This study systematically studied the moisture characteristic curves, water‐holding capacity, and infiltration performance of different particle sizes of gangue in Nanliang coal mine and Dahaize coal mine by comprehensively using numerical simulation and measured data. The HYDRUS model was used to fit the measured moisture characteristic curve, determine the relevant soil parameters, and perform numerical simulations through the set boundary conditions to verify the reliability of the model. The results show that as the particle size of the gangue increases, the saturated water content gradually decreases, and the gangue with a smaller particle size exhibits a superior water‐holding capacity. In terms of wetting front migration, the migration distance of gangue with different particle sizes changes with time in a power function relationship, and the migration speed of gangue with a particle size of 1.25–2.5 mm is the fastest. Infiltration experiments show that gangue with a smaller particle size has a higher infiltration rate and a longer saturation time. The influence of coal gangue particle size on the water retention capacity and permeability of coal gangue is greater than the influence of coal gangue type on the water retention capacity and permeability of coal gangue. The gangue of Nanliang coal mine shows significant advantages in moisture characteristics, and its water‐holding capacity and infiltration performance are significantly better than those of Dahaize coal mine. This study systematically quantified the effects of different particle sizes of coal gangue on soil water retention characteristics, providing a new theoretical basis for its application in soil improvement. By combining numerical simulation and measured data verification methods, the accuracy and reliability of the research results were improved, providing an important reference for similar studies in the future. In addition, the significant effects of coal gangue particle size on soil wetting front migration speed and profile water content were revealed, providing new insights and basis for optimizing water resource management strategies.
Cemented backfill coal mining technology is gradually becoming a key technology for green mining of coal resources. And cemented backfill materials generally have congenital defects such as poor crack resistance, poor durability, and high brittleness, which restrict the promotion and application of cemented backfill coal mining technology. Due to the complex stress environment of in situ stress, mining stress, water pressure, and gas pressure, cemented backfill materials need to have good mechanical properties, and glass fiber is usually used to mix into cemented backfill materials to improve its performance, but there are many problems including complex testing process, high cost, and long time-consuming in the study of mechanical properties of glass fiber-modified cemented backfill materials (GFCBM) by laboratory tests. Consequently, this study proposed and compared four artificial intelligence models to forecast the tensile strength of GFCBM. Firstly, the laboratory tests of tensile properties of GFCBM under different influence factors were implemented to supply the prediction model with dataset. The input variables are aeolian sand content, cement content, glass fiber length, and glass fiber content, and the output variable is the tensile strength of GFCBM. The correlation coefficient (), mean absolute error (MAE), and root mean square error (RMSE) are selected to assess the estimated performance of the hybrid intelligent model. The results indicate that the four hybrid artificial intelligence models show a latent capacity for forecasting the tensile strength of GFCBM, and according to the order from high to low, the prediction ability of the four prediction models is as follows: ABC-SVM, GA-SVM, SSA-SVM, and DE-SVM, and the corresponding values are 0.9555, 0.9539, 0.9413, and 0.9359, respectively. The research findings are beneficial to promote the application of cemented backfill coal mining technology.
Coal gangue, an industrial solid waste generated during coal mining and processing, poses significant environmental challenges due to long-term stockpiling and landfilling. Its comprehensive utilization requires not only decarbonization but also the enrichment of valuable components such as calcium and magnesium through hydrocyclone separation. In this study, the multicomponent occurrence characteristics of coal gangue were examined at the microscale, and the flow-field behavior of hydrocyclones was investigated using computational fluid dynamics (CFD). Based on these insights, a hydrocyclone enrichment system for calcium and magnesium was developed by optimizing cyclone structure and operational parameters. The raw coal gangue exhibited a high ash content (81.66%), mainly composed of Al and Si, with 2.39% Ca and 0.46% Mg. After crushing to 0–1 mm, Ca was enriched in coarse, high-density fractions, while Mg was concentrated in fine, high-density fractions. In the conventional hydrocyclone, increasing feed velocity improved pressure and tangential velocity but caused instability in the locus of zero vertical velocity (LZVV) and air-core morphology, limiting separation accuracy. The bottom-impact hydrocyclone demonstrated superior performance at an impact-tube height of 80 mm and an impact velocity of 5 m/s, achieving improved pressure distribution, higher tangential velocity, and more stable air-core symmetry. Compared with the conventional design, the optimized structure enhanced classification efficiency from 92.47% to 96.13% and increased the Ca content in the underflow to 3.53%. However, Mg separation remained limited under all tested conditions.