Estimation of diaphragm wall deflections for deep braced excavation in anisotropic clays using ensemble learning

作     者：Runhong Zhang Chongzhi Wu Anthony T.C.Goh Thomas Bohlke Wengang Zhang Runhong Zhang;Chongzhi Wu;Anthony T.C.Goh;Thomas Böhlke;Wengang Zhang

作者机构：School of Civil EngineeringChongqing UniversityChongqing400045China School of Civil and Environmental EngineeringNanyang Technological University639798Singapore Institute of Engineering MechanicsKarlsruhe Institute of Technology(KIT)Kaiserstraße 1076131KarlsruheGermany Key Laboratory of New Technology for Construction of Cities in Mountain AreaChongqing UniversityMinistry of EducationChongqing400045China 

出 版 物：《Geoscience Frontiers》 (地学前缘（英文版）)

年 卷 期：2021年第12卷第1期

页      面：365-373页

核心收录：

学科分类：081401[工学-岩土工程] 08[工学] 0814[工学-土木工程] 

基　　金：supported by the High-end Foreign Expert Introduction program(No.G20190022002) Chongqing Construction Science and Technology Plan Project(2019-0045) the Science and Technology Research Program of Chongqing Municipal Education Commission(Grant No.KJZD-K201900102) The financial support is gratefully acknowledged 

主　　题：Anisotropic clay NGI-ADP Wall deflection Ensemble learning eXtreme gradient boosting Random forest regression 

摘      要：This paper adopts the NGI-ADP soil model to carry out finite element analysis,based on which the effects of soft clay anisotropy on the diaphragm wall deflections in the braced excavation were *** than one thousand finite element cases were numerically analyzed,followed by extensive parametric *** models were developed via ensemble learning methods(ELMs),including the e Xtreme Gradient Boosting(XGBoost),and Random Forest Regression(RFR)to predict the maximum lateral wall deformation(δhmax).Then the results of ELMs were compared with conventional soft computing methods such as Decision Tree Regression(DTR),Multilayer Perceptron Regression(MLPR),and Multivariate Adaptive Regression Splines(MARS).This study presents a cutting-edge application of ensemble learning in geotechnical engineering and a reasonable methodology that allows engineers to determine the wall deflection in a fast,alternative way.