LAUSR

It is known that the construction over soft clay is always a great challenge to the geotechnical engineers. The soft clay poses high compressibility and low bearing capacity. It is a common practice to construct piles in the soft clay to transfer the superimposed load to the hard strata below. Construction of stone columns is also a technique of ground improvement normally applied to the soft clay for increase in bearing capacity and reduction in compressibility. Many theories are developed to determine the bearing of a soft soil reinforced with stone columns. However, most of the theories are site specific and do not show a very good match with the field observations. Artificial neural network (ANN) is an analytical tool which can be used to predict some specific behavior of soil like bearing capacity, settlement, etc. based on some input properties like density, shear strength parameters, void ratio, etc. In the present study, 90 data were collected from the previously published literatures to build an ANN model. Five parameters, namely, un-drained cohesion of soft clay (cu), friction angle of stone column material (ϕ), ratio of spacing to diameter of the stone columns (s/d), length of the stone column (l) and number of the stone columns (n) were taken as input data and the bearing capacity as an output. The predicted bearing capacity was compared with the laboratory experimental data and Plaxis 2D data. The predicted values were also compared with the values obtained from the established theories. ANN predicated values showed a very good match even better than any of the established theories. Sensitivity analysis showed that the effect of the ϕ value is maximum on determination of the bearing capacity.