Floor grouting reinforcement and aquifer reform can effectively improve the water barrier performance of fractured rock mass, which is widely used to prevent water inrush from a confined aquifer in theClean Utilization and SDUST Research Fund floor. In order to reveal the mechanical and strain energy characteristics of fractured rock mass after grouting with different grouting parameters, the discrete element numerical simulation software PFC is used to study the mechanical and strain energy characteristics of limestone after filling the fractures with cement stones with different parameters. The numerical test results show that the displacement of the limestone grouting stone bodies with a longer prefabricated crack length decreases more obviously after grouting, and the strain energy, dissipation energy, and total input energy increase when the strengthened limestone sample is destroyed. The greater the stiffness of the cement stone, the easier the limestone grouting stone bodies will be destroyed from the position of the prefabricated crack. The internal friction angle of cement stones has little effect on the strength, deformation, and energy characteristics of limestone. Under the same cohesion, the number and the distribution range of secondary cracks of limestone grouting stone bodies with smaller prefabricated crack length are larger. However, with the increase of the tensile strength of the cement stones, the number, distribution range, and strength of the secondary fractures of the limestone grouting stone bodies are increasing. The longer the prefabricated crack is, the greater the influence of grouting parameters on the rock. The study provides a reference for the selection of reinforcement material parameters during grouting reinforcement.

Based on the basic idea of Bayes discriminant analysis method, the Bayes discriminant analysis model for the difficulty of coal seam water injection was established. This model selects seven indicators, namely burial depth, crack development degree, porosity, wetting edge angle, solidity coefficient, saturated water increment, and gas pressure, as discriminant factors. The difficulty of coal seam water injection is divided into three levels as three normal populations for Bayes discriminant analysis. Taking 23 groups of actual data of coal seam water injection project as training samples, Bayes discriminative model is established. Perform cross validation on 23 sets of measured data to obtain the accuracy of the model. Finally, Bayes discriminative model is applied to the actual coal seam water injection project. The research results show that the Bayes discriminant analysis model has a lower misjudgment rate and can be better applied in practical engineering.