Evaluation of SPT-N values and internal friction angle correlation using artificial intelligence methods in granular soils

Abstract

Context Artificial neural networks (ANNs) and genetic algorithms (GAs) have become widely used in various engineering fields due to their ability to solve complicated issues directly. Aims In this study, internal friction angle (ϕ) values for granular soils were calculated using ANNs, GAs, and empirical methods based on standard penetration test (SPT) data to designate the system that produced the best statistical outcomes. Methods Utilising the literature, experimentally determined internal friction angle (Eϕ) values were obtained for a significant quantity of standard penetration test data. Analysis of variance was performed to ascertain whether there was a significant correlation between SPT-N60 values and Eϕ. A simulated network was created with ANNs, and a function was obtained with GAs for SPT-N60–ϕ correlation. The outcomes obtained with ANNs and GAs were compared with empirical equations and experimental results. Optimisation analysis was conducted with the novel Improved Goal Attainment method to minimise the margin of error. Key results Compared to the GAs and empirical equations, the ANN has been determined to have a reasonable correlation with experimental results. Conclusions It was determined that by utilising ANNs, the current empirical equations indicating the relationship between different soil parameters and the data of tests such as SPT and cone penetration test (CPT) could be produced in improved correlations by employing a large number of data sets obtained from different regions. Implications Effective predictions can be achieved instead of present methods.