Reliability Analysis of Settlement of Pile Group in Clay Using LSSVM, GMDH, GPR

Abstract

Robust and reliable design at certain levels of safety has earned lot of attention in recent. To build over the limitations of FOSM based reliability analysis, the paper proposes least square support vector machine (LSSVM), The Group Method of Data Handling (GMDH) and Gaussian process regression (GPR) based reliability analysis of pile group resting on cohesive soil. LSSVM is an improvement over support-vector machines (SVM) which uses linear systems instead of complex quadratic equations. GMDH is a self-organized neural network capable of solving complex non-linear problems. GPR is an effective Bayesian tool of machine learning the performance of the developed models is ascertained using various statistical parameters and Taylor curves. The reliability indices of the simulated values are compared to that of the actual values obtained from FOSM. The results show that all the models are applicable for reliability analysis of settlement of pile group.