首页 | 本学科首页   官方微博 | 高级检索  
     检索      

基于神经网络的岩土工程结构随机有限元分析
引用本文:邓建,朱合华.基于神经网络的岩土工程结构随机有限元分析[J].同济大学学报(自然科学版),2002,30(3):269-272.
作者姓名:邓建  朱合华
作者单位:同济大学地下建筑与工程系,上海,200092
基金项目:中国博士后科学基金资助项目
摘    要:针对有限元蒙特卡罗法计算量大的弊端和岩土工程结构功能函数不能用显式表达的可靠性分析问题,提出并论证了基于神经网络的随机有限元(有限元蒙特卡罗)分析法。神经网络具有高度非线性的映射能力,可用来逼近结构响应量与随机变量的映射关系。通过典型岩土工程结构的应用实例分析,初步显示了基于神经网络的有限元蒙特卡罗法的应用效果和前景。

关 键 词:神经网络  有限元蒙特卡罗法  可靠性分行  结构分析  岩土工程  非线性映射能力
文章编号:0253-374X(2002)03-0269-04
修稿时间:2001年2月9日

Finite Element Monte- Carlo Method Using Neural Networks for Geotechnical Reliability Analysis
DENG Jian,ZHU He-hua.Finite Element Monte- Carlo Method Using Neural Networks for Geotechnical Reliability Analysis[J].Journal of Tongji University(Natural Science),2002,30(3):269-272.
Authors:DENG Jian  ZHU He-hua
Abstract:A finite element Monte-Carlo method using artificial neural networks(ANN) is presented in this paper.It is especially useful in such reliability analysis problems as those whose performance funtions are implicit.ANN,a universal approximator,is used to approximate the implicit mapping between structural response variables and basic random variables.ANN is trained and validated by samples generated from selected structural analyses.The tyained ANN is used to compute the response variables and then the reliability index.The new method is proved to be theoretically correct.The application and prospect of the method are illustrated by examples of geotechnical engineering structures'reliability analysis.
Keywords:artificial neural networks  finite element Monte-Carlo method  reliability analysis
本文献已被 CNKI 维普 万方数据 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号