面向大型场馆疏散的改进多蚁群算法

摘要

针对大型场馆应急疏散的路径优化问题,提出了一种基于遗传算法交叉变异算子的多蚁群算法.该算法通过引入多蚁群信息素组的概念,将遗传算法交叉和变异的思想应用到信息素更新模型中,解决了传统蚁群算法易陷入局部最优的问题.最后,将此模型应用在武汉体育馆及其周边路网集成环境中.实验结果表明,该算法能够为大型场馆中大规模人群提供一个有效可行的疏散方案.%For the problems of emergency evacuation route optimization in large public building, this paper proposed an improved multi-ant colony algorithm based on crossover-mutation operator of genetic algorithm. By introducing the concept of multi-pheromone, the algorithm applied the idea of crossover and mutation of genetic algorithm to the pheromone update model and solved the problem of trapping in local optima of traditional ant colony algorithm. Finally, it applied this model to Wuhan Stadium to simulate the whole evacuation process. By simulating the process of pedestrian evacuation with this model, the results show the feasibility of this algorithm, so as to provide a scientific basis for guiding the real evacuation process.