Estimation of Dynamic Properties of Sand Using Artificial Neural Networks

Abstract

Dynamic properties of soils are usually determined by time-consuming laboratory tests. This study presents a method for estimating dynamic soil parameters using artificial neural networks. A simple feedforward neural network with back-propagation training algorithm is used. The neural network is trained with actual laboratory data, which consists of six input variables. They are the standard penetration test value, the void ratio, the unit weight, the water content, the effective overburden pressure, and the mean effective confining pressure. The output layer consists of a single neuron, representing shear modulus or damping ratio. Results of the neural network training and testing show that predictions of shear modulus by the neural network approach is reliable although it is less successful in predicting damping ratio.