This study investigates the structural behavior of composite double-web steel beams filled with different types of concrete made from a combination of recycled concrete aggregates and normal aggregates. The research includes both experimental and numerical analyses. Seven specimens were tested under symmetrical two-point loading, all having identical geometric properties: a span length of 1100 mm, flange plates 120 mm wide and 6 mm thick, and web plates 3 mm thick and 188 mm deep. The specimens were divided into two groups, with a control beam without concrete infill. Group one included beams filled with normal concrete in different locations (middle region, two sides, and fully filled), while group two mirrored the same fill locations but used recycled concrete instead. The experimental results showed that using normal concrete improved the ultimate load by 10.19% to 55.30%, with the fully filled beam achieving a maximum increase in ductility of about 568% and a stiffness improvement ranging from 2.6% to 39% compared to the control beam. Beams filled with recycled concrete showed increases in ultimate load from 9.52% to 42.03%, ductility improvements of up to 380%, and stiffness enhancements between 4.5% and 8.03%. Numerical modeling using ABAQUS (2021) showed excellent agreement with the experimental results, with differences in ultimate load and maximum deflection averaging 5.5% and 7.9%, respectively.

The growing demand for sustainable pavement materials has driven increased interest in asphalt mixtures incorporating recycled crumb rubber (CR). While CR modification enhances mechanical performance and durability, its often increases initial production costs and energy demand. This study develops an integrated framework that combines machine learning (ML) and economic analysis to identify the optimal balance between performance and cost in CR-modified asphalt overlay mixtures. An experimental dataset of conventional and CR-modified mixtures was used to train and validate multiple ML algorithms, including Random Forest (RF), Gradient Boosting (GB), Artificial Neural Networks (ANNs), and Support Vector Regression (SVR). The RF and ANN models exhibited superior predictive accuracy (R² > 0.98) for key performance indicators such as Marshall stability, tensile strength ratio, rutting resistance, and resilient modulus. A Cost–Performance Index (CPI) integrating life-cycle cost analysis was developed to quantify trade-offs between performance and economic efficiency. Environmental life-cycle assessment indicated net greenhouse gas reductions of approximately 96 kg CO₂-eq per ton of mixture despite higher production-phase emissions. Optimization results indicated that a CR content of approximately 15% and an asphalt binder content of 4.8–5.0% achieve the best performance–cost balance. The study demonstrates that ML-driven optimization provides a powerful, data-based approach for guiding sustainable pavement design and promoting the circular economy in road construction.