基于神经网络方法对多层砖房震害预测

英文篇名：Earthquake Damage Prediction of Multistory Masonry Building Base on Neural Network
中文刊名：黑龙江八一农垦大学学报
英文刊名：Journal of Heilongjiang Bayi Agricultural University
作者：马令勇 ; 刘功良 ; 姜伟
英文作者：Ma Lingyong1 ; Liu Gongliang1 ; Jiang Wei2 (1.The Architecture Engineering Department of Daqing Petroleum Institute ; 163318 ; 2. College of Engineering ; Heilongjiang Bayi Agricultural University)
中文关键词：人工神经网络 ; 震害预测 ; 贝叶斯正则化算法 ; 多层砖房
英文关键词：artificial neural network ; earthquake damage prediction ; bayesian regularization algorithm ; multistory masonry building
出版日期：2010-10-15
机构：大庆石油学院土木建筑工程学院;黑龙江八一农垦大学工程学院;
年：2010
期：05
出版单位：黑龙江八一农垦大学学报

摘要

强烈的地震给人们生命财产带来巨大损失,为了能够在地震之前预测出建筑物震害,提出一多层砖房为例。利用MATLAB神经网络工具箱,建立一种基于贝叶斯正则算法的BP神经网络模型,并以过去发生地震地区的多层砖房调查数据为震害因子的震害预测方法。结果表明:对多层砖房的震害样本的预测达到理想效果。
A strong earthquake causes huge losses for people’s life and property. In order to predict the building earthquake damage before earthquake,we take the multistory masonry building as the sample to propose by MATLAB neural network toolbox,we should establish one kind of BP neural network model based on Bayesian method and take the survey data of multistory masonry building as the earthquake damage prediction method of earthquake damage factor. The result indicates that the method can achieve an ideal effect for predicting earthquake damage of the multistory masonry building .

引文

[1]赵文津.就汶川地震失报探讨地震预报的科学思路——再论李四光地震预报思想[J].中国工程科学,2009,11(6):4-15.
    [2]吴育才.单层厂房震害预测方法的补充[J].工程抗震,1988(1):35.
    [3]徐敬海,刘伟庆,邓民宪.建筑物震害预测模糊震害指数法[J].地震工程与工程振动,2002,22(6):84-88.
    [4]常业军,吴曙光,张坤勇.底层框架砖房的震害预测方法[J].四川建筑科学研究,2001,27(2):51-53.
    [5]刘恢先.唐山大地震震害(第2册)[M].北京:地震出版社,1986.
    [6]蒲春,孙政顺,赵世敏.Matlab神经网络工具箱BP算法比较[J].计算机仿真,2006,23(5):142-144.