Using FEM-AI Technique to Predict the Behavior of Strip Footing Rested on Undrained Clay Layer Improved with Replacement and Geo-Grid

The objective of this research is to predict how strip footings behave when rested on an undrained clay layer enhanced using a top replacement layer with and without a geo-grid. The study was conducted in several stages, including collecting load-settlement curves from "Finite Element Method" (FEM) models with different clay strengths, replacement thicknesses, and axial stiffnesses of the geo-grid. These curves were then idealized using a hyperbolic model, and the idealized hyperbolic parameters were predicted using three different AI techniques. According to the numerical results, the ultimate bearing pressure of pure clay models was found to be five times the undrained strength of the clay. These findings align with most established empirical bearing capacity formulas for undrained clays. The results also suggest that the initial modulus of the subgrade reaction is solely influenced by replacement thickness. Additionally, the enhancement in subgrade reaction due to the replacement layer decreases with increasing clay strength. However, the percentage of improvement decreased with higher clay strength. Moreover, the impact of the geo-grid was significant for settlement beyond 50mm, and it was more impactful in soft clay than in stiff clay. Finally, the research proposed predictive models employing the "Genetic Programming" (GP), "Artificial Neural Networks" (ANN), and "Evolutionary Polynomial Regression" (EPR) techniques, and these models exhibited an accuracy of about 88%. Doi: 10.28991/CEJ-2023-09-05-014 Full Text: PDF