Using ANN for Predicting Bearing Capacity of Shallow Foundations

Abstract

Shallow foundations ensure the stability of the building when acting as a transmission load from the structure to the soil layer. Therefore, the bearing capacity of shallow foundations is an important indicator to determine the stability of the building. However, determining the bearing capacity of shallow foundations is a challenge for geotechnical engineers, and expensive to manipulate. In this investigation, Artificial neural network (ANN) model is used to predict the bearing capacity of shallow foundations. To perform the simulation, 50 experimental data were collected from the literature. The data set consists of 2 groups of input variables (geometric dimensions of foundation, physical properties of soil) and output variables (bearing capacity of foundation). Evaluation of the models was made and compared on training data set (70% data) and testing data set (30% remaining data) by criteria of Pearson’s correlation coefficient (R) and root mean square error (RMSE). The results show that the ANN model can accurately predict the bearing capacity of shallow foundations.