Study on Indoor Fire Evacuation Path Planning Method Based on the Grey Wolf Optimization Algorithm

Abstract

In pursuit of enhancing the efficiency of indoor fire evacuation path planning and reducing crowd density, this paper introduces an advanced evacuation path planning method based on the Grey Wolf Optimizer (GWO) algorithm. Initially, a grid-based approach is utilized to model the fire scenario. Subsequently, a path planning problem is formulated that incorporates the effects of CO concentration and crowd density. This model integrates the relationship between crowd density and evacuation speed, employing a Gaussian plume model to quantify the impact of crowd density and smoke hazards on individuals. The GWO algorithm is then introduced to solve this optimization problem, aiming to derive an optimal evacuation plan that comprehensively considers path length, smoke concentration, and crowd density. The model is validated across four distinct environmental scenarios. The experimental results demonstrate that the proposed method effectively identifies the shortest evacuation path and boasts rapid convergence rates while avoiding local optima. In non-fire scenarios, the method reduces the optimization cycle by 10%-25% and shortens path length by 10%-25% compared to other algorithms. During fire incidents, optimization cycles and path lengths are reduced by 10%-20%. These improvements enhance evacuation safety and efficiency while providing flexibility across settings, from indoors to commercial areas. This study offers valuable tools and insights for urban fire emergency management and safety planning.