基于MATLAB神经网络方法的多层砖房震害预测  

Earthquake Damage Prediction of Multistory Masonry Building Based on MATLAB Neural Network Method

作　　者：姜伟[1] 马令勇[2] 刘功良[2] 

机构地区：[1]黑龙江八一农垦大学工程学院,黑龙江大庆163319 [2]大庆石油学院土木建筑工程学院,黑龙江大庆163318

出　　处：《西北地震学报》2011年第2期155-158,共4页Northwestern Seismological Journal

基　　金：黑龙江省教育厅科学技术研究项目(11513015)

摘　　要：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。Using the MATLAB artificial neural network toolbox to establish BP neural network model based on Bayesian regularization algorithm,a method of earthquake damage prediction for multistory masonry building based on the survey data of earthquake damage from earthquake events is proposed.The input earthquake damage factors include building story number,construction quality and house integrity.The output value is building＇s destructiveness under seismic action.The result shows that the method can predict earthquake damage of multistory masonry building with good achievement.

关 键 词：MATLAB 人工神经网络 震害预测 贝叶斯正则化算法 多层砖房 

分 类 号：P315.941[天文地球—地震学]