A new hybrid simulated annealing-based genetic programming technique to predict the ultimate bearing capacity of piles

The aim of this research is to develop three soft-computing techniques, including adaptive-neuro-fuzzy inference system (ANFIS), genetic-programming (GP) tree-based, and simulated annealing-GP or SA-GP for prediction of the ultimate-bearing capacity (Q(ult)) of the pile. The collected database consists of 50 driven piles properties with pile length, pile cross-sectional area, hammer weight, pile set and drop height as model inputs andQ(ult)as model output. Many GP and SA-GP models were constructed for estimating pile bearing capacity and the best models were selected using some performance indices. For comparison purposes, the ANFIS model was also applied to predictQ(ult)of the pile. It was observed that the developed models are able to provide higher prediction performance in the design ofQ(ult)of the pile. Concerning the coefficient of correlation, and mean square error, the SA-GP model had the best values for both training and testing data sets, followed by the GP and ANFIS models, respectively. It implies that the neural-based predictive machine learning techniques like ANFIS are not as powerful as evolutionary predictive machine learning techniques like GP and SA-GP in estimating the ultimate-bearing capacity of the pile. Besides, GP and SA-GP can propose a formula forQ(ult)prediction which is a privilege of these models over the ANFIS predictive model. The sensitivity analysis also showed that theQ(ult)of pile looks to be more affected by pile cross-sectional area and pile set.

Automated summary

This research develops three soft-computing techniques for predicting the ultimate-bearing capacity of a pile, with the SA-GP model performing the best in terms of correlation coefficient and mean square error. The pile's Q(ult) is most affected by the pile cross-sectional area and pile set.