Utilization of Silicon Carbide Waste in Concrete: Experimental Assessment and AI-Driven Compressive Strength Prediction

As global attention increasingly shifts toward sustainability and the well-being of future generations, the use of environmentally friendly materials in construction has gained significant importance. This research investigates the feasibility of utilizing silicon carbide waste (SiCW) as a partial replacement for fine aggregate in concrete mixtures. Renowned for its exceptional thermal resistance, hardness, and durability, SiCW shows potential as an additive to enhance the strength and durability of concrete. Various replacement ratios were tested to evaluate the effects of SiCW on workability, durability, and compressive strength. Experimental results indicate that the inclusion of SiCW improves the mechanical properties of concrete, although it slightly reduces workability due to the angular and coarse nature of its particles. Overall, SiCW proves to be a promising sustainable material, particularly suitable for concrete structures exposed to aggressive environments. Additionally, five machine learning models—Linear Regression (LR), Decision Tree (DT), Random Forest (RF), Support Vector Regression (SVR), and K-Nearest Neighbors (KNN)—were employed to predict compressive strength. Among these, the Decision Tree model demonstrated superior performance based on both Mean Squared Error (MSE) and Mean Absolute Error (MAE), identifying it as the most effective predictive algorithm for this application.