth and water flow velocity information; using a density-based spatial clustering algorithm with noise to model the passenger density information and identify areas with high passenger density; using a Bayesian network to divide areas within the subway station into different danger levels based on the passenger location distribution data and disaster data; constructing a robust optimization problem based on the areas with high passenger density and the danger levels; solving the robust optimization problem and determining the location and quantity of the life-saving equipment.

[0195] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, i.e., they may be located in one location or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of the present embodiment. Persons of ordinary skill in the art will be able to understand and implement the present invention without inventive effort.

[0196] Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented using software plus a necessary general-purpose hardware platform, or of course, hardware. Based on this understanding, the essence of the above technical solution, or the portion that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, or an optical disk, and includes a number of instructions for causing a computer device (such as a personal computer, server, or network device) to execute the methods described in each embodiment or certain portions of the embodiments.

[0197] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A method for optimizing the layout of life-saving facilities in flood-prone subway stations, characterized in that: include: Obtaining passenger location distribution data of a target subway station and flood disaster data, wherein the disaster data includes water depth and water flow velocity information; Using a density-based spatial clustering algorithm with noise to model the passenger density information and identify high-density passenger areas; Dividing the area within the subway station into different danger levels using a Bayesian network based on the passenger location distribution data and the disaster data; Constructing a robust optimization problem based on the high passenger density area and the hazard level; Solving the robust optimization problem to determine the location and quantity of life-saving equipment; The objective function of the robustness optimization problem includes: ； in, A collection of all possible disaster scenarios, For different disaster scenarios The posterior probability of the lower risk reflects the actual situation that the subway station may face due to flooding; Represents the set of filtered high-density clustered areas; For disaster scenes Lower area Passenger density weight; For disaster scenes Lower area Value at Risk; For disaster scenes Next, area The distance to the nearest lifesaving device, which depends on where the lifesaving device is located and placement quantity , The maximum distance that passengers can be rescued is calculated by comparing the area The Euclidean distance between the center coordinates of and the positions of each life-saving equipment is selected as the minimum distance The value of Representatives at the disaster scene Next, for the area Costs incurred in equipping life-saving equipment; Budget for the maximum cost allowed; Used to normalize the cost, when the cost Approaching When , this term approaches 0, so as to balance the coverage effect and cost of life-saving equipment in the optimization process; It is a region Life-saving equipment in disaster scene The efficiency of use, is the disturbance variable; Among them, when optimizing the robust optimization problem, the constraints that need to be met include: life-saving equipment quantity constraint, life-saving equipment layout area constraint, area coverage requirement, minimum distance limit of life-saving equipment, life-saving equipment utilization efficiency constraint, and risk value constraint.

2. The method for optimizing the layout of life-saving facilities in subway stations during flooding according to claim 1, characterized in that: The passenger location distribution data includes a data set containing N passenger locations. The method of using a density-based spatial clustering algorithm with noise to model the passenger density information and identify high-density passenger areas includes: Extracting specific location information of each passenger from the dataset containing N passenger locations and representing it as two-dimensional coordinates; Determine the number of other passengers within each passenger's area based on the two-dimensional coordinates and a preset area radius; Determine the passengers whose positions are core points according to the number of other passengers contained in the area of ​​each passenger and a preset number threshold; For each passenger whose position is a core point, all passengers in its neighborhood are grouped into the same cluster; Passengers whose locations are neither core points nor belong to any cluster are identified as noise points; (4) Calculate the centroid coordinates of each cluster; Using the centroid coordinates, a density threshold is set based on the cluster area and the number of passengers in the cluster. , filter out areas with density greater than the threshold as key high-density areas. The specific screening conditions are: ； in, represents the number of cluster regions, It is The density of cluster areas, It is The area of ​​the cluster region, It is The number of passengers in each cluster area; Use the minimum-based linear normalization method to adjust the maximum density value according to the preset value. , for the filtered high-density areas , and normalize it by mapping it to the [0,1] interval in a linear proportional manner. The specific calculation formula is: ； in, It is a normalized value, representing the passenger density weight of the area.

3. The method for optimizing the layout of life-saving facilities in flood-prone subway stations according to claim 1, characterized in that: The method of dividing the area within the subway station into different danger levels using a Bayesian network based on the passenger location distribution data and the disaster data includes: Determine the variables that affect the division of dangerous areas, build the dependency relationship between variables, and form a directed graph structure of the Bayesian network: ； in, R Indicates the risk of the area, H Indicates water depth, V Indicates water flow velocity, D Indicates the degree of obstruction of the evacuation channel, P represents the passenger density; Based on the combination of pre-collected historical data and expert opinions, the conditional probability distribution of the following nodes is defined: P ( H ): prior probability of water depth; P ( V ): prior probability of water flow velocity; P ( P ): prior probability of passenger density; P ( D | P ): the conditional probability between the degree of evacuation channel obstruction and passenger density; P ( R|H,V,D,P ): conditional probability of scenario area risk; Use Bayes’ theorem to calculate the posterior probability of the scene area risk: ； in, The joint probability of water depth, water velocity, evacuation channel obstruction and passenger density for a given area risk; is the prior probability of regional risk, which represents the basic probability of regional risk when there is no observation data; is the joint probability of water depth, water velocity, evacuation channel obstruction degree and passenger density; according to the chain rule, the joint probability Expressed as: ； Based on the posterior probability of each area obtained from the inference results, the risk level of each area is divided according to the preset risk probability threshold: ； in, and Risk thresholds are set based on historical data and safety standards.

4. The method for optimizing the layout of life-saving facilities in flood-prone subway stations according to claim 1, characterized in that: The life-saving equipment quantity constraint includes the quantity of life-saving equipment satisfy: ； in, The maximum number of life-saving appliances allowed to be deployed; The life-saving equipment deployment area constraint includes the position of each life-saving equipment satisfy: ； in, A collection of space areas where life-saving equipment can be arranged; The area coverage requirement includes that each area is covered by at least one life-saving device, and the coverage distance must meet certain requirements. To ensure the maximum distance for passengers to be rescued in time, for each area ,exist: ； in, In disaster scenes Next, area To distance to life-saving equipment; The minimum distance limit of the life-saving equipment includes is the minimum distance between life-saving equipment. For any two life-saving equipment and , whose locations are and ,have: ； in, and Respectively represent and The components of the position of each lifesaving device in two-dimensional coordinates; The efficiency constraint of the life-saving equipment includes introducing an efficiency index to measure the efficiency of the life-saving equipment. , the efficiency index is reflected in the disaster scene Next, area The efficiency of life-saving equipment in the interior of the building to serve passengers is is the prescribed minimum efficiency threshold, then: ； The risk value constraints include the risk size of different regions meeting the following requirements: ； in, To adjust the disturbance variable For the control coefficient of regional risk impact, is the regional risk uncertainty set; is the regional risk function within the subway station, calculated using the following formula: ； in, is the critical speed of passenger instability, which is calculated by the following formula (19): ； ； in, is the coefficient of static friction; is the passenger weight; is the acceleration due to gravity; is the slope of the ground; It is a preset constant related to the passenger shape characteristics and water flow characteristics; is the flow velocity of the flood; the regional risk uncertainty set is defined as: ； in, express I dimensional real space, and is the disturbance variable Upper and lower bounds, is the risk volatility budget level, Used for calculation Its most likely value The deviation is defined as: 。 5. The method for optimizing the layout of life-saving facilities in flood-prone subway stations according to claim 4, characterized in that: Solving the robustness optimization problem to determine the location and quantity of life-saving equipment includes: Regional risk uncertainty Transformed into a finite system with clear convex constraints, the transformed regional risk volatility set The cone representation of is defined as: ； in, is the disturbance variable, , , Expressed as A zero matrix with 1 row and 1 column, is the linear transformation matrix, is the offset vector, is a convex set, and , belong dimensional real number space vector, is the regional risk value, so The corresponding dual cone is ; , for The diagonal matrix of represents the standard deviation of the regional risk volatility parameter, , express The inverse matrix of , is the risk volatility budget level and , is the linear transformation matrix, is the offset vector, and , so the corresponding dual cone is ;make , ,in, , ; and for I dimensional variables, and is a one-dimensional variable, so the semi-infinite constraint is: ； For each feasible solution of the semi-infinite constraint system, and Eliminate, be able to obtain , Similarly, if the system is used and replace and , the solution obtained is still a feasible solution; set the most likely value of the deviation Take the median of the upper and lower bounds of the deviation, and let , then converted into the formula: ； By introducing auxiliary variables , , which can be expressed as: ； in, and are corresponding auxiliary variables.

6. The method for optimizing the layout of life-saving facilities in subway stations during flooding according to claim 5, characterized in that: Solving the robustness optimization problem to determine the location and quantity of life-saving equipment includes: Determine the initial parameters and boundary conditions of the starfish optimization algorithm and set the population size to , the maximum number of iterations is , the switching probability between exploration and development phase is , the problem dimension is B , determine the plane according to the actual area and constraints of the subway station where life-saving equipment can be arranged. x The axis range is , y The axis range is , while clarifying the parameters in the constraints; Based on the initial parameters and the boundary conditions, randomly generate The position of the starfish individuals, the size of the composition is The position matrix: ； in, , indicating the The starfish individuals The location of the dimension, correspond x axis, correspond y axis, is At the same time, a random number between 1 and The integers between are used as the initial number of life-saving equipment to form a quantity vector ,in, Indicates the The number of life-saving equipment corresponding to each starfish individual; The solver is used to solve the undetermined variables in the starfish optimization algorithm, and the fitness value of each starfish individual is calculated based on the solution results. The fitness function in the starfish optimization algorithm is as follows: ； According to the robust optimization problem and the constraints, a solution model of a solver is constructed, and the solver solves the unresolved variables according to the constraints. , ensuring that the objective function value remains robust and optimal under all disturbances; The result of the solver is substituted into the fitness function to calculate the fitness value of each starfish individual, so that the starfish optimization algorithm adjusts the equipment layout position and quantity according to the calculated fitness value and generates the next round of candidate solutions until the termination condition is met.

7. A device for optimizing the layout of life-saving facilities in case of a subway station flood, used to execute the method for optimizing the layout of life-saving facilities in case of a subway station flood according to claim 1, characterized in that: include: an acquisition unit configured to acquire passenger location distribution data of a target subway station and disaster data during a flood, wherein the disaster data includes water depth and water flow velocity information; an identification unit configured to model the passenger density information using a density-based spatial clustering algorithm with noise, and identify high-density passenger areas; a division unit configured to divide areas within the subway station into different danger levels using a Bayesian network based on the passenger location distribution data and the disaster data; a construction unit configured to construct a robustness optimization problem based on the high passenger density area and the risk level; The solving unit is configured to solve the robust optimization problem and determine the installation location and quantity of the life-saving equipment.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the method for optimizing the layout of life-saving facilities in subway stations during flooding according to any one of claims 1 to 6 is implemented.

9. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the method for optimizing the layout of life-saving facilities in subway stations during flooding as claimed in any one of claims 1 to 6 is implemented.

Images