摘要
利用有限元分析软件ANSYS分析岸坡位移场,取不同土层测点处的位移和弹性模量作为神经网络的输入层与输出层,利用同时反演法与分层迭代反演法分别反演土体弹性模量。为验证反演结果的准确性,将2种方法反演得到的弹性模量分别进行有限元正分析,结果显示,2种正分析得到的测点计算位移与实测位移误差均较小;采用分层迭代反演法反演所得的弹性模量进行正分析,位移准确度更高。
The displacement of bank slope is analyzed by finite element analysis software ANSYS. The displacement values of soils and the elastic modulus of corresponding soil layers are taken as the input layer and the output layer of neural network respectively. The simultaneous inversion method and the hierarchical iterative inversion method are used to carry out the inversion of elastic modulus respectively. In order to verify the accuracy of inversion results, the elastic modulus obtained by two inversion methods are analyzed by using finite element analysis. The results show that the errors between calculated displacement and measured displacement of two methods are all smaller. and the elastic modulus simulation results obtained by hierarchical iterative inversion method are better fitted with the measured displacement series.
作者
刘学德
黄铭
LIU Xuede;HUANG Ming(School of Civil Engineering, Hefei University of Technology, Hefei 230009, Anhui, China;Key Laboratory of Geological Hazards on Three Gorges Reservoir Area of Ministry of Education, China Three Gorges University, Yiehang 443000, Hubei, China)
出处
《水力发电》
北大核心
2018年第5期36-39,共4页
Water Power
基金
安徽省科技攻关计划项目(1604a0802106)
水利部公益性行业专项经费资助项目(201401063-02)
三峡库区地质灾害教育部重点实验室(三峡大学)开放研究基金(2015KDZ03)
关键词
岸坡工程
神经网络
有限元分析
位移场
弹性模量
bank slope engineering
neural network
finite element analysis
displacement field
elastic modulus