Finite element and ANN-based prediction of bearing capacity of square footing resting on the crest of c-φ soil slope

Abstract

For footings located on or near a slope, the slope face acts as a finite boundary that leads to an inadequate development of the resisting passive zone. Depending upon the footing location and slope inclination, the outward deformation of the soil from beneath the loaded footing might lead to substantial reduction in the bearing capacity. A series of finite element analysis has been carried out using Plaxis 3D vAE.01 to investigate the bearing capacity of a square footing placed on crest of the slope. The effect of various geotechnical and geometrical parameters of the footing has also been investigated. Based on the simulated outcomes, an optimal 7-10-1 artificial neural network (ANN) architecture has been developed for the direct prediction of bearing capacity based on the input parameters. Sensitivity analysis conducted using Garson’s algorithm and connection weight approach revealed that angle of internal friction of the slope constituent material and the embedment depth have the highest importance ranking.