期刊
SOIL DYNAMICS AND EARTHQUAKE ENGINEERING
卷 104, 期 -, 页码 276-295出版社
ELSEVIER SCI LTD
DOI: 10.1016/j.soildyn.2017.09.016
关键词
Concrete damage; Dams; Reliability; Classification; Randomness; Support vector machine
This paper presents possible combination of structural responses of concrete dams with machine learning techniques. Support vector machine (SVM) method is adopted and two broad applications are presented: one for a simplified flood reliability assessment of gravity dams and the other for detailed nonlinear seismic finite element method (FEM) based analysis. Up to seventeen random variables are considered in the former example and the results of SVM contrasted with classical reliability analyses techniques (i.e., first- and second-order reliability methods, Monte Carlo simulation, Latin Hypercube and importance sampling techniques). For the latter example, a FEM-SVM based hybrid methodology is proposed for reduction of number of nonlinear analyses. A discussion is provided on the relation between the optimal earthquake intensity measures, the damage states and the accuracy of prediction. It is found that the family of SVM (i.e. standard, least squares, multi-class and regression) is an useful and effective tool for classification, response prediction and reliability analysis of the concrete dams with reasonable accuracy.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据