Bearing capacity of conical footing on anisotropic and heterogeneous clays using FEA and ANN

Abstract

The paper presents axisymmetric FEA solutions for the bearing capacity of conical footings embedded in anisotropic and inhomogeneous clays using NGI-ADP model. The bearing capacity factor of conical footings is defined to be a function of three dimensionless parameters: (i) the cone apex angle, (ii) the increasing strength gradient ratio, and (iii) the anisotropic shear strength ratio. A series of parametric studies is carried out to portray the influence of all input parameters on the bearing capacity factors. Based on the FEA results of 216 investigated cases, the artificial neural network (ANN) is adopted to capture the relationship between input parameters and output bearing capacity factors. The complex relationship between input parameters and output bearing capacity is studied through the use of design charts and failure patterns. A new accurate equation with a high value of R2 is proposed and the sensitivity of each input parameter on the output results is scored by adopting the results from the ANN model. This study has provided some practical insights into the performance of conical footings embedded in anisotropic and inhomogeneous clays.