FELA-DNN framework to predict the seismic bearing capacity of skirted strip footing built on a non-cohesive slope

Abstract

Miscellaneous conditions reduce the bearing capacity of strip footings, including the location of the strip footings near the slopes. Earthquakes can also affect existing infrastructure and reduce the bearing capacity of the footing. Non-cohesive slopes are affected more by this factor. Various methods have been considered to increase the bearing capacity of the footing under these conditions. Using vertical skirt elements in strip footings is one of the most effective solutions. In this study, the seismic bearing capacity of skirted strip footings near a non-cohesive slope was investigated by soft computing. Complex and time-consuming calculations in this field have drawn attention to soft computing methods. Thus, the SBC-SSF dataset (containing 8000 samples) was used to predict the seismic bearing capacity of a skirted strip footing. Accordingly, a comprehensive comparison was made between various regression and Deep Neural Network (DNN) models. Also, three different methods based on soft computing were proposed to predict the seismic bearing capacity of a skirted strip footing adjacent to a non-cohesive slope.