Prediction of Pile Capacity Using Neural Networks

Abstract

A back-propagation neural network model for estimating static pile capacity from dynamic stress-wave data is proposed. The training and testing of the network were based on a database of 37 precast reinforced concrete (RC) piles from 21 different sites. The CAPWAP-predicted soil parameters were used as the desired output in training. Three different network models were used to study the ability of the neural network to predict the desired output to increasing degree of detail. The study showed that the neural network model predicted the total capacity reasonably well. The neural-network-predicted soil resistance along the pile was also in general agreement with the CAPWAP solution. The capability of the network to generalize from limited training examples was verified by its performance against dynamic test data obtained from non-RC piles.