基于改进哈里斯鹰算法的消防疏散系统路径规划研究  

Research on route planning of fire evacuation system based on improved Harris Hawks optimization algorithm

作　　者：何志祥 王立纲 董勤 He Zhixiang;Wang Ligang;Dong Qin(Guanghan Branch of Civil Aviation Flight University of China,Guanghan Sichuan 618307,China)

机构地区：[1]中国民用航空飞行学院广汉分院,四川广汉618307

出　　处：《消防科学与技术》2025年第3期347-355,共9页Fire Science and Technology

基　　金：中央高校基本科研专项资金资助(QJ2022-57)。

摘　　要：针对大型公共建筑物发生火灾时疏散难度大的问题,提出了一种基于改进哈里斯鹰算法的消防疏散路径规划方法。首先,通过栅格法对路径规划所需的数字地图进行建模,并以最短路径为目标构建路径规划评价的目标函数。其次,引入拉丁超立方抽样、透镜逆学习策略以及自适应权重因子对传统哈里斯鹰算法进行改进,并采用B-spline曲线平滑方法对规划路径进行平滑处理。最后,在未发生火灾和发生火灾情况下与其他3种算法进行了比较分析,以验证所提算法的优良性能。试验结果表明:所提算法在未发生火灾情况下,平均路径长度为21.82 m,规划时间为20.4 s,比改进前分别减少5.9%和6.8%;在发生火灾时,平均路径长度为22.45 m,规划时间为21.5 s,较改进前减少39.0%和48.8%。与其他算法相比,所提算法在路径搜索速度、平均长度、稳定性等方面均具有良好优势,能够获得最优的路径规划综合性能。Aiming at the problem that it is difficult to evacuate from large public buildings when a fire occurs,a fire evacuation path planning method based on improved Harris Hawks optimization algorithm was proposed.Firstly,the digital map required for path planning was modeled by the grid method,and the objective function of path planning evaluation was constructed with the shortest path as the goal.Secondly,Latin hypercube sampling,lens inverse learning strategy and adaptive weighting factor were introduced to improve the traditional Harris Hawks optimization algorithm,and B-spline curve smoothing method was used to smooth the planning path.Finally,it was compared with the other three algorithms in the case of no fire and fire to verify the excellent performance of the proposed algorithm.The experimental results show that in the case of no fire,the average path length of the proposed algorithm is 21.82 m,and the planning time is 20.4 s,which are reduced by 5.9%and 6.8%respectively compared with those before improvement.In the case of fire,the average path length is 22.45 m,and the planning time is 21.5 s,which is 39.0%and 48.8%lower than that before the improvement.Compared with other comparison algorithms,the proposed algorithm has good advantages in path search speed,average length and stability,and can obtain the comprehensive optimal path planning performance.

关 键 词：路径规划 哈里斯鹰算法 火灾 消防疏散 栅格法 

分 类 号：X913.4[环境科学与工程—安全科学] TU998.12[建筑科学—市政工程]