Multi-Objective Optimization of Evacuation Route for Passengers in Metro Stations Considering Node Efficiency

Reasonable planning of passenger evacuation routes can directly improve the evacuation efficiency in metro stations. Considering the effect of traffic capacity at nodes such as the gate, stair/escalator, a multi-objective optimization model aimed at minimizing the maximum evacuation time of heterogeneous passengers in different segmentation areas is established, which achieves local optimization on the basis of the global optimization of the evacuation route. Node traffic capacity is assessed by a new prediction model of node travel time based on the combination of BP neural network and atomic orbital search algorithm, which is helpful to ameliorate the route optimization strategy. Mass motion with embedded the social force model and the minimum cost model is applied to simulate passenger movement, and its effectiveness is verified by T-independent sample test and nonparametric independent sample test. The simulation results indicate that the performance of the established prediction model of node travel time is good, and the mean square error can be as low as 0.2555. Meanwhile, the proposed route strategy can improve the overall evacuation efficiency by 21.5%, and passengers’ choice of evacuation routes is more reasonable. The sensitivity analysis of factors affecting evacuation through random forest algorithm shows that the number of passengers with person attribute E has the greatest impact on evacuation time, which should be the focus of attention in the evacuation process. The proposed method could help passengers avoid the bottlenecks in advance and realize the safe and efficient evacuation.