Chapter 16 - Modeling the Axial Capacity of Bored Piles Using Multi-Objective Feature Selection, Functional Network and Multivariate Adaptive Regression Spline

Abstract

Owing to the variable behavior of soil and the dependence of bearing capacity of piles on numerous factors, there does not exist a definite equation, which can estimate the pile loads accurately and include all the factors comprehensively. The available methods are mostly empirical; therefore, in this paper, the efficient prediction models for determining the axial capacity of bored piles have been presented using recently developed artificial intelligence (AI) techniques, multi-objective feature selection (MOFS). MOFS has been applied with artificial neural network (ANN) and non-dominated sorting genetic algorithm (NSGA II) to find the subset of influential parameters responsible for the axial capacity of bored piles along with the development of prediction equations. Prediction models are also presented using two other AI techniques: multivariate adaptive regression spline (MARS) and functional network (FN). A ranking criterions approach has been implemented to assess the performance of above prediction models, along with other prediction models available in literature.