Research on Subway Fire Evacuation Path Planning Based on Improved Ant Colony Algorithm

When an ant colony algorithm is used to plan the evacuation path for a fire in a subway station, the traditional ant colony evacuation path scheme cannot dynamically instruct people to evacuate and escape in response to the fire situation in the subway, which leads to a lower escape rate. In order to overcome this problem, this paper proposes an improved ant colony approach for subway fire evacuation, which aims to ensure the safety of the personnel with the optimal escape path at their location. Firstly, according to the development of subway fire events, we consider each parameter of the ant colony algorithm, improve its initial pheromone distribution based on the traditional ant colony algorithm based on the A* algorithm, secondly, improve its pheromone update strategy, and improve the heuristic function and transfer probability of the algorithm, and finally conduct simulation experiments with the M subway station as an example. The results show that the subway fire evacuation algorithm based on the improved A* algorithm effectively improves the algorithm computation speed by about 63% and 55% in the early stage of fire and the spread of fire state, and reduces the total distance of people escaping.