Predictive Modelling of Compression Strength of Waste Gp/Fa Blended Expansive Soils Using Multi-Expression Programming

Abstract

Expansive soils (ES) are unsuitable for construction because of their low shear strength, bearing capacity, unconfined compression strength (UCS), and high shrink-swell potential. This study determines the UCS of waste glass powder (WGP) and Fly Ash (FA) modified ES using a robust computational technique, i.e., multi-expression programming (MEP). The ES was modified using WGP at 0, 5, 10, 15, 20, 25, and 30%, in order to determine the optimum dosage of WGP. Furthermore, FA was incorporated at 0, 5, 8, 11, 14, and 17% in the ES at the optimum WGP content, and their synergistic effect was determined. An experimental dataset was compiled with 180 test results on the unstabilized ES to develop the MEP model. The proposed optimal MEP model relates the UCS at 28 days (UCS 28d ) to its plasticity index, specific gravity, swell potential, and UCS 3d , and UCS 7d . It was also evaluated using different statistical indices, such as correlation coefficient (R), Nash-Sutcliffe efficiency (NSE), coefficient of determination (R 2 ), and error analysis indices (MAE, RMSE, and performance index ρ). The predictive capability of the MEP model was found to be robust based on a wide range of evaluations and hence his model can be used in practical applications by designers and practitioners.

Keywords: Expansive soils, waste glass powder, fly ash, unconfined compression strength, curing, multi-expression programming