提出利用MATLAB人工神经网络工具箱建立基于贝叶斯正则算法的BP神经网络模型,以地震区多层砖房震害调查数据为因子的震害预测方法。神经网络模型输入震害因子包括建筑的层数、施工质量、房屋整体性等,输出值为建筑物在地震作用下的破坏程度。结果表明,本方法可以对多层砖房的震害样本进行预测并达到较理想的效果。 A BP neural network model based on Bayesian regular algorithm was established by using MATLAB artificial neural network toolbox and the earthquake damage prediction method based on the seismic damage survey data of multi-storey brick houses in seismic area was taken as a factor. The input seismic damage factors of neural network model include the number of building layers, construction quality, house integrity and so on. The output value is the degree of damage caused by the earthquake caused by the building. The results show that this method can predict earthquake damage in multi-story brick houses and achieve better results.