Due to the high water absorption of coal gangue aggregate, concrete prepared with a high content of this material exhibits a significantly reduced service life under freeze–thaw conditions. This study evaluates the frost resistance of gel-enhanced coal gangue aggregate concrete modified by incorporating nano-SiO₂ and polypropylene fibre (PPF) to generate more C-S-H gel and form a dense structure with different dosages of air-entraining agent (0, 0.004%, 0.008%, 0.012%, and 0.016%). The research results show that when the admixture content is 0.012%, the concrete still exhibits excellent frost resistance after 100 freeze–thaw cycles. The mass loss is only 4.7%, compressive strength loss is 37%, and dynamic elastic modulus loss is 39%, while the specimen maintains the best apparent integrity. In addition, the capillary water absorption rate, initial capillary water absorption rate, and cumulative water absorption all reach their lowest values under this condition, indicating optimal frost resistance performance. Finally, through regression analysis, a highly accurate predictive model for capillary water absorption was established, providing a theoretical basis for further research on the durability and frost resistance of coal gangue aggregate concrete.

Coal gangue concrete (CGC) is an effective green building material that can promote the resource utilization of solid waste. To study its durability performance and degradation mechanism under sulfate attack with dry-wet cycles, and to realize the intelligent prediction of mechanical properties, this study prepared CGC specimens with a water-to-binder ratio of 0.4, a fine aggregate replacement rate of 20%, and coarse aggregate replacement rates of 0%, 20%, 50%, 80%, and 100%. The specimens were tested under 30, 60, 90, and 120 dry-wet cycles in 10% MgSO₄ solution. Mass loss, relative dynamic elastic modulus, and compressive and flexural strength corrosion resistance coefficients were used as evaluation indices, and SEM and XRD were adopted to analyze microstructural deterioration. A database compiled from literature data was established, and six machine learning models-random forest (RF), artificial neural network (ANN), decision tree (DT), support vector machine (SVM), particle swarm optimization-artificial neural network (PSO-ANN), and particle swarm optimization-support vector machine (PSO-SVM) were constructed to predict the strength corrosion resistance coefficients. Test results indicate that all macroscopic indices first increased and then decreased with the number of dry-wet cycles. Early ettringite and gypsum products filled internal pores, while prolonged sulfate attack caused decalcification and structural degradation of C-S-H gel, resulting in obvious performance loss. The PSO-SVM model showed the best prediction accuracy, with R² values of 0.912 and 0.981 for compressive and flexural strength corrosion resistance coefficients, respectively. Feature importance analysis shows that dry-wet cycles had the most significant negative impact, followed by the coal gangue fine aggregate replacement rate. This study provides support for the durability evaluation and intelligent prediction of coal gangue concrete in sulfate environments.

The layer-by-layer construction process of roller-compacted concrete (RCC) leads to the formation of layer zones, resulting in the transversely isotropic constitutive behavior of the RCC dam. Crucially, the thickness of the layer zone exerts a non-negligible influence on the overall deformation behavior of the RCC dam structure. An analytical expression for the thickness of the layer zone is derived based on the equivalent elastic modulus theory, and the influence of concrete with the same and different properties on the thickness of the layer zone is investigated. Numerical analysis is employed in conjunction with the RCC dam project to quantitatively assess the influence of layer thickness on the displacement of the dam structure. The numerical results demonstrate that considering the thickness of the layer zone leads to a substantial increase in both horizontal and vertical displacements of the dam. Furthermore, the range of extreme values of layer thickness is established using the variational principle of elasticity mechanics. When the elastic modulus ratio of RCC with layer zones to bulk concrete β is 0.85–0.99, a reasonable thickness of the layer can be obtained. When the weakening coefficient k and β are close to 1, the thickness of the layer is close to 10 cm, which is close in nature to the RCC dam.