The sustainable application of ultra-high-performance concrete (UHPC) is often constrained by high material costs and environmental footprints. While the individual effects of various industrial wastes have been extensively studied, the synergistic mechanism of multi-source waste in UHPC remains poorly understood. To fill the research gap, an eco-UHPC was developed wherein river sand (RS) was partially replaced by spontaneous combustion gangue sand (SCGS), and Portland cement (PC) was partially replaced by spontaneous combustion gangue (SCG) powder and phosphorous slag (PS). A systematic investigation was conducted to assess the packing density, flowability, mechanical properties, chloride ion penetration resistance, and micromorphology. The results indicate that 40% SCGS substitution (by mass) optimizes particle packing density and aggregate gradation, while PS incorporation significantly improves flowability by up to 16.83%. Notably, persistent pozzolanic reactions and the consumption of Ca(OH)₂ facilitate the generation of dense C-S-H gel, which creates a uniform microstructure and enhances late-stage compressive strength. Furthermore, superior chloride penetration resistance is achieved when the PS content is maintained below 20%. These findings support the synergistic utilization of SCGS, SCG, and PS in UHPC production, while facilitating broader application of UHPC through reduced costs and lower carbon emissions.

Recycled concrete ultra-high performance concrete (RC-UHPC) prepared from recycled concrete sand (RCS) and recycled concrete powder (RCP) represents an important pathway for achieving the high-value utilization of construction and demolition waste. However, influenced by the material properties and compositional complexity, the application of RC-UHPC requires extensive performance optimization trials, a process that is not only inefficient but also accompanied by high costs. To address this challenge, this study introduces machine learning (ML) methods to improve the design efficiency of RC-UHPC, reduce reliance on conventional experimental methods, and facilitate its engineering application. A feature system comprising 11 key input variables, including cementitious materials, admixtures, and RCS with different particle sizes, was established. The performance of various models in predicting the 28-day compressive strength (CS28) of RC-UHPC was systematically evaluated, and the main influencing factors were identified through feature analysis. The results indicate that k-nearest neighbors, random forest, and gradient boosting regression trees are the optimal ML models, with mean R ² values of 0.974 ± 0.014, 0.954 ± 0.008, and 0.971 ± 0.007, respectively, under different random seeds. Feature analysis indicates that steel fibers and fly ash have a significant positive effect on CS28. In contrast, RCS and RCP exhibit a deteriorating effect, and no significant difference is observed in the effect of RCS with different particle sizes (0–1.18 mm and 0–2.36 mm) on CS28. This study analyzes the statistical associations between RC-UHPC performance and its influencing factors from a data-driven perspective. The results can provide scientific guidance for mix design and performance regulation of RC-UHPC in engineering applications.