基于FEM-ANN-MCS法的边坡工程可靠度分析  

Analysis on the Reliability of the Slope Stability Based on Finite Element Monte-Carlo Method Using Artificial Neural Networks

作　　者：方建瑞[1] 许文达[2] 谢秀栋[1] 

机构地区：[1]同济大学土木工程学院,上海200092 [2]福州大学土木建筑学院,福州350002

出　　处：《地下空间与工程学报》2006年第4期578-581,共4页Chinese Journal of Underground Space and Engineering

摘　　要：针对有限元蒙特卡罗法计算量大的弊端和边坡工程稳定功能函数不能显式表达的可靠度分析问题,文章提出了应用于边坡工程稳定可靠度分析的基于神经网络的随机有限元分析法的基本思路。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。借助这种方法计算出边坡工程的可靠指标,并通过寻求失稳模式进行整体稳定可靠度分析。最后对一工程实例进行几种方法的计算分析,表明该方法用于边坡整体稳定可靠度分析是切实可行的,可供工程科学技术人员参考。In reliability analysis of the slope stability, due to the disadvantage of excessive computation of the finite element Monte Carlo method and the problem of impossible explicit expression by slope function, the basic idea about application of the Monte-Carlo finite element method using artificial neural networks（ANN） to analyze the reliability of slope stability is presented in this paper. ANN is used to approximate the implicit mapping between structural response variables and basic random variables. Then, through calculating the corresponding reliability index and seeking the instability pattern, the whole reliability of the slope stability is analyzed. Finally, the feasibility of this method used to analyze the whole reliability of the slope stability is indicated by one practical example calculated and analyzed using several methods, which can serve as reference to the scientific and technical professionals.

关 键 词：边坡稳定 蒙特卡洛模拟 有限元 神经网络 可靠度分析 

分 类 号：TU43[建筑科学—岩土工程] TB115[建筑科学—土工工程]