基于BP神经网络的客船疏散时间快速预测模型

Rapid prediction model of passenger ship evacuation time based on BP neural network

为快速准确地预测客船人员疏散时间,将具有良好计算精度的疏散仿真模型与具有较高计算效率的BP人工神经网络模型相结合,提出一种快速预测客船人群疏散时间的方法,以不同场景客船疏散仿真结果作为数据驱动,构建客船人群疏散时间的BP神经网络预测模型。结果表明:该方法计算效率高,对不同疏散场景的预测相对误差为0.9%~3.6%,可为客船应急管理提供决策依据和新的技术工具。

In order to quickly and accurately predict the evacuation time of passenger ships personnel, an evacuation simulation model with good calculation accuracy was combined with a BP artificial neural network model with high calculation efficiency, and a method for quickly predicting the evacuation time of passenger ships was proposed. Based on the simulation results of passenger ships evacuation in different scenarios, a BP neural network prediction model for the evacuation time of passenger ships personnel was constructed. The results show that the proposed method has high calculation efficiency, and the prediction relative error of different evacuation scenarios is 0.9%~3.6%, which can provide decision-making basis and new technical tools for passenger ship emergency management.