Sahu, R., Patra, C.R., Sivakugan, N., and Das, B.M. (2017) Use of ANN and Neuro Fuzzy Model to predict bearing capacity factor of strip footing resting on reinforced sand and subjected to inclined loading. International Journal of Geosynthetics and Ground Engineering, 3. 29.

PDF (Published Version) - Published Version Restricted to Repository staff only

6

Abstract

Laboratory model tests have been conducted on a strip foundation resting over multi-layered geogrid-reinforced dense and loose sand subjected to inclined load. In this study, two different approaches are proposed, namely, artificial neural network (ANN) and Adaptive Neuro Fuzzy Inference system (ANFIS) to determine the reduction factor for ultimate bearing capacity of shallow foundations on reinforced soil. Firstly, ANN model is proposed to determine the reduction factor which can be used to estimate the ultimate bearing capacity of an inclined loaded foundation from the ultimate bearing capacity of a vertically loaded foundation. A thorough sensitivity analysis was carried out to find out the important parameters affecting the reduction factor. The results from ANN were compared with the laboratory model test results and these results are in good agreement. Secondly, ANFIS is proposed to determine the reduction factor. A neuro fuzzy system is a fuzzy system that uses a learning algorithm derived from neural network theory to determine its parameters by processing data samples. Performance of neurofuzzy model was comprehensively evaluated with that of independent ANN model developed using the same data. The values of the performance evaluation measures such as coefficient of correlation, root mean square error, coefficient of efficiency, mean bias error obtained through the neurofuzzy model are found to be good, which reveals that the neurofuzzy model can be effectively used for the bearing capacity prediction.

Actions (Repository Staff Only)

Item Control Page