The problem of managing effective pedestrian evacuation during disruptions is a significant challenge because of the complexity and randomness of the passenger flow dynamics as well as the difficulty in predicting the responsive behaviour of the passengers. In this study, a hybrid agent-based and discrete-event simulation model of passenger flow is designed and implemented to assess the service level performance and the crowdedness ratio in a transfer metro station. This study investigates the statistical significance of the results obtained by the design alternatives and the safety analysis of a multiple-level transfer station through a real-world case study. The simulation model is designed to test various disruption scenarios, including train failure in the tunnel, as well as fire at the station gallery of a crowded metro station. The simulation result shows that the evacuation time can be decreased by 19.5%, compared with the basic design layout.

由于乘客流动力学的复杂性和随机性以及难以预测乘客的响应行为，因此在中断期间管理有效的行人疏散问题是一个重大挑战。在这项研究中，设计并实现了一种基于混合智能体和离散事件的客流仿真模型，以评估换乘地铁站的服务水平性能和拥挤率。本研究通过实际案例研究，通过设计替代方案和多层转运站的安全性分析获得的结果的统计意义。仿真模型旨在测试各种中断情况，包括隧道中的火车故障以及拥挤的地铁站的车站大火。