Experimental and Computational Analysis of lime-treated geogrid-reinforced Silty Sand Beneath Circular Footings

Abstract

The endeavor of civil and geotechnical engineers to enhance soil stability and durability, reduce settlement, and optimize construction costs is a considerable challenge. Given the intricate nature of these complexities, it is important to note the increasing recognition of ground improvement methods, particularly the use of geosynthetics for reinforcement. Considering these factors, a detailed series of model experiments was conducted to explore the intricate dynamics of load-settlement relationships. This study involved experiments to examine the effects of various geogrid placements and lime content on the mechanical properties and settlement behavior of silty sand reinforced with a single layer of geogrid. Additionally, this research introduces novel computational approaches, specifically artificial neural network (ANN) and extreme learning machine (ELM) models, which utilize evolutionary algorithms and artificial intelligence (AI). These techniques are employed to predict the soil’s load-bearing capacity. Incorporating computational models offers an advanced methodology for predicting the ultimate bearing capacity (UBC) of circular footings in a straightforward and cost-effective manner. The accuracy of these computational models was assessed using well-established statistical measures. The results indicate that the artificial neural network (ANN) model surpasses the extreme learning machine (ELM) model in estimating the ultimate bearing capacity (UBC) of circular footings. This study makes a significant contribution to the field by improving our understanding of soil behavior under various conditions, thus providing crucial insights for enhancing the efficiency and reliability of foundation design.