Hybrid machine learning and genetic algorithm framework for performance-based optimization of sustainable concrete with industrial and polymer wastes

This paper outlines a hybrid experimental and computational model to assess and optimize the mechanical behavior of sustainable concrete with silica fume (SF), waste glass powder (WGP), and crumb rubber (CR). Compared to current research, which mainly concentrates on individual or binary systems, this paper explores a ternary blended system and characterizes the intricate interactions among mix parameters with advanced machine learning methods. To establish compressive, flexural and tensile strengths of 7, 28 and 56 days, experimental investigations were carried out. The findings suggest that SF and WGP increase strength because of pozzolanic reactivity and refinement of microstructure, and CR decreases strength because of the weaker interfacial bonding. Several machine learning models, such as Random Forest, XGBoost, Support Vector Machine, Decision Tree, and Ensemble, were built on the basis of strength prediction with the highest level of accuracy being XGBoost and Ensemble (R2 > 0.88). Moreover, optimization with the help of Genetic Algorithms was used to determine the optimal mix proportions leading to the increase in compressive, flexural, and tensile strengths by 34%, 37%, and 46%, respectively. The proposed framework offers a sound and data-driven methodology of designing high-performance and environmentally friendly concrete mixtures.