Ultimate Bearing Capacity Prediction of Eccentrically Loaded Rectangular Foundation on Reinforced Sand by ANN

Laboratory model tests were conducted on a rectangular surface foundation resting over multilayered geogrid-reinforced dry sand bed subjected to eccentric load. Based on the model test results, a neural network model was developed to predict the reduction factor that can be used in computing the ultimate bearing capacity of an eccentrically loaded rectangular foundation. This reduction factor (R_k) is the ratio of the ultimate bearing capacity of the foundation subjected to an eccentric load to the ultimate bearing capacity of the foundation subjected to a centric load. A thorough sensitivity analysis was carried out to evaluate the parameters affecting the reduction factor. Based on the weights of the developed neural network model, a neural interpretation diagram is developed to find out whether the input parameters have direct or inverse effect to the output. An ANN equation is developed based on trained weights of the neural network model. The results from artificial neural network (ANN) were compared with the laboratory model test results and these results are in good agreement.