论文部分内容阅读
在火灾环境中,针对蚁群算法容易陷入局部最优的问题,文章使用了一种改进的蚁群算法用于解决火灾环境中人群疏散的路径规划问题。对蚁群算法的改进分为两个方面:一是在蚁群算法的启发式函数中考虑人员密度因素;二是动态自适应调整信息素强度,采取局部和全局信息素更新相结合的策略更新路径上的信息素,并引入交叉操作,加快算法的逃逸能力。由于在火灾环境中个体情绪差异对路径选择的影响较大,在文章的规划方法中,为个体建立情绪数学模型,不同情绪的个体对路径的选择是不同的。仿真实验表明,文中提出的规划方法能够为不同情绪类型的个体规划出最优逃生路径,避免了局部最优且收敛速度较快。
In the fire environment, aiming at the problem that the ant colony algorithm is easy to fall into the local optimum, an improved ant colony algorithm is used to solve the path planning problem of crowd evacuation in a fire environment. The improvement of the ant colony algorithm is divided into two aspects: one is to consider the factor of human density in the heuristic function of the ant colony algorithm; the other is to adjust the pheromone intensity dynamically and adaptively, and adopt the strategy updating combining local and global pheromone updating Path pheromone, and the introduction of cross-operation, speed up the algorithm’s ability to escape. Due to the great influence of individual emotions in the fire environment on the path selection, in the article planning method, the emotional mathematical model is established for individuals, and the individuals of different emotions have different path selection. Simulation results show that the planning method proposed in this paper can plan the optimal escape route for individuals with different types of emotions, avoiding the local optimum and fast convergence.