Abstract:
The shortage of available and suitable construction sites in city centres has led to the increased use of problematic areas, where the bearing capacity of the underlying deposits is very low. The reinforcement of these problematic soils with granular fill layers is one of the soil improvement techniques that are widely used. Problematic soil behaviour can be improved by totally or partially replacing the inadequate soils with layers of compacted granular fill. The study presented herein describes the use of artificial neural networks (ANNs), and the multi-linear regression model (MLR) to predict the bearing capacity of circular shallow footings supported by layers of compacted granular fill over natural clay soil. The data used in running the network models have been obtained from an extensive series of field tests, including large-scale footing diameters. The field tests were performed using seven different footing diameters, up to 0.90 m, and three different granular fill layer thicknesses. The results indicate that the use of granular fill layers over natural clay soil has a considerable effect on the bearing capacity characteristics and that the ANN model serves as a simple and reliable tool for predicting the bearing capacity of circular footings in stabilized natural clay soil.