In order to effectively prevent and control spontaneous combustion of residual coal in the goaf and reduce the waste of nitrogen caused by setting the position of nitrogen injection, 1303 fully mechanized coal caving faces of the Jinniu Mine are studied. By deploying a bundle tube monitoring system in the inlet air side and return air side of the goaf, changes in gas concentration in the goaf are continuously monitored. In addition, the distribution area for spontaneous combustion three-zone in the goaf is divided into heat dissipation zone, oxidized spontaneous combustion zone, and suffocation zone. Simulations from the COMSOL Multiphysics 5.3 software provide insight based on the three zones division standard of spontaneous combustion in the goaf. The gradual deepening of the nitrogen injection position into the goaf affects the lower limit of the oxidized spontaneous combustion zone significantly, but the impact on the upper limit of the oxidized spontaneous combustion zone is not obvious and is negligible. With regard to the width of the oxidized spontaneous combustion zone, it initially decreases followed by a gradual increase. Numerical calculations suggest the optimal nitrogen injection position is 40 m from the roof cutting line, with an oxidized spontaneous combustion zone width of 28 m. Based on the simulation analysis results, nitrogen injection controlling measures have been adopted for spontaneous combustion of residual coal in the goaf of the 1303 fully mechanized coal caving faces, and coal self-ignition in the goaf has been successfully extinguished.

The feasibility and accuracy of the risk prediction of gas extraction borehole spontaneous combustion is improved to avoid the occurrence of spontaneous combustion in the gas extraction borehole. A gas extraction borehole spontaneous combustion risk prediction model (PSO-BPNN model) coupling the PSO algorithm with BP neural network is established through improving the connection weight and threshold values of BP neural network by the particle swarm optimization (PSO) algorithm. The prediction results of the PSO-BPNN model are compared and analyzed with that of the BP neural network model (BPNN model), GA-BPNN model, SSA-BPNN model and MPA-BPNN model. The results showed as follows: the average relative error of the PSO-BPNN model was 4.38%; the average absolute error was 0.0678; the root mean square error was 0.0934; and the determination coefficient was 0.9874. Compared with the BPNN model, the average relative error, average absolute error and root mean square error decreased by 9.35%, 0.1707 and 0.2056 respectively; and the determination coefficient increased by 0.1169. Compared with the GA-BPNN model, the average relative error, average absolute error and root mean square error decreased by 3.19%, 0.0602 and 0.0821 respectively; and the determination coefficient increased by 0.0320. Compared with the SSA-BPNN model, the average relative error, average absolute error and root mean square error decreased by 5.70%, 0.0820 and 0.1100 respectively; and the determination coefficient increased by 0.0474. Compared with the MPA-BPNN model, the average relative error, average absolute error and root mean square error decreased by 3.50%, 0.0861 and 0.1125 respectively; and the determination coefficient increased by 0.0488, proving that the PSO-BPNN model is more accurate than the BPNN model, GA-BPNN model, SSA-BPNN model and MPA-BPNN model as for prediction. When the PSO-BPNN model was applied to three extraction boreholes A, B, and C in a coal mine of Shanxi, the prediction results were better than the BPNN model, GA-BPNN model, SSA-BPNN model and MPA-BPNN model, proving the accuracy and stability of the PSO-BPNN model in predicting risk of borehole spontaneous combustion in other mine.

In order to effectively prevent the spontaneous combustion of residual coal in goaf, taking the 10,101 fully mechanized top coal caving face of Baozigou coal mine as research object, the multi-field coupling numerical model of nitrogen injection in goaf is established. The FLUENT software is used to study the variation law of spontaneous combustion zone in goaf under dynamic mining of working face with different nitrogen injection parameters, determining the range of spontaneous combustion zone in stable stage. The fitting curve between nitrogen injection parameters and width of spontaneous combustion zone in goaf is obtained. Results show that with the increase of nitrogen injection depth from 10 to 60 m, the width of spontaneous combustion zone in goaf begins to decrease gradually, yet the width of spontaneous combustion zone tends to expand after more than 40 m. When the nitrogen injection location is 40 m, the spontaneous combustion zone width decreases from 49 to 22 m as the nitrogen injection volume increases from 500 to 1000 m³/h. Nitrogen injection continuously reduces the area of high temperature zone and temperature extreme value. When the nitrogen injection parameter is set to (40 m–1000 m³/h), temperature extreme value decreases by 308.85 K compared with that without nitrogen injection. When the nitrogen injection parameter is (40 m–690 m³/h), it can meet the inert cooling requirements of goaf. The width of spontaneous combustion zone is 31 m and the temperature extreme value is 309.95 K at the moment. Finally, engineering application of the fire prevention technology combining shot-off loss wind and nitrogen injection is used to test effect of spontaneous combustion prevention and verify accuracy of nitrogen injection simulation. CO concentration at the measuring point 1, 3 and 5 are reduced to 0 × 10⁻³‰, 2 × 10⁻³‰ and 1.2 × 10⁻³‰, and temperature are reduced to 295.15 K, 296.15 K and 295.65 K respectively. It shows that the spontaneous combustion of residual coal in goaf has been successfully controlled.

Due to the problems related to the numerous factors affecting the spontaneous combustion of goaf coal, such as sudden, uncertain, and dynamic changes, and the fact that the weight of the indexes in the prediction model of the spontaneous combustion risk is difficult to determine, an improved Criteria Importance Through Inter-criteria Correlation (CRITIC) modified Technique for Order of Preference by Similarity to Ideal Solution G2-(TOPSIS) dynamic prediction model of goaf spontaneous combustion was developed. An optimal decision-making model was established by introducing the Euclidean distance function, and the function-driven type G2 weighting method was modified using the differential-driven type weighting method of the CRITIC. In addition, the comprehensive weights of each index were obtained. An update factor was introduced to obtain the dynamic weight, and the primary-secondary relationship of the risk factors affecting the spontaneous combustion of goaf was evaluated. Based on the G2 weighting method, which approximates the driving function principle of the ideal solution ranking method (TOPSIS), a G2-TOPSIS goaf spontaneous combustion risk assessment model was established. The degree of closeness was analyzed and the risk grade of the goaf spontaneous combustion was finally predicted. The sub-model was applied to the goaf of working face 1303 in the Jinniu Coal Mine. It was concluded that the air leakage duration was the dominant factor inducing the risk of the spontaneous combustion of the goaf. The risk grade of spontaneous combustion of the goaf is Class III, and the predicted results are consistent with the actual situation. The improved CRITIC-G2-TOPSIS dynamic model was demonstrated to be scientific in predicting the goaf spontaneous combustion risk, and these research results have important popularization and application value.

Accurate measurement of coal gas permeability helps prevent coal gas safety accidents effectively. To predict permeability more accurately, we propose the IDBO-BPNN coal body gas permeability prediction model. This model combines the Improved Dung Beetle algorithm (IDBO) with the BP neural network (BPNN). First, the Sine chaotic mapping, Osprey optimization algorithm, and adaptive T-distribution dynamic selection strategy are integrated to enhance the DBO algorithm and improve its global search capability. Then, IDBO is utilized to optimize the weights and thresholds in BPNN to enhance its prediction accuracy and mitigate the risk of overfitting to some extent. Secondly, based on the influencing factors of gas permeability, effective stress, gas pressure, temperature, and compressive strength, they are chosen as the coupling indicators. The SPSS 27 software is used to analyze the correlation among the indicators using the Pearson correlation coefficient matrix. Additionally, the Kernel Principal Component Analysis (KPCA) is employed to extract the original data. Then, the original data is divided into principal component data for the model input. The prediction results of the IDBO-BPNN model are compared with those of the PSO-BPNN, PSO-LSSVM, PSO-SVM, MPA-BPNN, WOA-SVM, BES-SVM, and DPO-BPNN models. This comparison assesses the capability of KPCA to enhance the accuracy of model predictions and the performance of the IDBO-BPNN model. Finally, the IDBO-BPNN model is tested using data from a coal mine in Shanxi. The results indicate that the predicted outcome closely aligns with the actual value, confirming the reliability and stability of the model. Therefore, the IDBO-BPNN model is better suited for predicting coal gas permeability in academic research writing.

In order to quickly and accurately predict borehole spontaneous combustion danger and avoid borehole spontaneous combustion fires, a borehole spontaneous combustion prediction model combining the Hunger Games search optimization algorithm (HGS) and Random Forest (RF) algorithm was introduced. The number of trees and the minimum number of leaf nodes in RF were optimized by HGS. Based on the data obtained from the temperature rise experiment of spontaneous combustion characteristics in a Shandong mine laboratory, O₂, CO, C₂H₄, CO/∆O₂ and C₂H₄/C₂H₆ were selected as the input indexes for the prediction of borehole spontaneous combustion, and the spontaneous combustion temperature was selected as the output indexes to train the built model. The prediction performance and accuracy of the model were evaluated using four indexes: the mean absolute error (MAE), mean absolute percentage error (MAPE), root mean square error (RMSE) and coefficient of determination (R2). At the same time, the prediction results of the HGS-RF model were compared with those of the RF model, Sparrow search algorithm (SSA) optimization RF model, particle swarm optimization RF model (PSO) optimization RF model and quantum particle swarm optimization RF model (QPSO) optimization. The results showed that the MAE of the RF, SSA-RF, PSO-RF, QPSO-RF and HGS-RF model samples were 17.541, 15.7752, 12.5903, 6.8594 and 6.6921, respectively. MAPE was 13.81%, 10.9766%, 9.6802%, 4.5731% and 5.1536%, respectively. RMSE values were 21.5646, 15.2017, 17.0091, 11.9879 and 12.1691, respectively. The R2 values were 0.9043, 0.9315, 0.9266, 0.9668, and 0.9717, respectively. At the same time, the reliability of the HGS-RF model was supplemented by taking the test data of the Zhengjia1204 coal mining face as an example. Finally, the model was applied to the prediction of borehole spontaneous combustion in the Jinniu Coal Mine, Shanxi Province. The prediction results show that the HGS-RF model can predict the spontaneous combustion temperature of different boreholes quickly and accurately. The results show that the HGS-RF model is more universal and stable than other models, indicating that the HGS-RF model is more suitable for the prediction of borehole spontaneous combustion.