Application of Machine Learning to Predict the Dimensionless Bearing Capacity of Circular Footing on Layered Sand under Inclined Loads.

The present study aims to utilise machine learning techniques in order to predict the dimensionless bearing capacity (DBCp) of the circular footing on layered sand under inclined loading. For this objective, 2400 data points were collected from the literature using the finite element approach for the circular footing on layered sand under inclined loads. The dimensional bearing capacity (DBC_P) was predicted using the independent variables thickness ratio (H/D), load inclination angle (α₁/90°), unit weight ratio of the loose sand layer to the dense sand layer (γ2/γ1), friction angle ratio of the loose sand layer to the dense sand layer (φ2/φ1), and embedment ratio (u/D). Moreover, sensitivity analysis was performed to evaluate the effect of each independent variable on the structural integrity. At embedment ratios of 0, 1, and 2, the results show that load inclination is the primary factor influencing bearing capacity. In the end, six statistical parameters were used to evaluate the effectiveness of the machine learning model that had been built. For predicting the dimensionless bearing capacity of the circular footing on layered sand under inclined loading, the created model was found to work satisfactorily.