During the process of coal sampling through drilling and determining the gas content, the movement characteristics of coal particles within the borehole will affect the exposure time of the collected coal samples. Therefore, studying the movement characteristics of coal particles within the borehole is of great significance. This study employs CFD-DEM to simulate the transport dynamics of Rosin-Rammler distributed coal cuttings during pneumatic sampling, quantifying the effects of drill rod rotation (0–200 rpm) and particle size. Key findings reveal: (1) Axial migration velocity increases significantly with rotational speed, with 0.5–1 mm fine particles accelerating by 39% to 3.9 m s ^-1 at 100 rpm compared to static condition, though an optimal threshold exists at 150 rpm; (2) Rod rotation induces vortical flow fields, where bit geometry impedes coarse particles (>1 mm) in blade zones, while 0.5–1 mm particles migrate at velocities higher than 2–3 mm fractions under different rotational speeds; (3) Mass flow rate at the orifice doubles with speed (reaching 0.06 kg s ^-1 at 200 rpm), while static condition reduces efficiency by 50%. The observed significant velocity differentiation depending on particle size implies that using narrowly graded samples (e.g., obtained with adjacent sieve sizes such as 3–4 mm) could potentially improve the accuracy of lost gas content estimation by minimizing variations in particle transport history.

An HPO (Hunter–Prey Optimizer)-optimized Bidirectional LSTM (HPO-BiLSTM) model is introduced to address the challenges in predicting gas concentration within coal mining working faces. This study aims to adaptively adjust the key hyperparameters (such as learning rate and number of hidden layer units) of the BiLSTM network through intelligent optimization algorithms. While the BiLSTM architecture inherently mitigates gradient vanishing and exploding problems through its gating mechanisms, the proposed HPO method focuses on addressing the inefficiency of manual parameter tuning and the risk of trapping in local optima that traditional methods encounter when dealing with nonlinear and non-stationary gas concentration time series. The experiment utilized the actual methane monitoring data from the 15117 working face of Jishazhuang Coal Mine in Jinzhong City, Shanxi Province (with a sampling interval of 2 min). The proposed HPO-BiLSTM model was compared with baseline models such as LSTM, BiLSTM, GA-BiLSTM, and PSO-BiLSTM in terms of performance. This study systematically compares the performance of LSTM, BiLSTM, and BiLSTM models optimized with GA, PSO, and HPO. Results demonstrate that all optimized models outperform the baselines, with HPO-BiLSTM achieving the best overall performance. It attained the lowest RMSE and highest R² across the training, validation, and test sets, showcasing superior fitting and generalization capabilities. Furthermore, HPO-BiLSTM converged to the lowest loss value (0.00062) in only 15 iterations, demonstrating significantly greater efficiency and stability than both GA-BiLSTM (loss 0.00072, 25 iterations) and PSO-BiLSTM (loss 0.00071, 30 iterations). The experiments confirm that the HPO algorithm effectively configures BiLSTM hyperparameters, mitigates overfitting, and provides a more accurate and robust solution for gas concentration prediction in coal mines.

There are numerous constraints in conducting on-site experiments on the characteristics of gas emissions from boreholes in underground coal mines. Hence, it holds great significance to carry out experimental studies on gas emissions from boreholes in the laboratory. However, some of the conditions of the previous experimental systems employed differ from those in the field; especially, the drill bit used in actual coal mining borehole drilling and the diameter of the drilled hole are not unified, and the size of the borehole and drill bit affect the gas emission characteristics. In response to the above circumstances, this paper proposed and developed a physical simulation experimental system for a coal borehole drilling experimental system; the borehole and drill bit size were close to the actual engineering situation. The coal seam gas pressure was chosen, which directly influences the risk index of coal and gas outburst; experiments on the characteristics of gas emission from boreholes under different adsorption pressure conditions were conducted. The results indicated that the gas emission volume from the borehole increased with the increase of adsorption equilibrium pressure. The initial gas emission model conformed to the exponential decay model. The gas emission velocity initially rose and then remained stable. Under conditions of higher adsorption pressure, it took longer for the borehole gas emission velocity to reach stability. The developed experimental system provides technical conditions for the follow-up laboratory study of gas emission in coal cutting borehole drilling. The research results provide technical conditions for follow-up studies on gas emission in coal cutting boreholes and a basis for further development of the characteristics of gas emission in briquette boreholes.