A Multivariate Adaptive Regression Splines model for determining horizontal wall deflection envelope for braced excavations in clays

Abstract The horizontal wall deflection of the braced excavations is influenced by many factors, including the excavation geometry, wall stiffness, soil parameters, struts spacing and so forth. In this study, three-dimensional (3D) finite element (FE) analyses were carried out to examine the corner restraining effects. A series of 3D FE analyses using the Hardening Soil (HS) model were carried out to investigate the effects of the strength of the clay, wall stiffness, excavation length, excavation depth and width, on the horizontal wall deflection envelope induced by braced-excavation in clays. Based on the results, a Multivariate Adaptive Regression Splines (MARS) model able to accurately learn the complicated implicit relationship between the maximum wall deflection envelope and these influential factors as well as the various interaction factors is developed. The developed MARS model is of good interpretability and enables the design engineer to estimate the shape of the wall deflection profiles. In addition, wall deflection profiles computed by this method compare favourably with a number of field and published records.

[1]  Weiwei. Li.  Braced excavation in old alluvium in Singapore. , 2002 .

[2]  Wengang Zhang,et al.  Evaluating stability of underground entry-type excavations using multivariate adaptive regression splines and logistic regression , 2017 .

[3]  Wengang Zhang,et al.  Influence of groundwater drawdown on excavation responses – A case history in Bukit Timah granitic residual soils , 2018, Journal of Rock Mechanics and Geotechnical Engineering.

[4]  Fook Hou Lee,et al.  Application of Large Three-Dimensional Finite-Element Analyses to Practical Problems , 2011 .

[5]  Richard J. Finno,et al.  Three-Dimensional Effects for Supported Excavations in Clay , 2007 .

[6]  Ali Lashkari,et al.  Prediction of the shaft resistance of nondisplacement piles in sand , 2013 .

[7]  Robert Tibshirani,et al.  The Elements of Statistical Learning: Data Mining, Inference, and Prediction, 2nd Edition , 2001, Springer Series in Statistics.

[8]  Anthony T. C. Goh,et al.  Multivariate Adaptive Regression Splines Application for Multivariate Geotechnical Problems with Big Data , 2016, Geotechnical and Geological Engineering.

[9]  Anthony T. C. Goh,et al.  Multivariate adaptive regression splines for analysis of geotechnical engineering systems , 2013 .

[10]  Wengang Zhang,et al.  Assessment of soil liquefaction based on capacity energy concept and multivariate adaptive regression splines , 2015 .

[11]  Michael Long,et al.  Closure of "Database for Retaining Wall and Ground Movements due to Deep Excavations" , 2001 .

[12]  Anthony T. C. Goh,et al.  Multivariate adaptive regression splines and neural network models for prediction of pile drivability , 2016 .

[13]  Christian Moormann,et al.  ANALYSIS OF WALL AND GROUND MOVEMENTS DUE TO DEEP EXCAVATIONS IN SOFT SOIL BASED ON A NEW WORLDWIDE DATABASE , 2004 .

[14]  Chang-Yu Ou,et al.  Three-dimensional numerical analysis of deep excavations with cross walls , 2013 .

[15]  Wengang Zhang,et al.  Assessment of strut forces for braced excavation in clays from numerical analysis and field measurements , 2017 .

[16]  Wenping Gong,et al.  Probabilistic assessment of liquefaction-induced lateral spreads using CPT — Focusing on the 2010–2011 Canterbury earthquake sequence , 2015 .

[17]  Wengang Zhang,et al.  A simple estimation model for 3D braced excavation wall deflection , 2017 .

[18]  G. Wayne Clough,et al.  Construction Induced Movements of Insitu Walls , 1990 .

[19]  Hao Wang,et al.  Predicting tunnel convergence using Multivariate Adaptive Regression Spline and Artificial Neural Network , 2013 .

[20]  Chang-Yu Ou,et al.  Three-Dimensional Finite Element Analysis of Deep Excavations , 1996 .

[21]  Ing Hieng Wong,et al.  Performance of Excavations for Depressed Expressway in Singapore , 1997 .

[22]  Richard J. Bathurst,et al.  Comparison of numerical and analytical solutions for reinforced soil wall shaking table tests , 2011 .

[23]  Wengang Zhang,et al.  A simple prediction model for wall deflection caused by braced excavation in clays , 2015 .

[24]  Min-Yuan Cheng,et al.  Prediction of Diaphragm Wall Deflection in Deep Excavations Using Evolutionary Support Vector Machine Inference Model (ESIM) , 2009 .

[25]  H. V. Langen,et al.  Numerical analysis of soil-structure interaction , 1991 .

[26]  Pijush Samui,et al.  Multivariate Adaptive Regression Spline and Least Square Support Vector Machine for Prediction of Undrained Shear Strength of Clay , 2012, Int. J. Appl. Metaheuristic Comput..

[27]  Youssef M. A. Hashash,et al.  Simplified Model for Wall Deflection and Ground-Surface Settlement Caused by Braced Excavation in Clays , 2007 .

[28]  Wengang Zhang,et al.  Multivariate adaptive regression splines for inverse analysis of soil and wall properties in braced excavation , 2017 .

[29]  B. Chandrasekaran,et al.  Performance of Two Propped Diaphragm Walls in Stiff Residual Soils , 1997 .

[30]  Wengang Zhang,et al.  Estimation of strut forces for braced excavation in granular soils from numerical analysis and case histories , 2019, Computers and Geotechnics.

[31]  Osamu Kusakabe,et al.  A numerical study on ground displacement and stress during and after the installation of deep circular diaphragm walls and soil excavation , 2008 .

[32]  Gordon Tung-Chin Kung,et al.  Estimation of Wall Deflection in Deep Excavation — Neural Network Approach , 2006 .

[33]  L. Sebastian Bryson,et al.  Method for Estimating System Stiffness for Excavation Support Walls , 2012 .

[34]  Paul J Cosentino,et al.  Innovations in Geotechnical Engineering , 2018 .

[35]  Anthony T. C. Goh,et al.  An improvement to MLR model for predicting liquefaction-induced lateral spread using multivariate adaptive regression splines , 2014 .

[36]  Kok Hun Goh,et al.  Performance of braced excavation in residual soil with groundwater drawdown , 2018 .

[37]  Chang-Yu Ou,et al.  Characteristics of ground surface settlement during excavation , 1993 .

[38]  J. Friedman.  Multivariate adaptive regression splines , 1990 .

[39]  Zhandos Y. Orazalin,et al.  Three-Dimensional Analyses of Excavation Support System for the Stata Center Basement on the MIT Campus , 2015 .

[40]  Nii O. Attoh-Okine,et al.  Multivariate adaptive regression (MARS) and hinged hyperplanes (HHP) for doweled pavement performance modeling , 2009 .

[41]  Lidija Zdravković,et al.  Modelling of a 3D excavation in finite element analysis , 2005 .

[42]  C. Hsein Juang,et al.  Estimation of wall deflection in braced excavation in clays using artificial neural networks , 2006 .

[43]  Charles Wang Wai Ng,et al.  Characteristics of wall deflections and ground surface settlements in Shanghai , 2005 .

[44]  Wengang Zhang,et al.  Multivariate Adaptive Regression Splines Approach to Estimate Lateral Wall Deflection Profiles Caused by Braced Excavations in Clays , 2017, Geotechnical and Geological Engineering.

[45]  Chang-Yu Ou,et al.  Performance of Diaphragm Wall Constructed Using Top-Down Method , 1998 .

[46]  Wengang Zhang,et al.  Evaluating seismic liquefaction potential using multivariate adaptive regression splines and logistic regression , 2016 .