A fire evacuation path planning method and system based on A*-EACO algorithm

Abstract

The present application provides a fire evacuation path planning method and system based on A*-enhanced ant colony algorithm, which obtains a two-dimensional plan of a building, and establishes an environmental model based on the two-dimensional plan using a 0-1 grid method; determines the node coordinates of each grid based on the environmental model; determines the node area based on the start node and target node selected by the user using the A* algorithm; determines the next path node based on the node area; wherein the path node contains pheromones; determines the pheromone evaporation factor based on the maximum number of iterations and the current number of iterations, and updates the pheromone based on the pheromone evaporation factor; when the current number of iterations reaches the maximum number of iterations, outputs the target evacuation path with the shortest distance. The pheromone evaporation factor is improved through a nonlinear decreasing strategy, and the pheromone is updated, thereby reducing the complexity of the problem, improving the algorithm's search capability, and reducing the complexity of solving the fire evacuation path problem.

Description

Technical Field

[0001] The present application relates to the field of dynamic planning of fire evacuation paths, and in particular to a fire evacuation path planning method and system based on the A*-EACO algorithm. Background Art

[0002] Building fires are a constant threat to public safety, causing massive property losses and casualties. When a fire occurs, smoke spreads rapidly inside the building due to the complexity of the building structure and materials, making evacuation more difficult. Therefore, an optimal fire evacuation route is particularly important.

[0003] The goal of fire evacuation path planning technology is to plan an optimal path from the starting point to the end point that is away from the fire source and has no obstacles. Existing fire evacuation path planning algorithms are mainly divided into two categories: traditional algorithms and swarm intelligence algorithms. Among them, traditional algorithms mainly include grid method, Dijkstra algorithm, A* algorithm, etc. Swarm intelligence algorithms mainly include particle swarm algorithm, genetic algorithm and ant colony algorithm, etc. In the problem of fire evacuation path planning, traditional algorithms can find a good fire evacuation path in simple buildings, but the path planning ability in complex buildings is poor. Swarm intelligence algorithms have better evacuation effects in complex buildings, but such algorithms usually have problems such as premature convergence and easy to fall into local optimality. Therefore, exploring new path planning algorithms has become a hot topic of research. Summary of the invention

[0004] In view of the above problems, the present application is proposed to provide a fire evacuation path planning method and system of an A*-EACO algorithm that overcomes the above problems or at least partially solves the above problems, including:

[0005] A fire evacuation path planning method based on A*-EACO algorithm, the method comprising:

[0006] Obtaining a two-dimensional plan view of a target building, and establishing an environmental model using a 0-1 grid method based on the two-dimensional plan view;

[0007] Determining the node coordinates of each grid according to the environmental model;

[0008] The node area is determined using the A* algorithm based on the start node and target node selected by the user;

[0009] Determining a maximum number of iterations according to the node area, and determining a next path node in the node area; wherein the path node contains pheromones;

[0010] Determine a pheromone evaporation factor according to the maximum number of iterations and the current number of iterations, and update the pheromone according to the pheromone evaporation factor;

[0011] When the current number of iterations reaches the maximum number of iterations, the target evacuation path with the shortest distance is output.

[0012] Furthermore, the step of determining the pheromone evaporation factor according to the maximum number of iterations and the current number of iterations includes:

[0013] Determining an initial pheromone evaporation factor according to the current number of iterations;

[0014] The pheromone evaporation factor is determined according to the initial pheromone evaporation factor, the maximum number of iterations and the current number of iterations.

[0015] Furthermore, the step of updating the pheromone according to the pheromone evaporation factor comprises:

[0016] Determining a pheromone increment according to the current number of iterations;

[0017] The pheromone is updated according to the pheromone increment and the pheromone evaporation factor.

[0018] Furthermore, the step of determining the node coordinates of each grid according to the environmental model includes:

[0019] Determining the number of each grid according to the environmental model;

[0020] The corresponding node coordinates are determined according to the number.

[0021] Furthermore, the step of determining the node area using the A* algorithm based on the start node and the target node selected by the user includes:

[0022] Determining an actual cost based on the starting node and the current node;

[0023] Determining an estimated cost based on the current node and the target node;

[0024] Determining a path cost based on the actual cost and the estimated cost;

[0025] The node area is determined according to the path cost.

[0026] Furthermore, the formula for determining the next path node in the node area is as follows:

[0027]

[0028] In the formula, represents the probability of ant k going from node i to the next path node j at time t; C represents the set of nodes that can be visited in the next step; η ij (t) represents the heuristic function, where η ij(t) = 1 / d ij , d ij represents the distance between nodes i and j; α is the pheromone importance factor; β is the heuristic function importance factor.

[0029] Furthermore, when the current number of iterations reaches the maximum number of iterations, the step of outputting the target evacuation path with the shortest distance comprises:

[0030] When the path node is a target node, the pheromone on the path is updated, and the length of the target path from the starting node to the path node is determined;

[0031] When the current number of iterations reaches the maximum number of iterations, an evacuation path set is generated according to the target path;

[0032] Determine the target evacuation path with the shortest distance in the evacuation path set.

[0033] A fire evacuation path planning system based on A*-EACO algorithm, the system comprising:

[0034] An environmental modeling module is used to obtain a two-dimensional plan view of a target building and establish an environmental model using a 0-1 grid method based on the two-dimensional plan view;

[0035] A coordinate calculation module, used to determine the node coordinates of each grid according to the environmental model;

[0036] The first optimization module is used to determine the node area using the A* algorithm according to the starting node and the target node selected by the user;

[0037] A transfer module, used to determine the maximum number of iterations according to the node area, and determine the next path node in the node area; wherein the path node contains pheromone;

[0038] A second optimization module is used to determine a pheromone evaporation factor according to the maximum number of iterations and the current number of iterations, and to update the pheromone according to the pheromone evaporation factor;

[0039] The path output module is used to output a target evacuation path with the least nodes and the shortest distance when the current number of iterations reaches the maximum number of iterations.

[0040] A computer device comprises a processor, a memory and a computer program stored in the memory and capable of running on the processor, wherein when the computer program is executed by the processor, the steps of a fire evacuation path planning method based on the A*-EACO algorithm as described above are implemented.

[0041] A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of a fire evacuation path planning method based on the A*-EACO algorithm as described above are implemented.

[0042] This application has the following advantages:

[0043] In an embodiment of the present application, a two-dimensional plan of a building is obtained, and an environmental model is established based on the two-dimensional plan using a 0-1 grid method; the node coordinates of each grid are determined based on the environmental model; the node area is determined using an A* algorithm based on the start node and target node selected by the user; the maximum number of iterations is determined based on the node area, and the next path node is determined in the node area; wherein the path node contains pheromones; the pheromone evaporation factor is determined based on the maximum number of iterations and the current number of iterations, and the pheromone is updated based on the pheromone evaporation factor; when the current number of iterations reaches the maximum number of iterations, the target evacuation path with the shortest distance is output. The pheromone evaporation factor is improved through a nonlinear decreasing strategy, and the pheromone is updated, thereby reducing the complexity of the problem, improving the algorithm's search capability, and reducing the complexity of solving the fire evacuation path problem. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the technical solution of the present application, the drawings required for use in the description of the present application will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0045] Figure 1 It is a flowchart of a method for planning a fire evacuation path based on the A*-EACO ant colony algorithm according to an embodiment of the present application;

[0046] Figure 2 It is a grid map of a two-dimensional plane model of a target building provided by an embodiment of the present application;

[0047] Figure 3 It is a 0-1 distribution grid diagram of a two-dimensional plane model of a target building provided by an embodiment of the present application;

[0048] Figure 4 This is a schematic diagram of an 8-neighborhood search provided by an embodiment of the present application;

[0049] Figure 5 It is a flowchart of a fire evacuation path planning method based on the A*-EACO algorithm provided in one embodiment of the present application;

[0050] Figure 6aIt is a fire evacuation path planning diagram of the A* algorithm provided in an embodiment of the present application;

[0051] Figure 6b It is an iterative graph of fire evacuation path planning of the A* algorithm provided in an embodiment of the present application;

[0052] Figure 6c It is a schematic diagram of a node area of ​​an A* algorithm provided in an embodiment of the present application;

[0053] Figure 7a It is a fire evacuation path planning diagram of the ACO algorithm provided in an embodiment of the present application;

[0054] Figure 7b It is an iterative diagram of fire evacuation path planning of the ACO algorithm provided in an embodiment of the present application;

[0055] Figure 8a It is a fire evacuation path planning diagram of the A*-EACO algorithm provided in an embodiment of the present application;

[0056] Figure 8b It is an iterative diagram of fire evacuation path planning of the A*-EACO algorithm provided in one embodiment of the present application;

[0057] Figure 9a It is a fire evacuation path planning diagram of the A*-EACO algorithm when a fire occurs, provided in an embodiment of the present application;

[0058] Figure 9b It is an iterative diagram of fire evacuation path planning of the A*-EACO algorithm when a fire occurs, provided in one embodiment of the present application;

[0059] Fig.10 It is a structural block diagram of a fire evacuation path planning system based on the A*-EACO algorithm provided in one embodiment of the present application;

[0060] Fig.11 It is a structural schematic diagram of a computer device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0061] In order to make the objects, features and advantages of the present application more obvious and understandable, the present application is further described in detail below in conjunction with the accompanying drawings and specific implementation methods. Obviously, the described embodiments are part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work are within the scope of protection of the present application.

[0062] Reference Figure 1 , showing a fire evacuation path planning method based on A*-EACO ant colony algorithm provided by an embodiment of the present application;

[0063] The method comprises:

[0064] S110, obtaining a two-dimensional plan view of the target building, and establishing an environment model using a 0-1 grid method according to the two-dimensional plan view;

[0065] S120, determining the node coordinates of each grid according to the environmental model;

[0066] S130, determining the node area using the A* algorithm according to the starting node and the target node selected by the user;

[0067] S140, determining a maximum number of iterations according to the node area, and determining a next path node in the node area; wherein the path node contains pheromones;

[0068] S150, determining a pheromone evaporation factor according to the maximum number of iterations and the current number of iterations, and updating the pheromone according to the pheromone evaporation factor;

[0069] S160: When the current number of iterations reaches the maximum number of iterations, outputting a target evacuation path with the shortest distance.

[0070] In an embodiment of the present application, a two-dimensional plan of a building is obtained, and an environmental model is established based on the two-dimensional plan using a 0-1 grid method; the node coordinates of each grid are determined based on the environmental model; the node area is determined using an A* algorithm based on the start node and the target node selected by the user; the maximum number of iterations is determined based on the node area, and the next path node is determined in the node area; wherein the path node contains pheromones; the pheromone evaporation factor is determined based on the maximum number of iterations and the current number of iterations, and the pheromone is updated based on the pheromone evaporation factor; when the current number of iterations reaches the maximum number of iterations, the target evacuation path with the shortest distance is output. The pheromone evaporation factor is improved by a nonlinear decreasing strategy, and the pheromone is updated. This strategy makes the algorithm nonlinear in the optimization process, reducing the complexity of the problem. Therefore, the nonlinear decreasing strategy can better improve the algorithm's search capability and reduce the complexity of solving the fire evacuation path problem.

[0071] Next, a fire evacuation path planning method based on the A*-EACO algorithm in this exemplary embodiment will be further described.

[0072] As described in step S110, a two-dimensional plan view of the target building is obtained, and an environment model is established based on the two-dimensional plan view using a 0-1 grid method.

[0073] In one embodiment of the present invention, the specific process of "obtaining a two-dimensional plan view of the target building, and establishing an environment model by using a 0-1 grid method according to the two-dimensional plan view" in step S110 can be further explained in combination with the following description.

[0074] As an example, in order to implement the algorithm in the planning of fire evacuation routes in buildings, we need to make the following assumptions about the environment inside the building: (1) Assume that the fire evacuation route environment is a top view of a certain floor in a building, that is, a two-dimensional plane; (2) The rooms in the building are set as obstacles, and the positions of the rooms are fixed and represented by polygons; (3) During the fire evacuation process, the escapees move at a uniform speed, and this process ignores the psychological and physical factors of the personnel; (4) In order to facilitate the simulation of the experiment, we set the escapees as a point mass.

[0075] In a specific implementation, in order to establish a top view of a building, this embodiment establishes an environment model. The environment model is a top view of a building, that is, a two-dimensional plane. The 0-1 grid method is used to divide the entire two-dimensional plane into 20×20 grids of uniform size, such as Figure 2 shown.

[0076] As described in step S120, the node coordinates of each grid are determined according to the environment model, and the starting node and the target node are determined according to the node coordinates.

[0077] In an embodiment of the present invention, the specific process of "determining the node coordinates of each grid according to the environment model" in step S120 can be further explained in combination with the following description.

[0078] As described in the following steps, the number of each grid is determined according to the environmental model;

[0079] As described in the following steps, the corresponding node coordinates are determined according to the number.

[0080] As an example, in Figure 2 In the 20×20 grid map, grids are numbered starting from 1 from left to right and from top to bottom until the 400th grid in the lower right corner. Each grid coordinate is represented by its center point coordinate (x, y). The center coordinate of each grid, i.e., the node coordinate, is calculated using the conversion formula between grid number and coordinate, and the starting node and the target node are set. The starting coordinate and the target node are selected from the node coordinates; the conversion between grid number and grid coordinate is calculated as follows:

[0081]

[0082] y=a*(col+0.5-ceil(m / col))

[0083] In the formula, x and y represent the horizontal and vertical coordinates of the node respectively; col represents the total number of columns of the environment model; m represents the number of the grid; a represents the side length of the grid; mod() represents the remainder function; ceil() represents the upward rounding function.

[0084] In a specific implementation, in order to facilitate the algorithm to implement the planning of fire evacuation paths, this embodiment converts the 20×20 grid map into a 0-1 grid map, such as Figure 3 As shown. Assume that the input map is G, G(x,y)=1 represents an immovable area, and G(x,y)=0 represents a movable area.

[0085] Reference Figure 2 , obstacles and passable areas are marked in black and white respectively, such as Figure 2 The white grid indicates the area where escapees can move, corresponding to Figure 3 The black grid represents the static obstacle, that is, the area where the escapee cannot move, corresponding to Figure 3 The 0-1 distribution maps the data to "1".

[0086] As described in step S130 , the node region is determined using the A* algorithm according to the start node and the target node selected by the user.

[0087] In an embodiment of the present invention, the specific process of "determining the node area using the A* algorithm according to the start node and the target node selected by the user" in step S130 can be further explained in combination with the following description.

[0088] As described in the following steps, determining the actual cost according to the starting node and the current node;

[0089] As described in the following steps, determining an estimated cost based on the current node and the target node;

[0090] Determine the path cost according to the actual cost and the estimated cost as described in the following steps;

[0091] As described in the following steps, the node area is determined according to the path cost.

[0092] It should be noted that the key to solving the fire evacuation path planning problem lies in the selection of nodes. A set of suitable nodes can construct the shortest path, thereby providing sufficient escape time for the crowd. Therefore, this application uses a two-layer optimization strategy to plan the fire evacuation path. The two-layer optimization strategy consists of two parts: the first optimization and the second layer optimization. In solving the fire evacuation path planning problem, the A* algorithm in the first layer is used to solve the node area that the escapees have walked from the starting point to the end point, and then the enhanced ACO algorithm (i.e., EACO algorithm) of the second layer is used to find the globally optimal evacuation path in the node area in the first layer optimization. The two-layer optimization strategy can plan a suitable fire evacuation path.

[0093] The A* (A-Star) algorithm is the most effective direct search method for solving the shortest path in a static road network. It starts from the starting point, continuously expands the adjacent nodes, and uses the defined cost function to find the node with the smallest function value until it expands to the end point.

[0094] As an example, determine whether there is a fire in a building. If there is no fire in the building, use the A* algorithm to plan the shortest escape route and plan the node areas that the escapees may pass through in advance based on the starting point. If there is a fire in the building, use the enhanced ant colony algorithm to plan the path in the planned node area, first let the escapees stay away from the fire area, and then plan an obstacle-free and shortest fire evacuation route.

[0095] As an example, in the fire evacuation path planning problem, as long as the starting point and the end point are given, the A* algorithm can obtain a good evacuation path in a short time. In the process of searching for the path, the A* algorithm uses the cost function, that is, the path cost, as the basis for optimization, so as to obtain the optimal path. The cost function is:

[0096] f(n)=g(n)+h(n)

[0097] Among them, f(n) represents the estimated cost from the starting node S to the current node n to the target node E; g(n) represents the actual cost from the starting node S to the current node n; h(n) represents the estimated cost from the current node n to the target node E.

[0098] The calculation formulas for g(n) and h(n) are:

[0099]

[0100]

[0101] Among them, (x n ,y n ) is the coordinate of node n, (x S ,yS ) is the coordinate of the starting point S, (x E ,y E ) are the coordinates of the end point E.

[0102] As an example, neighborhood search is the basic principle of A* algorithm for evacuation planning. The neighborhood search of A* algorithm includes 4-neighborhood search and 8-neighborhood search. Compared with 4-neighborhood search, 8-neighborhood search is faster, more efficient and has a shorter path length. Therefore, this application adopts the 8-neighborhood search method, referring to Figure 4 , represents the moving direction of the 8-neighborhood search. When searching for a path, the A* algorithm starts from the starting node and continues to expand outward. The first level of optimization uses the A* algorithm to solve the node area that the escapees have walked from the starting point to the end point, and records the node area that the escapees have walked through. Secondly, the recorded node area is used as the optimization range of the EACO algorithm to find the optimal escape path.

[0103] As described in step S140, the maximum number of iterations is determined based on the node area, and the next path node is determined in the node area; wherein the path node contains pheromones.

[0104] In one embodiment of the present invention, the specific process of "determining the maximum number of iterations based on the node area, and determining the next path node in the node area; wherein the path node contains pheromones" in step S140 can be further explained in combination with the following description.

[0105] It should be noted that iteration is a repetition, that is, repeatedly executing the loop in the program until the ant is able to walk from the starting node to the target node. By determining the maximum number of iterations, the accuracy of the calculation is improved.

[0106] As an example, the second-level optimization uses the EACO algorithm to plan the fire evacuation path in the node area solved by the A* algorithm in the first level, so as to find the shortest evacuation path. In the ant colony algorithm, each ant has a taboo table to record the grids it has walked through. During the foraging process, each ant will leave pheromones on the route to transmit information, and guide the direction of advance according to the concentration of pheromones, so as to obtain the shortest foraging path.

[0107] Usually, when choosing a path, ants need to consider the transition probability. To determine the probability of ant k moving from node i to the next path node j at time t, the state transition probability is expressed as follows:

[0108]

[0109] In the formula, represents the probability of ant k going from node i to the next path node j at time t; C represents the set of nodes that can be visited in the next step; η ij (t) represents the heuristic function, where η ij (t) = 1 / d ij , d ij represents the distance between nodes i and j; α is the pheromone importance factor; β is the heuristic function importance factor.

[0110] As described in step S150, the pheromone evaporation factor is determined according to the maximum number of iterations and the current number of iterations, and the pheromone is updated according to the pheromone evaporation factor.

[0111] In an embodiment of the present invention, the specific process of "determining the pheromone evaporation factor according to the maximum number of iterations and the current number of iterations, and updating the pheromone according to the pheromone evaporation factor" in step S150 can be further explained in combination with the following description.

[0112] As an example, as time goes by, the pheromones left by ants on the path gradually evaporate. In order to prevent the large-scale loss of pheromones from affecting the ants' choice of nodes, the pheromones need to be adjusted after the ants complete one iteration.

[0113] In an embodiment of the present invention, the specific process of “determining the pheromone evaporation factor according to the maximum number of iterations and the current number of iterations” may be further explained in combination with the following description.

[0114] As described in the following steps, determining the initial pheromone evaporation factor according to the current number of iterations;

[0115] As described in the following steps, the pheromone evaporation factor is determined according to the initial pheromone evaporation factor, the maximum number of iterations and the current number of iterations.

[0116] In a specific implementation, the calculation formula of the pheromone evaporation factor is as follows:

[0117] ρ=ρ0 / (1+exp(20*iter) / maxiter-10)

[0118] Wherein, ρ represents the pheromone evaporation factor; ρ0 represents the initial pheromone evaporation factor; iter represents the current number of iterations; and maxiter represents the maximum number of iterations.

[0119] Among them, ρ0=0.8, the pheromone evaporation factor ρ decreases nonlinearly from 0.8 to 0. This strategy makes the algorithm nonlinear in the optimization process, reducing the complexity of the problem.

[0120] In an embodiment of the present invention, the specific process of “updating the pheromone according to the pheromone evaporation factor” can be further explained in combination with the following description.

[0121] As described in the following steps, determining the pheromone increment according to the current number of iterations;

[0122] As described in the following steps, the pheromone is updated according to the pheromone increment and the pheromone evaporation factor.

[0123] As an example, in the fire evacuation path problem, since there are many nodes that need to be traversed, the search process is usually an extremely complex nonlinear process. At the same time, the pheromone evaporation factor ρ in the basic ant colony algorithm is a constant, which makes it easy for the algorithm to ignore the complexity of the problem during the optimization process, resulting in its inability to search for the shortest evacuation path. Therefore, the present invention adopts a nonlinear decreasing strategy to improve the pheromone evaporation factor ρ and to improve the pheromone τ ij (t) is adjusted, and the formula is as follows:

[0124] τ ij (t+1)=(1-ρ)*τ ij (t)+ρ*Δτ ij ,0<ρ<1

[0125]

[0126]

[0127] In the formula, τ ij (t) represents pheromone; Δτ ij represents the pheromone increment left on the node (i, j) in the current iteration of the ant; represents the pheromone left by the kth ant on the node (i, j) in the current iteration; L k It represents the path length after the kth ant completes one iteration, and Q represents the intensity coefficient of the pheromone increase.

[0128] As described in step S160, when the current number of iterations reaches the maximum number of iterations, the shortest target evacuation path is output.

[0129] In an embodiment of the present invention, the specific process of "when the current number of iterations reaches the maximum number of iterations, outputting the shortest target evacuation path" in step S160 may be further explained in combination with the following description.

[0130] As described in the following steps, when the path node is a target node, the pheromone on the path is updated, and the length of the target path from the starting node to the path node is determined.

[0131] As an example, determine whether the ant has reached the end position. If it has reached the end, calculate the length of the target path from the start point to the end point. If it has not reached the end point, continue to visit the next node until the end point is reached. Count the target paths of all ants, and record the nodes that the ants pass through on the path. Use the improved nonlinear decreasing strategy to update the pheromone evaporation factor and pheromone.

[0132] As described in the following steps, when the current number of iterations reaches the maximum number of iterations, an evacuation path set is generated according to the target path; and the target evacuation path with the shortest distance in the evacuation path set is determined.

[0133] As an example, determine whether the maximum number of iterations has been reached. If so, the ant colony will select the path with the highest pheromone content as the best path, that is, output the shortest target evacuation path and node from the evacuation path set formed by the shortest target path obtained from each iteration, and draw a planning diagram for the shortest evacuation path for fire; if not, replan the fire evacuation path until the maximum number of iterations is met.

[0134] Reference Figure 5 , the specific steps of the A*-EACO algorithm are as follows:

[0135] (1) Use the 0-1 grid method to establish the environmental model and calculate the node coordinates.

[0136] (2) Use the A* algorithm to solve and record the node area that the escapee passes through from the starting point to the end point.

[0137] (3) Initialization of the EACO algorithm. Initialize the starting position start, the end position goal, the number of ants num, the maximum number of iterations maxiter, the current number of iterations iter, the importance factor of the ant pheromone α, the importance factor of the heuristic function β, the intensity coefficient of the pheromone increase Q, the taboo table Tab, the pheromone evaporation factor ρ and the adjacency matrix, etc.

[0138] (4) The EACO algorithm searches for paths in the node area of ​​step (2). The algorithm enters a loop iteration, and the ants avoid the fire area and plan an obstacle-free and shortest evacuation path in the pre-planned node area. Put num ants at the starting point, put the starting point into the taboo table, and the ants use the heuristic function η according to the current node position. ij (t) Select the next node to go to.

[0139] (5) After the next node is determined, the ant needs to locally update the pheromones on the path it just traversed.

[0140] (6) Determine whether the ant has reached the end point. If it has, go to step (7); otherwise, go to step (4) until the end point is reached.

[0141] (7) Count the optimal paths currently searched by the num ants, select the shortest path, and update the global pheromone.

[0142] (8) Determine whether the number of iterations satisfies iter≤maxiter. If so, go to step (4). Otherwise, the program ends and the optimal fire evacuation path and nodes are output.

[0143] Compared with the prior art, the improved A*-EACO algorithm of this application has the following beneficial effects:

[0144] 1. This application imports the 0-1 map of the building, uses the 0-1 grid method to perform two-dimensional modeling of the building, marks obstacles and passable areas, and uses the conversion formula between grid numbers and coordinates to calculate the center coordinates of each grid, thereby reducing the difficulty of modeling;

[0145] 2. This application calls the fastest running A* algorithm to search for the shortest path and plan in advance the node areas that the escapees may pass through when there is no fire in the building;

[0146] 3. In the event of a fire in a building, this application immediately calls the EACO algorithm with high solving efficiency to search for the shortest path in the pre-planned node area. During the search process, the algorithm first keeps the escapees away from the fire area, and then plans an obstacle-free shortest fire evacuation path;

[0147] 4. This application takes into account that there are many nodes that need to be traversed in the fire evacuation path problem, and the search process is usually an extremely complex nonlinear process. At the same time, the pheromone evaporation factor in the basic ant colony algorithm is a constant, which makes it easy for the algorithm to ignore the complexity of the problem during the optimization process, resulting in the algorithm being unable to search for the shortest evacuation path. This application uses a nonlinear decreasing strategy to improve the pheromone evaporation factor and update the pheromone. This strategy makes the algorithm nonlinear during the optimization process, reducing the complexity of the problem. Therefore, the nonlinear decreasing strategy can better improve the algorithm's search ability and reduce the complexity of solving the fire evacuation path problem.

[0148] The following is a simulation experiment of the A*-EACO algorithm of this application

[0149] Experimental setup:

[0150] In order to verify the feasibility of the A*-EACO algorithm in fire evacuation path planning, the A* algorithm, ACO and A*-EACO algorithm were simulated respectively. The software used in the experiment is MATLAB R2017a, and the computer hardware is Intel Corei5 processor with 8G memory. The environmental model is as follows Figure 2 As shown in Figure 1, the starting point of the model is (0.5, 19.5), which is the location of the evacuees, and the end point is (19.5, 0.5), which is the location of the safety exit. The parameter settings of the A*-EACO algorithm are shown in Table 1:

[0151]

[0152] Table 1 Simulation assumptions parameters

[0153] Experimental simulation and analysis:

[0154] The black grids in Figure 6-8 represent obstacles, the white grids represent areas where escapees can walk, and the black solid line represents the shortest fire evacuation path planned by the corresponding algorithm.

[0155] (1) Simulation experiment of A* algorithm: Figure 6a The A* algorithm is used to plan the fire evacuation path. The shortest path planned by the algorithm is 35.7990m, and the running time of the algorithm is 2.025s. Since the A* algorithm calculates the shortest distance from any point in all nodes to the starting point, it finally obtains the optimal path from the starting point to the end point. Figure 6b The convergence curve is a straight line. Figure 6c It represents the node area that the escapee passes through from the starting point to the end point.

[0156] (2) Simulation experiment of ACO algorithm: Figure 7a The ACO algorithm is used to plan the fire evacuation route. The shortest path planned by the algorithm is 34.9706 m, and the algorithm running time is 10.445 s. Figure 7a It can be seen from the figure that when obstacles are dense, the planned local path is not optimal. Figure 7b It can be seen that the ant colony algorithm converges slowly. Since all nodes need to be iteratively solved, the algorithm runs for too long.

[0157] (3) Simulation experiment of A*-EACO algorithm: The first level optimization uses A* algorithm to find the node area from the starting point to the end point of the escapee, such as Figure 6c The circled part shown is the node area. Secondly, the EACO algorithm is used to plan a global optimal evacuation path in the node area. Figure 8a The A*-EACO algorithm is used to plan the fire evacuation route. The shortest path planned by the algorithm is 34.3848 m, and the algorithm running time is 7.251 s. Figure 8a It can be seen that A*-EACO obtains a good fire evacuation path regardless of whether the obstacles are dense or sparse. Figure 8b It can be seen that the A*-EACO algorithm can converge quickly.

[0158] (4) Comparative analysis of simulation results: As can be seen from Figures 6 to 8, although the ACO algorithm shortens the distance of the fire evacuation path, it takes a long time, and the local path planned in places with dense obstacles is not optimal. Although the A* algorithm has a fast calculation speed, the evacuation path it plans is longer. This is because the algorithm limitation causes it to be unable to obtain the local optimal path when obstacles are sparse. The A*-EACO algorithm uses the EACO algorithm to plan the path in the node area based on the node area obtained by the A* algorithm. The planned fire evacuation path is the shortest and significantly better than the other two algorithms. The algorithm converges faster. In terms of algorithm calculation time, the running time of the A*-EACO algorithm is higher than that of the A* algorithm, but lower than that of the ACO algorithm. The simulation results of the three algorithms are shown in Table 2.

[0159] Here, the starting point (0.5, 19.5) is regarded as the emergency indicator light. When there is no fire, the indicator light is on in both the x and y directions. Figure 9a The node (1.5, 16.5) is the fire point, and (19.5, 0.5) is the safe exit. When a fire occurs at the fire point, the sensor in the fire point area sends a fire signal to the control console. After the control console obtains the fire information, it uses the A*-EACO algorithm to re-plan the fire evacuation path and select the safest shortest path. Figure 9a As shown, when a fire occurs at (1.5, 16.5), the indicator light pointing to the y direction goes out to remind the escapees that this direction is not passable, and the indicator light in the x direction remains on, that is, this direction is passable. Figure 9b It can be seen that the A*-EACO algorithm can converge quickly. Therefore, the A*-EACO algorithm is used to dynamically plan the fire evacuation path and change the direction of the emergency indicator light in real time to achieve dynamic evacuation of the fire and guide the escapees to reach a safe location in time.

[0160]

[0161] Table 2 Simulation results of three algorithms

[0162] As for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0163] Reference Fig.10 , showing a fire evacuation path planning system based on the A*-EACO algorithm provided in one embodiment of the present application;

[0164] Specifically include:

[0165] The environment modeling module 1010 is used to obtain a two-dimensional plan view of the target building and establish an environment model using a 0-1 grid method based on the two-dimensional plan view;

[0166] A coordinate calculation module 1020, used to determine the node coordinates of each grid according to the environmental model;

[0167] The first optimization module 1030 is used to determine the node area using the A* algorithm according to the start node and the target node selected by the user;

[0168] The transfer module 1040 is used to determine the maximum number of iterations according to the node area and determine the next path node in the node area; wherein the path node contains pheromone;

[0169] The second optimization module 1050 is used to determine the pheromone evaporation factor according to the maximum number of iterations and the current number of iterations, and update the pheromone according to the pheromone evaporation factor;

[0170] The path output module 1060 is configured to output a target evacuation path with the least nodes and the shortest distance when the current number of iterations reaches the maximum number of iterations.

[0171] In one embodiment of the present invention, the second optimization module 1050 includes:

[0172] An initial pheromone evaporation factor determination submodule, used to determine the initial pheromone evaporation factor according to the current number of iterations;

[0173] The pheromone evaporation factor determination submodule is used to determine the pheromone evaporation factor according to the initial pheromone evaporation factor, the maximum number of iterations and the current number of iterations.

[0174] In one embodiment of the present invention, the second optimization module 1050 further includes:

[0175] A pheromone increment determination submodule, used to determine the pheromone increment according to the current number of iterations;

[0176] An updating submodule is used to update the pheromone according to the pheromone increment and the pheromone evaporation factor.

[0177] In one embodiment of the present invention, the coordinate calculation module 1020 includes:

[0178] A numbering submodule, used to determine the number of each grid according to the environmental model;

[0179] The conversion submodule is used to determine the corresponding node coordinates according to the number.

[0180] In one embodiment of the present invention, the first optimization module 1030 includes:

[0181] An actual cost determination submodule, used to determine the actual cost based on the starting node and the current node;

[0182] An estimated cost determination submodule, used to determine an estimated cost based on the current node and the target node;

[0183] A path cost determination submodule, configured to determine a path cost based on the actual cost and the estimated cost;

[0184] The node area determination submodule is used to determine the node area according to the path cost.

[0185] In one embodiment of the present invention, the calculation formula of the transfer module 1040 is as follows:

[0186]

[0187] In the formula, represents the probability of ant k going from node i to the next path node j at time t; C represents the set of nodes that can be visited in the next step; η ij (t) represents the heuristic function, where η ij (t) = 1 / d ij , d ij represents the distance between nodes i and j; α is the pheromone importance factor; β is the heuristic function importance factor.

[0188] In one embodiment of the present invention, the path output module 1060 includes:

[0189] An updating submodule, for updating the pheromone on the path when the path node is a target node, and determining the length of the target path from the starting node to the path node;

[0190] A path set submodule, configured to generate an evacuation path set according to the target path when the current number of iterations reaches the maximum number of iterations;

[0191] The output submodule is used to determine the target evacuation path with the shortest distance in the evacuation path set.

[0192] Reference Fig.11 , shows a computer device of a fire evacuation path planning method based on the A*-EACO algorithm of the present invention, which may specifically include the following:

[0193] The computer device 12 is in the form of a general-purpose computing device, and the components of the computer device 12 may include but are not limited to: one or more processors or processing units 16, a system memory 28, and a bus 18 connecting different system components (including the system memory 28 and the processing unit 16).

[0194] The bus 18 represents one or more of several types of bus 18 structures, including a memory bus 18 or memory controller, a peripheral bus 18, an accelerated graphics port, a processor or a local bus 18 using any of a variety of bus 18 architectures. These architectures include, by way of example, but are not limited to, an Industry Standard Architecture (ISA) bus 18, a Micro Channel Architecture (MAC) bus 18, an Enhanced ISA bus 18, an Audio Video Electronics Standards Association (VESA) local bus 18, and a Peripheral Component Interconnect (PCI) bus 18.

[0195] The computer device 12 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by the computer device 12, including volatile and non-volatile media, removable and non-removable media.

[0196] System memory 28 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 30 and / or cache memory 32. Computer device 12 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, storage system 34 may be used to read and write to non-removable, non-volatile magnetic media (commonly referred to as a "hard drive"). Although Fig.11 Not shown, a disk drive for reading and writing to a removable non-volatile disk (such as a "floppy disk"), and an optical disk drive for reading and writing to a removable non-volatile optical disk (such as a CD-ROM, DVD-ROM or other optical medium) may be provided. In these cases, each drive may be connected to the bus 18 via one or more data medium interfaces. The memory may include at least one program product having a set (e.g., at least one) of program modules 42, which are configured to perform the functions of various embodiments of the present invention.

[0197] A program / utility 40 having a set (at least one) of program modules 42 may be stored in, for example, a memory, such program modules 42 including, but not limited to, an operating system, one or more application programs, other program modules 42, and program data, each of which or some combination may include an implementation of a network environment. The program modules 42 generally perform the functions and / or methods of the embodiments described herein.

[0198] The computer device 12 may also communicate with one or more external devices 14 (e.g., keyboards, pointing devices, displays 24, cameras, etc.), one or more devices that enable an operator to interact with the computer device 12, and / or any device that enables the computer device 12 to communicate with one or more other computing devices (e.g., network cards, modems, etc.). Such communication may be performed via an input / output (I / O) interface 22. Furthermore, the computer device 12 may also communicate with one or more networks (e.g., local area networks (LANs)), wide area networks (WANs), and / or public networks (e.g., the Internet) via a network adapter 20. As shown, the network adapter 20 communicates with the other modules of the computer device 12 via the bus 18. It should be understood that although Fig.11 Not shown, other hardware and / or software modules may be used in conjunction with the computer device 12, including but not limited to: microcode, device drivers, redundant processing units 16, external disk drive arrays, RAID systems, tape drives, and data backup storage systems 34, etc.

[0199] The processing unit 16 executes various functional applications and data processing by running the programs stored in the system memory 28, for example, implementing a fire evacuation path planning method based on the A*-EACO algorithm provided in an embodiment of the present invention.

[0200] That is, when the processing unit 16 executes the program, the following is achieved: obtaining a two-dimensional plan of the building, and establishing an environmental model based on the two-dimensional plan by using a 0-1 grid method; determining the node coordinates of each grid based on the environmental model; determining the node area based on the start node and the target node selected by the user by using an A* algorithm; determining the maximum number of iterations based on the node area, and determining the next path node within the node area; wherein the path node contains pheromones; determining a pheromone evaporation factor based on the maximum number of iterations and the current number of iterations, and updating the pheromones based on the pheromone evaporation factor; and outputting a target evacuation path with the shortest distance when the current number of iterations reaches the maximum number of iterations.

[0201] In an embodiment of the present invention, the present invention further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements a fire evacuation path planning method based on the A*-EACO algorithm as provided in all embodiments of the present application:

[0202] That is, when the program is executed by the processor, the following are achieved: obtaining a two-dimensional plan of the building, and establishing an environmental model based on the two-dimensional plan using a 0-1 grid method; determining the node coordinates of each grid based on the environmental model; determining the node area using an A* algorithm based on the start node and the target node selected by the user; determining the maximum number of iterations based on the node area, and determining the next path node within the node area; wherein the path node contains pheromones; determining a pheromone evaporation factor based on the maximum number of iterations and the current number of iterations, and updating the pheromones based on the pheromone evaporation factor; and outputting a target evacuation path with the shortest distance when the current number of iterations reaches the maximum number of iterations.

[0203] Any combination of one or more computer-readable media may be used. A computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium. A computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any combination thereof. More specific examples of computer-readable storage media (a non-exhaustive list) include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In this document, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in conjunction with an instruction execution system, device, or device.

[0204] Computer-readable signal media may include a data signal propagated in baseband or as part of a carrier wave, which carries a computer-readable program code. Such propagated data signals may take a variety of forms, including, but not limited to, electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0205] The computer program code for performing the operation of the present invention can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" language or similar programming languages. The program code can be executed entirely on the operator's computer, partially on the operator's computer, as an independent software package, partially on the operator's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the operator's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (for example, using an Internet service provider to connect through the Internet). The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same and similar parts between the various embodiments can be referred to each other.

[0206] Although the preferred embodiments of the present application have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the embodiments of the present application.

[0207] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or terminal device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or terminal device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or terminal device including the elements.

[0208] The above is a detailed introduction to a fire evacuation path planning method and system based on the A*-EACO algorithm provided by the present application. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea; at the same time, for general technical personnel in this field, according to the idea of ​​the present application, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A fire evacuation path planning method based on A*-EACO algorithm, characterized in that: The method comprises: Obtaining a two-dimensional plan view of the building, and establishing an environmental model using a 0-1 grid method based on the two-dimensional plan view; Determining the node coordinates of each grid according to the environmental model; The node area is determined using the A* algorithm based on the start node and target node selected by the user; Determining a maximum number of iterations according to the node area, and determining a next path node in the node area; wherein the path node contains pheromones; Determine a pheromone evaporation factor according to the maximum number of iterations and the current number of iterations, and update the pheromone according to the pheromone evaporation factor; specifically, determine an initial pheromone evaporation factor according to the current number of iterations; determine a pheromone evaporation factor according to the initial pheromone evaporation factor, the maximum number of iterations and the current number of iterations; determine a pheromone increment according to the current number of iterations; and update the pheromone according to the pheromone increment and the pheromone evaporation factor; When the current number of iterations reaches the maximum number of iterations, the target evacuation path with the shortest distance is output; specifically, when the path node is the target node, the pheromone on the path is updated, and the length of the target path from the starting node to the path node is determined; when the current number of iterations reaches the maximum number of iterations, an evacuation path set is generated according to the target path; and the target evacuation path with the shortest distance in the evacuation path set is determined; The calculation formula of the pheromone evaporation factor is as follows: ρ=ρ0 / (1+exp(20*iter) / maxiter-10) Wherein, ρ represents the pheromone evaporation factor; ρ0 represents the initial pheromone evaporation factor; iter represents the current number of iterations; maxiter represents the maximum number of iterations; Among them, for pheromone τ ij (t) The update formula is as follows: t ij (t+1)=(1-ρ)*τ ij (t)+ρ*Δτ ij ,0<ρ<1 In the formula, τ ij (t) represents pheromone; Δτ ij It represents the pheromone increment left by the ant on the node (i, j) in the current iteration; represents the pheromone left by the kth ant on the node (i, j) in the current iteration; L k It represents the path length after the kth ant completes one iteration, and Q represents the intensity coefficient of the pheromone increase.

2. The method according to claim 1, characterized in that The step of determining the node coordinates of each grid according to the environmental model comprises: Determining the number of each grid according to the environmental model; The corresponding node coordinates are determined according to the number.

3. The method according to claim 1, characterized in that The step of using the A* algorithm to determine the node area according to the starting node and the target node selected by the user includes: Determining an actual cost based on the starting node and the current node; Determining an estimated cost based on the current node and the target node; Determining a path cost based on the actual cost and the estimated cost; The node area is determined according to the path cost.

4. The method according to claim 1, characterized in that: The formula for determining the next path node in the node area is as follows: In the formula, represents the probability of ant k going from node i to the next path node j at time t; C represents the set of nodes that can be visited in the next step; η ij (t) represents the heuristic function, where η ij (t) = 1 / d ij , d ij represents the distance between nodes i and j; α is the pheromone importance factor; β is the heuristic function importance factor.

5. A fire evacuation path planning system based on A*-EACO algorithm, characterized in that: The system comprises: An environmental modeling module is used to obtain a two-dimensional plan view of a target building and establish an environmental model using a 0-1 grid method based on the two-dimensional plan view; A coordinate calculation module, used to determine the node coordinates of each grid according to the environmental model; The first optimization module is used to determine the node area using the A* algorithm according to the starting node and the target node selected by the user; A transfer module, used to determine the maximum number of iterations according to the node area, and determine the next path node in the node area; wherein the path node contains pheromone; The second optimization module is used to determine the pheromone evaporation factor according to the maximum number of iterations and the current number of iterations, and update the pheromone according to the pheromone evaporation factor; specifically, determine the initial pheromone evaporation factor according to the current number of iterations; determine the pheromone evaporation factor according to the initial pheromone evaporation factor, the maximum number of iterations and the current number of iterations; determine the pheromone increment according to the current number of iterations; and update the pheromone according to the pheromone increment and the pheromone evaporation factor; A path output module, configured to output a target evacuation path with the shortest distance when the current number of iterations reaches the maximum number of iterations; specifically, when the path node is a target node, update the pheromone on the path, and determine the length of the target path from the starting node to the path node; when the current number of iterations reaches the maximum number of iterations, generate an evacuation path set based on the target path; and determine the target evacuation path with the shortest distance in the evacuation path set; The calculation formula of the pheromone evaporation factor is as follows: ρ=ρ0 / (1+exp(20*iter) / maxiter-10) Wherein, ρ represents the pheromone evaporation factor; ρ0 represents the initial pheromone evaporation factor; iter represents the current number of iterations; maxiter represents the maximum number of iterations; Among them, for pheromone τ ij (t) The update formula is as follows: t ij (t+1)=(1-ρ)*τ ij (t)+ρ*Δτ ij ,0<ρ<1 In the formula, τ ij (t) represents pheromone; Δτ ij It represents the pheromone increment left by the ant on the node (i, j) in the current iteration; represents the pheromone left by the kth ant on the node (i, j) in the current iteration; L k It represents the path length after the kth ant completes one iteration, and Q represents the intensity coefficient of the pheromone increase.

6. A computer device, characterized in that: The method comprises a processor, a memory, and a computer program stored in the memory and capable of running on the processor, wherein the computer program implements the method according to any one of claims 1 to 4 when executed by the processor.

7. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 4 is implemented.

Images