Modelling and interpreting evacuation time and exit choice for large-scale ancient architectural complex using machine learning

Wang, Yi; Chen, Jialiang; Hu, Yi; Weng, Xinran

doi:10.1016/j.jobe.2023.108133

Cited by 3 publications

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

Rescue guiders layout study based on a two-layer optimization framework

Wang,

Yuan,

Yao

2024

Urban Lifeline

View full text Add to dashboard Cite

In an emergency evacuation, the free evacuation of pedestrians can make the entire evacuation process slow and dangerous. To limit the free behavior of pedestrians and reduce the interaction between pedestrians, a reasonable layout of the guider can improve the efficiency and safety of evacuation. How to set the number, location, and exit allocation of guiders requires further investigation. In the current study, we transform the evacuation into a multi-objective optimization problem. A two-layer optimization framework is developed. In the upper level, the improved NSGA-II multi-objective algorithm is introduced to generate the favorable guider layout, and a chromosome fragment deletion operator is added to improve the optimization efficiency. In the lower layer, the agent movement simulation model is used to simulate the evacuation dynamic of crowd under the favorable guider layout. The variables of this multi-objective solution model in the upper layer are the number and location of the guiders. The evacuation time and agent movement cost are calculated by the lower layer simulation as the objective values of the solution sample, and guide the iterative search process to obtain more reasonable optimization results. The developed model is verified and then applied to a fictional scenario. The number, initial position and exit allocation of guiders are obtained by optimizing the iterative process. The results show that the near optimal solution can be applied in various visibility conditions, and the evacuation efficiency is much higher than that of unguided evacuation. This optimization framework can provide theoretical and methodological support for emergency evacuation planning.

show abstract