Fire escape path optimization method based on improved SWO

Abstract

This invention relates to the field of path optimization technology, and particularly to a fire escape path optimization method based on an improved SWO algorithm. The method includes obtaining the location of trapped personnel, target location, obstacle location, and fire location; constructing an objective function for the optimal escape distance; constructing an improved SWO algorithm, employing an adaptive trade-off factor rate to adaptively adjust the search strategy, balancing global search and local exploration capabilities; and using an improved spiral update mechanism to optimize the location update during the spider-wasp nest-building stage, providing search direction for the exploration process during the nest-building stage. This invention addresses the issue that the convergence speed and stability of the SWO algorithm need further improvement.

Description

Technical Field

[0001] This invention relates to the field of path optimization technology, and in particular to a fire escape path optimization method based on an improved SWO. Background Technology

[0002] Fire path planning is one of the current hot topics in the field of safety research. The purpose of fire path planning is to enable trapped personnel to avoid obstacles in a fire scene with many obstacles and complex environment by following the on-site instructions and the optimal solution criteria, thereby choosing an optimal path from the starting point of the entrapment to the safe end point.

[0003] When dealing with path planning problems involving complex fire scene information, inspiration from nature can often play a significant role. Commonly used algorithms include ant colony optimization, neural network optimization, particle swarm optimization, and genetic algorithms.

[0004] Patent application number 202411475567.4 describes a neural network fire trend prediction method based on an improved GWO algorithm. While improving the adaptive convergence factor of the GWO algorithm can enhance the accuracy of prediction, this method does not consider the search direction, and the accuracy of path planning needs further improvement.

[0005] In addition, the Spider Wasp Optimizer (SWO) algorithm has been widely used in the field of path planning due to its fast solution, strong global search capability and strong robustness; however, there is still room for improvement in the convergence speed and stability of the Spider Wasp algorithm. How to further shorten the convergence time of the Spider Wasp algorithm and eliminate some unstable optimal solutions has become an urgent part of the Spider Wasp algorithm. Summary of the Invention

[0006] To address the shortcomings of existing methods, this invention solves the problem that the convergence speed and stability of the SWO algorithm need further improvement.

[0007] The technical solution adopted in this invention is: a fire escape path optimization method based on an improved SWO, comprising the following steps:

[0008] Step 1: Obtain the location of trapped personnel, target location, obstacle location, and fire location;

[0009] In a preferred embodiment of the present invention, the fire location is acquired by a fire detection sensor.

[0010] In a preferred embodiment of the present invention, the location of the trapped person, the target location, and the location of the obstacle are simulated by a two-dimensional model of the fire scene using a grid method.

[0011] Step 2: Construct the objective function for the optimal escape distance;

[0012] In a preferred embodiment of the present invention, the objective function uses Euclidean distance to determine the path length.

[0013] Step 3: Construct an improved SWO algorithm, adopting an adaptive trade-off factor rate and adaptively adjusting the search strategy to balance global search and local development capabilities; and use an improved spiral update mechanism to optimize the position update of the spider wasp during the nest building stage, providing search direction for the exploration process during the nest building stage.

[0014] As a preferred embodiment of the present invention, the SWO algorithm improved by adaptive tradeoff factor rate includes:

[0015] Initialize the population size N and the maximum number of iterations; the current location of the trapped personnel, the location of obstacles, the location of the target, and the location of the fire;

[0016] The formula for constructing the tradeoff factor ratio TR is:

[0017]

[0018] In the formula, Indicates the current iteration number; Indicates the maximum number of iterations; and These represent the current population size and the maximum population size, respectively.

[0019] Spider-bee location update during the search phase;

[0020] The location of the spider wasps during the pursuit phase is updated;

[0021] The location of spider wasps during the nest-building phase is updated;

[0022] Determine whether the maximum number of iterations or the optimal solution has been reached. If the termination condition is not met, repeat the position update. If the termination condition is met, output the optimal fire escape route.

[0023] In a preferred embodiment of the present invention, the formula for updating the position of spider wasps during the nest-building stage using the improved spiral update mechanism is as follows:

[0024]

[0025]

[0026] In the formula, This indicates the current location of the spider wasp. This indicates that the parameters are dynamically adjusted. Indicates the current iteration number; Indicates the maximum number of iterations; , and express a , b , c Three random spider wasps; , and Represents a random number between [0, 1]; U This represents a vector that prevents nesting in the same location; It represents a random number between [-2, 1].

[0027] As a preferred embodiment of the present invention, the improved SWO algorithm is evaluated using the average fitness value and the minimum fitness value.

[0028] As a preferred embodiment of the present invention, a fire escape path optimization system based on an improved SWO includes: a memory for storing instructions executable by a processor; and a processor for executing the instructions to implement a fire escape path optimization method based on an improved SWO.

[0029] As a preferred embodiment of the present invention, a computer-readable medium storing computer program code implements a fire escape path optimization method based on an improved SWO when executed by a processor.

[0030] The beneficial effects of this invention are:

[0031] 1. In the process of exploring nest-building behavior, there is a lack of effective search direction. An improved dynamic spiral update mechanism can provide search direction, enhance the adaptability of the algorithm and improve its convergence accuracy.

[0032] 2. Improve the adaptive trade-off factor of the SWO algorithm to enable the algorithm to adaptively adjust the search strategy and balance the ability of global search and local exploitation, thereby improving the search efficiency and convergence accuracy of the algorithm. Attached Figure Description

[0033] Figure 1 This is a flowchart of the fire escape path optimization method based on the improved SWO of the present invention;

[0034] Figure 2 This is a flowchart of the improved SWO algorithm of the present invention;

[0035] Figure 3 This is a comparison chart of the data fitness values ​​of the present invention and existing methods;

[0036] Figure 4 This is a comparison chart of the number of iterations between the present invention and existing methods;

[0037] Figure 5This is the path planning diagram of the present invention in which no fire occurred;

[0038] Figure 6 The detection terminal 1 of this invention detects the path planning map of a fire. Detailed Implementation

[0039] The present invention will be further described below with reference to the accompanying drawings and embodiments. The drawings are simplified schematic diagrams, which only illustrate the basic structure of the present invention in a schematic manner, and therefore only show the components related to the present invention.

[0040] like Figure 1 As shown, a fire escape route optimization method based on an improved SWO includes the following steps:

[0041] Fire escape route planning is a challenging problem. Traditional route planning algorithms often struggle to find the optimal solution in such environments because the complexity of the target point leads to a very large search space and the existence of many local optima. How to solve the problems of local optima traps, slow convergence speed, and parameter sensitivity in algorithms is the technical problem that this invention aims to address.

[0042] Step 1: Obtain the location of trapped personnel, target location, obstacle location, and fire location;

[0043] A two-dimensional model simulating a fire scenario is constructed using the grid method, setting the starting position of trapped personnel, target position, obstacles, and detection terminal node positions; the detection terminal node positions are obtained by acquiring the location information of the fire through on-site detection terminals when a fire occurs; the target position is the exit position.

[0044] Step 2: Construct the objective function for the optimal escape distance;

[0045] To improve the efficiency of escape for trapped personnel, optimizing the escape route to shorten the distance is a key approach. This invention uses Euclidean distance to determine the path length, and the objective function is expressed as:

[0046] (1)

[0047] in, x i , y i For the first i Each node position m This represents the total number of nodes.

[0048] Step 3: Input the location of the trapped person into the objective function, and use the ISWO algorithm to calculate the next optimal location of the trapped person;

[0049] The ISWO algorithm (improved SWO) calculates the next optimal position for trapped personnel by including:

[0050] Initialize the population size N, maximum number of iterations, and tradeoff TR; the current location of the trapped personnel, the location of obstacles, the location of the target, and the location of the fire;

[0051] Input the current location information of the trapped personnel into the target function, and the location of each female wasp represents a safe location.

[0052] During the search phase, the female spider wasp randomly explores the space, and its location is updated as follows:

[0053] (2)

[0054] (3)

[0055] (4)

[0056] (5)

[0057] In the formula, Indicates the updated position of the spider wasp; Indicates the current location of the spider wasp; , and express a , b , c Three random spider wasps; , , and Represents a random number between [0, 1]; This represents the coefficient used to adjust the step size; B Indicates control The amplitude coefficient, with The value increases and then decreases; Represents a random number between [-2, 1]; and Indicates the upper and lower bounds of the predefined parameters.

[0058] During the pursuit phase, the spider wasp's position update formula is:

[0059] (6)

[0060] (7)

[0061] In the formula, Indicates random selection of spiders and bees a individual; C The factor that controls the change in the speed of the spider wasp; and This indicates the current iteration number and the maximum iteration number; and Represents a random number between [0, 1]; Represents a vector representing the normal distribution [-k, k]; k is generated by the following formula:

[0062] (8)

[0063] In the formula, and This indicates the current iteration number and the maximum iteration number;

[0064] During the nest-building phase, the spider wasp's position update formula is:

[0065] (9)

[0066]

[0067] In the formula, This represents the currently generated optimal solution; , and This indicates that spider wasps were randomly selected from the population. a, b, c Three solutions; This represents a number generated by Levy's flight; U This represents a vector that avoids nesting in the same location.

[0068] Determine whether the maximum number of iterations or the optimal solution has been reached, i.e., the safe exit has been reached. If the termination condition is not met, repeat the above steps. If the termination condition is met, output the optimal fire escape route.

[0069] This invention employs an adaptive tradeoff factor rate (TR) and an improved dynamic spiral update mechanism. Specific improvements include:

[0070] In the SWO algorithm, the tradeoff factor ratio TR determines whether the algorithm chooses hunting or mating behavior. Existing fixed tradeoff factor ratios cannot guarantee better optimization every time. This invention employs an adaptive tradeoff factor, enabling the algorithm to adaptively adjust its search strategy, balancing global search and local exploitation capabilities, thereby improving the algorithm's search efficiency and convergence accuracy. The formula for the tradeoff factor ratio TR is:

[0071] (10)

[0072] In the formula, Indicates the current iteration number; Indicates the maximum number of iterations; and These represent the current population size and the maximum population size, respectively.

[0073] Since the algorithm lacks an effective search direction during the exploration process of nest building behavior, this invention adopts an improved dynamic spiral update mechanism, which can provide a search direction, enhance the algorithm's adaptability, and improve its convergence accuracy.

[0074] Randomly select spider wasps from the population of Equation 7 a, b, c The three solutions for spider wasp position updates are optimized, and an improved spiral update mechanism is constructed to improve the position update during the spider wasp's nest-building phase. The formula is:

[0075] (11)

[0076]

[0077]

[0078] In the formula, This indicates that the parameters are dynamically adjusted. Indicates the current iteration number; This indicates the maximum number of iterations.

[0079] like Figure 3 A comparison of the average fitness and minimum fitness values ​​of the present invention with those of existing methods shows that the average fitness value of the ISWO of the present invention is significantly better than that of existing methods.

[0080] Figure 4 The objective function curves of this invention and existing methods show that the convergence speed of the algorithm is significantly improved after the introduction of the adaptive trade-off factor and the improved spiral update mechanism.

[0081] like Figure 5 and Figure 6 This is the path planning diagram of the present invention. Figure 5 The optimal route generated by the system when no fire has occurred; Figure 6 The optimal route is generated when the acquisition terminal 1 detects a fire; the acquisition terminal is a fire detection sensor or a fire image detection module.

[0082] Based on the above-described preferred embodiments of the present invention, and through the foregoing description, those skilled in the art can make various changes and modifications without departing from the inventive concept. The technical scope of this invention is not limited to the contents of the specification, but must be determined according to the scope of the claims.

Claims

1. A fire escape path optimization method based on an improved SWO (Self-Oriented Path) model, characterized in that: Includes the following steps: Step 1: Obtain the location of trapped personnel, target location, obstacle location, and fire location; Step 2: Construct the objective function for the optimal escape distance; Step 3: Construct an improved SWO algorithm, adopting an adaptive trade-off factor rate and adaptively adjusting the search strategy to balance global search and local development capabilities; and use an improved spiral update mechanism to optimize the position update of the spider wasp during the nest building stage, providing search direction for the exploration process during the nest building stage. The SWO algorithm improved with adaptive tradeoff factor rate includes: Initialize the population size N and the maximum number of iterations; the current location of the trapped personnel, the location of obstacles, the location of the target, and the location of the fire; The formula for constructing the tradeoff factor ratio TR is: In the formula, Indicates the current iteration number; Indicates the maximum number of iterations; and These represent the current population size and the maximum population size, respectively. Spider-bee location update during the search phase; The location of the spider wasps during the pursuit phase is updated; The location of spider wasps during the nest-building phase is updated; The formula for updating the position of spider wasps during the nest-building stage using the improved spiral update mechanism is as follows: In the formula, This represents the currently generated optimal solution. This indicates the current location of the spider wasp. This indicates that the parameters are dynamically adjusted. Indicates the current iteration number; Indicates the maximum number of iterations; , and express a , b , c Three random spider wasps; , and Represents a random number between [0, 1]; U This represents a vector that prevents nesting in the same location; Represents a random number between [-2, 1]; Determine whether the maximum number of iterations or the optimal solution has been reached. If the termination condition is not met, repeat the position update. If the termination condition is met, output the optimal fire escape route.

2. The fire escape path optimization method based on the improved SWO according to claim 1, characterized in that, The improved SWO algorithm is evaluated using the average fitness value and the minimum fitness value.

3. The fire escape path optimization method based on the improved SWO according to claim 1, characterized in that, The location of the fire is collected using fire detection sensors.

4. The fire escape path optimization method based on the improved SWO according to claim 1, characterized in that, The locations of trapped personnel, target locations, and obstacle locations are simulated using a two-dimensional model of the fire scene using a grid method.

5. The fire escape path optimization method based on the improved SWO according to claim 1, characterized in that, The objective function uses Euclidean distance to determine the path length.

6. A fire escape path optimization system based on an improved SWO, characterized in that, include: Memory is used to store instructions that can be executed by the processor; A processor for executing instructions to implement the fire escape path optimization method based on the improved SWO as described in any one of claims 1-5.

7. A computer-readable medium storing computer program code, characterized in that, The computer program code, when executed by a processor, implements the fire escape path optimization method based on any one of claims 1-5.

Images