An Analysis the bearing capacity factors of ring foundation on dense sand by using finite element limit analysis and hybrid ANFIS algorithms

Abstract

This article presents research on the analysis of the bearing capacity of foundations resting on dense sand using Bolton’s failure criterion. The study focuses on ring foundations under axisymmetric conditions. The analysis is conducted using the upper and lower bound theories of the finite element limit analysis (FELA) method. To better understand the behavior of dense sand based on Bolton’s model, the study examines the relationship between stress and dilation, considering various factors influencing the behavior of dense sand. The results obtained from this analysis are compared with previous research to validate the accuracy of this study. Additionally, a hybrid ANFIS model, which integrates artificial neural networks (ANN) with fuzzy logic to create models of learning from data and adapting, which is similar to the basic concept of the human nervous system, was used to study the relationship between input and output data in order to predict the problem's bearing capacity. The accuracy of using the hybrid ANFIS model was measured using three statistical measures, namely the coefficient of determination (R²), mean absolute error (MAE), and root mean square error (RMSE). The results from the GA-ANFIS approach have values of 0.985, 0.027, and 0.020, respectively, while the PSO-ANFIS approach has values of 0.997, 0.010, and 0.007. These findings indicate that the GA-ANFIS model provides predictions of bearing capacity that are more consistent with the FELA results compared to the PSO-ANFIS model.