摘要
动态逃生指示系统主要应用于大型综合建筑物内,此系统可根据建筑物内发生的火灾等突发情况动态指示人员疏散逃生,缩短逃生时间提高逃生成功率。通过研究现有动态逃生指示系统路径规划问题,提出一种改进蚁群算法,将Dijkstra算法和蚁群算法相结合,利用Dijkstra算法的全局搜索能力,调整了蚁群算法启发函数中初始信息素分布情况,同时结合探测到的火灾实时信息对蚁群算法的启发函数,转移概率,信息素挥发系数和更新规则进行改进。通过仿真实验表明改进的蚁群算法提高了搜索效率和全局搜索能力,降低了陷入局部最优的可能性并优化了逃生路线。
Dynamic escape indication system was mainly used in large-scale comprehensive building,this system could dynamically indicate evacuation and escape according to unexpected situations such as fires in the building,shorten the escape time and increase the escape power.By studying the path planning problem of the existing dynamic escape indication system,an improved ant colony algorithm was proposed.Combined the Dijkstra algorithm with the ant colony optimization algorithm,used the global search ability of Dijkstra algorithm,the initial pheromone distribution in the heuristic function of ant colony algorithm was adjusted.At the same time,combined with the real-time information of fire detection,the heuristic function,transition probability,pheromone volatilization coefficient and updated rule of ant colony algorithm are improved.Simulation experiments showing that improved ant colony algorithm improves search efficiency and global search ability,reducing the possibility of falling into local optimum and optimizes the escape route.
作者
张苏英
郭宝樑
赵国花
刘慧贤
ZHANG Su-ying;GUO Bao-liang;ZHAO Guo-hua;LIU Hui-xian(College of Electrical Engineering,Hebei University of Science and Technology,Shijiazhuang 050000,China)
出处
《科学技术与工程》
北大核心
2019年第36期258-264,共7页
Science Technology and Engineering
基金
国家自然科学基金(51507048)资助
关键词
大型综合建筑
动态逃生指示系统
蚁群算法
路径规划
large-scale comprehensive building
dynamic escape indication system
ant colony algorithm path planning
