Thermo-Mechanical and Data-Driven Assessment of Sustainable Concrete Incorporating Waste Tire Aggregates and Recycled Steel Fibers

This study examines the impact of recovered steel fibers (WTSFs) and waste tire aggregates of varying sizes—fine (FWTR), small coarse (SCWTR), and large coarse (LCWTR)—on the compressive strength of concrete subjected to elevated temperatures. Forty mixes were formulated utilizing four distinct WTR replacement ratios (0%, 5%, 10%, 20%) and four WTSF doses (0%, 0.5%, 1%, 2%), and evaluated at temperatures of 24 °C, 100 °C, 200 °C, and 300 °C. The findings indicate that elevated temperatures consistently diminish compressive strength, although the reference concrete saw around 18% loss at 300 °C, with WTR-containing mixes demonstrating losses ranging from 25% to 45%, contingent upon rubber size and dose. The type of WTR was critical—LCWTR mixes exhibited superior residual strength retention due to enhanced particle–matrix interlocking, whereas FWTR mixtures saw the most significant decline. The inclusion of WTSF increased strength by 2–10% at 0.5–1.0% fiber content through crack bridging, but excessive fiber addition (2.0%) decreased workability and caused clustering, leading to up to 40% strength loss. The ideal combination was 5LCWTR–1WTSF, which sustained 36.97 MPa at 24 °C and 29.65 MPa at 300 °C, indicating superior performance across all temperature ranges. Predictive modeling utilizing machine learning techniques (SVR, KRR, 1D-CNN, and DRL) corroborated the experimental results, with the CNN attaining the maximum generalization accuracy (R2 = 0.9374) and the KRR exhibiting the most consistent performance (R2 = 0.9305). The models indicated that WTR and temperature were the primary variables diminishing strength, although modest WTSF ratios enhanced overall thermal resilience. SHAP and ALE analysis further validated that WTR content exhibited the most significant negative feature contribution (~−6 MPa), succeeded by temperature, although modest fiber inclusion demonstrated a positive SHAP effect (+2–4 MPa), corroborating the experimentally observed non-linear reinforcement threshold. The combined experimental–computational framework demonstrates that the combination of coarse rubber aggregates (5–10%) with appropriate WTSF content (0.5–1.0%) improves sustainability and high-temperature durability. The integration of physical testing and interpretable AI modeling creates a hybrid approach that can anticipate and enhance thermo-mechanical performance in sustainable concrete systems.