Axial capacity prediction for driven piles at Macao using artificial neural network

A back-propagation neural network model is proposed for estimation of pile bearing capacity from dynamic stress wave data together with the properties of the driven pile. The bearing capacity predicted by TNOWAVE was employed as the desired output in training. Three network models were used to predict the total, shaft and toe resistance of the pile, respectively. The study showed that the neural network model predicted total bearing capacity reasonably well compared with TNOWAVE solution, and the prediction for shaft resistance and toe resistance were also in acceptable range. The neural network provides a method for prediction of pile bearing capacity, which is reliable but less dependent on experienced personnel than the signal matching method.