Backfill mining has significant advantages in safe mining, solid waste utilization and ecological environmental protection, but solid waste materials (tailings, gangue and coal gasification slag, etc.), as derivative residues of the chemical and metallurgical industries, contain a large number of heavy metal elements, which is posing great challenges to the underground environment after backfill. In order to study the feasibility of bentonite for reducing the permeability of gangue/tailing sand cemented backfill body, relevant tests were carried out from the basic performance index, flow performance and mechanical properties of paste backfill materials. The test results show that bentonite has a significant effect on the water secretion rate of cemented fillers, and also promotes the improvement of slump and diffusion diameter of backfill slurry. The enhancement effect of mechanical properties in the early stage is not obvious, mainly concentrated in the middle and late stages of specimen curing. With the increase of bentonite content, the 28-day uniaxial compressive strength increased from 7.1 MPa and 7.9 MPa to 8.7 MPa and 9.0 MPa, respectively. Bentonite is filled between the pores of the cemented backfill with its fine particles and water swelling, which can reduce the porosity and permeability of the gangue and tailings cemented backfill. Therefore, on the premise of satisfying the flow and mechanical properties of paste backfill, bentonite can be used to improve the permeability of cemented backfill and reduce the leaching and migration of heavy metal ions.

Addressing the difficult problem of predicting the height of water-conducting fracture zones in shallow and thin coal seams, a prediction model of water-conduction fracture zones based on a backpropagation (BP) neural network was developed by integrating theoretical analysis, field measurements, and algorithmic advancements. Firstly, through overburden migration analysis and correlation tests, the height index system of the water-conducting fracture zone was determined. This system includes mining height, buried depth, dip angle, working face width, and overburden rock lithology, with five groups of characteristic parameters. Then, 35 pairs of minefield-measured data were collected to establish the measured height data set of the water-conducting fracture zone. Secondly, a BP neural network prediction model and a traditional support vector regression (SVR) prediction model were constructed based on a Pytorch framework, and the models were trained and tested by selecting data sets. Thirdly, the optimal prediction model was determined by comparing the model with the empirical model and multiple regression model of mining regulations for coal pillar maintenance and pressure in buildings, water bodies, railways, and main shafts. Finally, a typical mine was selected for application to verify the suitability of the optimal model. The results show that: (1) the predicted value of the neural network model is consistent with the change trend of the measured value, which accords with the theoretical law; (2) compared with traditional forecasting methods, the error of the BP neural network prediction model is stable and the prediction effect is the best; (3) dropout can effectively mitigate mitigation training overfitting, achieve regularization, and improve prediction accuracy; (4) the field application further verified that the BP neural network model is the best for predicting the height of water-conducting fracture zones of extremely thin coal seams, and the research results can provide technical guidance for similar fragile coal seams.

To enhance mining safety in coal seam groups underlying ultra-thick sandstone aquifers, this study investigates the Yanjiahe Mine’s geological conditions through physical simulation, numerical modeling, and in-situ monitoring. We analyze the evolution patterns of bed-separation space in No. 5^− 1, 5^− 2, and 8 coal, revealing volume expansion characteristics across mining methods and strata migration mechanisms. Firstly, through physical simulation of upward mining of No. 8 and 5^− 1 coal and downward mining of No. 5^− 2 coal, it is determined that the bed-separation volume of coal seam group mining has the expansion characteristics of Fracture Type (FT) → Cavity Type (CT) → Cavity + Fracture Type (CFT)→ Fracture Type (FT). Secondly, through numerical simulation of upward mining of No. 8 and 5^− 1 coal and downward mining of No. 5^− 2 coal, it is determined that the bed-separation strata have the migration laws of Lower Type (LT) → Higher Type (HT) → Lower Type (LT). Finally, by observing the overlying strata of 8105, 5105, and 5205 working faces through borehole peeping, the evolution laws of bed-separation are obtained as Lower Fracture Type (LFT) → Lower Cavity Type (LCT) → Lower Cavity + Fracture Type (LCFT) → Higher Cavity Type (HCT)→ Higher Fracture Type (HFT)→ Lower Fracture Type (LFT).