Based on the traditional numerical simulation method, the BP neural network technology is introduced to predict the critical wind velocity of tunnel fire under various influencing factors.A two-lane highway tunnel is taken as the research object, a full-size horseshoe tunnel model is established.The FDS simulation is used to study five influencing factors of critical wind velocity, and the variation law of critical wind velocity with various influencing factors is obtained.The influencing factors are taken as input parameters, the experimental data are used as training samples to construct a BP neural network prediction model for the critical wind velocity of highway tunnel fire.The performance test of the prediction model established is tested by test samples.The results show that among all the prediction points, the maximum relative error between the predicted value and the expected value of the model is0.0211, which can meet the precision requirements of fire protection engineering.It can predict the critical wind velocity under multiple influencing factors, and it can provide a new method for the development of engineering calculation model for quickly predicting the critical wind velocity of highway tunnel fire.%在传统数值模拟方法的基础上,引入BP神经网络技术对多种影响因素下隧道火灾临界风速的预测展开研究.以双车道公路隧道为研究对象,建立全尺寸马蹄形隧道模型;利用FDS软件模拟研究临界风速的5个影响因素,得到临界风速随各影响因素的变化规律.将该影响因素作为输入参数,数值模拟试验数据作为训练样本,构建了公路隧道火灾临界风速的BP神经网络预测模型;通过测试样本对所建立的预测模型进行性能测试.结果表明,在所有的预测点中该模型的预测值与期望值的最大相对误差为0.0211,能够很好地满足消防工程的精度需求;较好地预测多种影响因素下的临界风速,为发展快速预测公路隧道火灾临界风速的工程计算模型提供了一种新方法.
展开▼
