Prediction of friction capacity of driven piles in clay using artificial intelligence techniques

Abstract

Driven piles are widely used due to their easy installation set up and are economical. In this paper, prediction models for predicting friction capacity of piles in clay soils based on experimental test results are developed using two recently developed artificial intelligence techniques; multivariate adaptive regression splines (MARS) and functional networks (FN). The efficacy of developed MARS and FN models has been compared with previously developed models as given in the literature in terms of statistical parameters like correlation coefficient (R), Nash–Sutcliffe coefficient of efficiency (E), absolute average error, maximum average error, root mean square error and normalised mean bias error. Based on statistical performances, MARS and FN models are found to have a better predictive capacity than existing models.