基于改进ACO算法的建筑疏散路径优化研究

针对大型公共建筑存在的结构复杂、消防疏散困难等问题，提出了用于优化疏散路径的改进蚁群算法。首先，针对基本蚁群算法(ACO)引入Dijkstra 算法，并利用Dijkstra 算法计算出全局性较好的次优路径进而对蚁群算法初始信息素分布情况进行了加强。其次，根据火灾的实时情况改进了蚁群算法的转移概率、更新规则、信息素挥发系数、启发函数等。最后，对改进的蚁群算法进行对比仿真实验。实验结果表明该算法具有较强的全局搜索能力以及较高的搜索效率，能够避免算法进入局部最优陷阱，有效提高消防疏散路径规划效率。

Optimization of building evacuation path based on improved ACO algorithm

Aiming at the problems of complex structures of large public buildings and difficulties in fire evacuation, an improved ant colony algorithm for optimizing evacuation paths was proposed.First,the Dijkstra algorithm is introduced for the basic ant colony algorithm(ACO),and the Dijkstra algorithm is used to calculate the suboptimal path with better globality to further strengthen the ini?tial pheromone distribution of the ant colony algorithm. Secondly,the transition probability,update rules,pheromone volatility coefficient, heuristic function, etc. of the ant colony algorithm are improved based on the real-time situation of the fire. Finally,a comparative simulation experiment is carried out on the improved ant colony algorithm. Experimental results show that the algorithm hasstrong global search ability and high search efficiency,can avoid entering the local optimal trap,and effectively improve the efficien?cy of fire evacuation path planning.