Nondestructive Testing And Evaluation, Journal Year: 2024, Volume and Issue: unknown, P. 1 - 24

Published: Nov. 22, 2024

This study proposes an advanced soft-computing approach for predicting the compressive strength (CS) of bentonite concrete using optimised XGBoost model. Bentonite is valued as a partial cement replacement its environmental benefits and improved properties, but CS remains challenging due to complex constituent interactions. The study's motivation increasing interest in sustainable materials like replacement, which presents unique challenges high plasticity swelling properties. While hybrid models are effective civil engineering, their application prediction limited. research simulates particle swarm optimisation (PSO), genetic algorithm (GA), dragonfly (DO), supported by comprehensive dataset with varied mix proportions multicollinearity analysis. Hyperparameter tuning feature selection techniques were applied optimise model's performance. results demonstrate that PSO-XGBoost best performing model (R2 = 0.974, RMSE 0.038), followed DO-XGBoost GA-XGBoost. All perform better than conventional developed robust based methodology can serve reliable alternative tool concrete, thereby facilitating design development mixtures enhanced performance characteristics.

Language: Английский