The impact force and effective impact area of are water jet are two important indexes for evaluating jet performance, and the outlet shape of the nozzle has a great influence on jet performance. In this study, five nozzles with different outlet shapes were designed, and water jet test experiments were conducted at different inlet pressures using an independently built water jet impact test platform, and the influence law of nozzle shape on the center impact pressure and flow coefficient of the water jet was investigated. The influence of nozzle shape on the effective impact area and entrainment rate of water jet was further investigated by numerical simulation. The results showed that the center impact pressure of the circular nozzle was the greatest when the inlet pressure and the target distance were small. The center impact pressure, the flow coefficient, and the effective area of the triangular nozzle with sharp edges were better than the traditional circular nozzle when the inlet pressure and the target distance were increased. Although the center impact pressure of the square nozzle is lower than that of the circular nozzle, its flow coefficient and effective impact area are higher than those of the circular nozzle with increasing target distance. The water jets of the elliptical and cross nozzles were the most divergent, and the jet performance was poor.

The technology of increasing coal seam permeability by high-pressure water jet has significant advantages in preventing and controlling gas disasters in low-permeability coal seam. The structural parameters of a nozzle are the key to its jet performance. The majority of the current studies take strike velocity as the evaluation index, and the influence of the interaction between the nozzle’s structural parameters on its jet performance is not fully considered. In practice, strike velocity and strike area will affect gas release in the process of coal breaking and punching. To further optimize the structural parameters of coal breaking and punching nozzle, and improve water jet performance, some crucial parameters such as the contraction angle, outlet divergence angle, and length-to-diameter ratio are selected. Meanwhile, the maximum X-axis velocity and effective Y-axis extension distance are used as evaluation indexes. The effect of each key factor on the water jet performance is analyzed by numerical simulation using the single factor method. The significance and importance effect of each factor and their interaction on the water jet performance are quantitatively analyzed using the orthogonal experiment method. Moreover, three optimal combinations are selected for experimental verification. Results show that with an increase in contraction angle, outlet divergence angle, and length-to-diameter ratio, the maximum X-axis velocity increases initially and decreases thereafter. The Y-direction expansion distance of the jet will be improved significantly with an increase in the outlet divergence angle. Through field experiments, the jet performance of the improved nozzle 3 is the best. After optimization, the coal breaking and punching diameter of the nozzle is increased by 118%, and the punching depth is increased by 17.46%.

The technology of coal breaking and punching by a high-pressure water jet can increase the permeability of coal seam and prevent gas explosion accidents. As one of the key components of this technology, the structural parameters of the nozzle have an important effect on the performance of the water jet. At present, the relationship between multiple optimization indexes and structural parameters of the nozzle is mostly studied separately. In fact, the influence of the nozzle structural parameters on different optimization indexes is different. When there are multiple optimization indexes, they should be considered collaboratively to achieve the best water jet performance of the nozzle. Therefore, a multi−objective collaborative optimization method is proposed which takes the maximum velocity in X-axis and effective extension distance in Y-axis as the performance evaluation indexes of the water jet. The numerical simulation of the nozzle jet is carried out by computational fluid dynamics(CFD) method, and an orthogonal test database is established. The weight of multi-objective is analyzed, and the key structural parameters of the nozzle are optimized by the combination of BP (back propagation) neural network and genetic algorithms. The results show that the primary and secondary sequence of each structural parameter on is $\gamma >\theta >l∕d$, which could reflect the comprehensive influence on the maximum velocity in the X-axis and effective extension distance in the Y-axis. The optimal structural parameters of the nozzle are, θ = 42.512°, l/d = 2.5608, γ = 12.431°. The field erosion experiment shows that compared with the original nozzle, the water jet performance of the optimized nozzle has been improved, the punching depth has been increased by 72.71%, and the punching diameter has been increased by 106.72%. This study provides a certain reference for the design and optimization of coal breaking and punching nozzle.

In order to solve the defects of traditional coal spontaneous combustion prevention technology in a closed goaf, a strain of aerobic endogenous bacteria was isolated from coal and used as a blocking raw material. Based on the metabolic and reproductive characteristics of microorganisms, the experimental study on the inhibition of coal spontaneous combustion by microorganisms was carried out. The colonies were isolated and purified by the dilution concentration plate method and the scribing plate method. The growth morphology of microorganisms was analyzed, and the growth curve was determined. The strains were identified by seamless cloning technology for high-throughput sequencing. The surface morphology of coal was analyzed by SEM, the differences of oxidation characteristic temperature points were analyzed by TG–DTG–DSC images, a programmed heating experiment was used to analyze the concentration of the indicator gas CO, and the changes in microscopic groups before and after microbial action were analyzed by FTIR and XPS spectra. Therefore, the inhibition of coal oxidation by endogenous bacteria was verified from macroscopic and microscopic perspectives. The results show that the coal bacteria isolated from the coal is Lysinibacilus sp. After the culture of Lysinibacilus sp., the surface of the coal demonstrated less detritus, and was relatively smooth. In the early stage of low temperature oxidation of coal spontaneous combustion, the characteristic temperature point of coal oxidation and the reaction between coal and O₂ could be delayed by Lysinibacilus sp., and the total heat release was reduced in the combustion process. Not only that, Lysinibacilus sp. could also reduce the CO concentration during coal heating. After the coal was decomposed by Lysinibacilus sp., the C=C thick ring skeleton structure had little effect; however, the aromatic substitution pattern changed. This bacterium had an effect on the C-O bond, reducing the percentage of -CH₂- and increasing the percentage of -CH₃. It might also use the crystalline water in coal for life activities. The carboxyl carbon in coal changed the most, with a decrease of 12.03%, so it might become the carbon source required for microbial growth. The reproductive metabolism of microorganisms also affected the form of nitrogen, and the percentage of pyridine nitrogen in coal was reduced. The ratio of single-bond carbon to double-bond carbon in raw coal was about 3:2, but after this bacterial action, the ratio of the two was about 1:1. The analytical conclusions of XPS and FTIR spectra were consistent, and the results supported each other.

Accurate prediction of toxic gas concentrations during conveyor-belt fires is essential for ensuring mine safety, yet the nonlinear, time-varying, and turbulent characteristics of underground environments pose significant challenges for real-time forecasting. This study proposes a Physics-Informed Neural Network–Long Short-Term Memory (PINN-LSTM) hybrid model that integrates the one-dimensional convection–diffusion equation as a physical constraint with the sequential learning capability of an LSTM. Full-scale mine tunnel combustion experiments and Fire Dynamics Simulator (FDS) numerical simulations under multiple wind speeds and distances were conducted for model training and validation. The results indicate that the proposed PINN-LSTM achieves the lowest error metrics under all test conditions. The model reduced MSE and RMSE by 70–78% and 65–73%, respectively, compared with traditional LSTM models, and by 8–12% compared with the PINN-TCN variant. The proposed PINN-LSTM achieves the lowest error under all conditions. The PINN-LSTM model has strong prediction accuracy, physical interpretability, and real-time reasoning ability, providing a reliable and physically consistent solution for intelligent gas monitoring and early warning systems in underground fire scenarios.