主管：中华人民共和国应急管理部
主办：应急管理部天津消防研究所
ISSN 1009-0029  CN 12-1311/TU
消防科学与技术

消防科学与技术 ›› 2022, Vol. 41 ›› Issue (8): 1066-1072.

• • 上一篇    下一篇

教学建筑室内火灾应急疏散路径寻优算法研究

李晟延1，马鸿雁1,2,3，窦嘉铭1，叶永雪1   

  1. （1.北京建筑大学 电气与信息工程学院，北京 100044；2.建筑大数据智能处理方法研究北京市重点实验室，北京 100044；3.智慧城市国家级虚拟仿真实验教学中心，北京 100044）
  • 出版日期:2022-08-15 发布日期:2022-08-15
  • 作者简介:作者简介：李晟延(1997-)，男，北京人，北京建筑大学电气与信息工程学院硕士研究生，主要从事火灾应急疏散、建筑能耗预测，北京市大兴区黄村镇永源路15号，100044。
  • 基金资助:
    ：北京建筑大学博士基金项目（ZF15054）

Research on the optimization algorithm of indoor fire emergency evacuation path for teaching buildings

LI Sheng-yan1, MA Hong-yan1,2,3, DOU Jia-ming1, YE Yong-xue1   

  1. (1. School of Electrical and Information Engineering, Beijing University of Civil Engineering and Architecture, Beijing 100044, China; 2. Beijing Key Laboratory of Intelligent Processing for Building Big Data, Beijing 100044, China; 3. National Virtual Simulation Experimental Center for Smart City Education, Beijing 100044, China）
  • Online:2022-08-15 Published:2022-08-15

摘要： 为解决建筑内人员疏散模拟时间长、效率低、无法根据火灾情况改变疏散方向的问题，提出一种新型的混合路径规划算法。首先，在A*算法中加入奖惩机制并对启发函数进行改进。其次，通过改进斥力函数解决人工势场算法易陷入局部极小值的问题。最后，将两种算法组合，构成一种混合路径规划算法。通过对某教学建筑应用BIM和PyroSim软件进行建模与分析,验证混合路径规划算法的可行性。结果表明，所提算法不仅能够快速找到最优疏散路径，还可以避免疏散路径经过危险区域。与单一算法相比，混合路径规划算法遍历节点个数更少，路径平滑性与路径规划效果更好，路径规划效率更高。

关键词: 路径规划, 混合路径规划算法, A*算法, 人工势场算法

Abstract: A novel hybrid path planning algorithm is proposed to solve the problems of long simulation time and low efficiency of evacuation of people in buildings, and the inability to change the evacuation direction according to the fire situation. First, a reward and punishment mechanism is added to the A* algorithm and the heuristic function is improved. Secondly, the problem that the artificial potential field algorithm is easy to fall into local minima is solved by improving the repulsion function. Finally, the two algorithms are combined to form a hybrid path planning algorithm. The feasibility of the hybrid path planning algorithm is verified by modeling and analyzing an educational building with BIM and PyroSim software. The results show that the proposed algorithm can not only find the optimal evacuation path quickly, but also avoid the evacuation path to pass through the dangerous area. Compared with a single algorithm, the hybrid path planning algorithm has fewer traversing nodes, better path smoothness and path planning effect, and higher path planning efficiency.

Key words: path planning, hybrid path planning algorithm, A* algorithm, artificial potential field algorithm