Rock bursts pose a significant risk to coal mine operation safety. Thus, accurately discriminating coal bursting liabilities is crucial for predicting and preventing rock burst events. To better understand the effects of a varying bedding angle on the crack propagation rule, failure mode and bursting liability level of coal and coal-rock combinations, we propose an optimized machine learning-based model. Additionally, uniaxial compressive tests are conducted using PFC3D software on samples with different bedding angles. The results indicate that, among the nine light gradient boosting machine discriminant models constructed using three data preprocessing methods and three parameter optimization algorithms, the optimal model is identified as the particle swarm optimization-light gradient boosting machine discriminant model based on Z-score standardization method, which exhibits the best stability and has a F1-score of 93.6%. Bedding has a significant impact on the failure modes of two kinds of samples, resulting in an evident bedding effect on their bursting liability. The uniaxial compression strength and bursting energy index of both samples show a reduction-rising trend with an increasing bedding dip angle. However, the bursting liability level of these samples is not affected by 0° or 90° bedding dip angle. Therefore, when assessing the bursting liability of samples, the influence of coal seam bedding and its dip angles should be thoroughly considered.

The magnitude and frequency of induced seismicity increase as mining excavation reaches greater depth, leading to the increasingly severe damage to roadways caused by high-energy seismic waves. To comprehensively simulate the damage caused by dynamic loads, a synchrosqueezing transform and empirical mode decomposition method was developed, which effectively decomposed raw seismic wave signals into transverse and longitudinal components. This novel method produced more accurate results in terms of velocity, displacement, rock yielding patterns, and reflecting theoretically orthogonal oscillating directions of transverse and longitudinal waves compared to using raw mixed waves at the seismic source. Under the disturbance of transverse and longitudinal waves, the vertical displacement was much higher than horizontal displacement at the top position of the roadway, while the horizontal displacement was greater at the sidewalls. The particle vibration velocity, displacement and yielding zone of the surrounding rock of roadway were proportional to the energy level of seismic, while inversely proportional to the source-roadway distance. The proportion of damage attributed to transverse waves increased with the energy level, ranging from 75.8% to 85.8%. Eventually, a roadway dynamic support design was optimized based on the proposed seismic wave processing and modeling methodology. The methodology offers guidance for roadway dynamic support design, with the goal of averting excessive or insufficient support strength.

The accurate detection of coal seam stress field effectively prevents coal and gas outbursts. This study uses wave velocity, wave velocity anomaly coefficient, and wave velocity gradient as indicators to identify stress anomalies in coal seam. The results show that these three indicators of wave velocity are all positively correlated with load, while changes in the wave velocity anomaly coefficient and wave velocity gradient are more gentle than those of wave velocity. The degree of damage of coal can be judged by the wave velocity anomaly coefficient, while the transition between high and low stress zones can be identified by the wave velocity gradient. In areas affected by geological structures such as valleys and mountain tops, the coal seam wave velocity and wave velocity anomaly coefficient may exhibit anomalies. The comparative analysis of wave velocity and its derived indicators can reveal the stress state and coal structure of coal seamwith higher accuracy, identify the areas affected by geological structures such as valleys and mountain tops, and determine the boundary of the stress relief zone after hydraulic fracturing. Combined with the actual geological structure characteristics of coal seam, it can accurately identify the stress disturbance region of coal seam and achieve the purpose of predicting coal and gas outbursts.