The purpose of the study was to explore the microscopic and mesoscopic damage mechanisms of water‐bearing coal mass in the freeze‐thaw process with liquid nitrogen. For this purpose, by using a Zeiss microscope, a nonmetal ultrasonic velocity detector and a nuclear magnetic resonance (NMR) spectrometer, the changes in the structures of surface fractures and pores before and after coal masses with different moisture contents when subjected to freeze‐thaw treatment with liquid nitrogen (FTTLN) were tested. The result showed that under the freeze‐thaw effect of liquid nitrogen, the structures of surface fractures and internal pores of coal mass were both changed. Upon increasing the moisture content of the coal, the width of surface fractures increased; the surface fractures showed significant fractal characteristics: The higher the moisture content of the coal, the greater the rate of change of fractal dimension after FTTLN; the ultrasonic wave velocity in the coal mass gradually decreased after FTTLN, and the greater the moisture content, the more significant the decrease in ultrasonic wave velocity; under the freeze‐thaw effect of liquid nitrogen, the pore structure in the coal mass was transformed from micropores and small pores to mesopores and macropores and certain new micropores and small pores were generated. Upon increasing the moisture content of the coal mass, the peak area of micropores and small pores and their proportion decreased at first and then increased (reaching the minimum at 9.12% of moisture content); the peak area, peak area proportion, and porosity of mesopores and macropores always increased. The damage factor attained based on the width of fractures, longitudinal wave velocity, fractal dimension of surface fractures, and porosity was favorably correlated with the moisture content: With increasing moisture content, the coal mass became more severely damaged.

Collaborative prediction model of gas emission quantity was built by feature selection and supervised machine learning algorithm to improve the scientific and accurate prediction of gas emission quantity in the mining face. The collaborative prediction model was screened by precision evaluation index. Samples were pretreated by data standardization, and 20 characteristic parameter combinations for gas emission quantity prediction were determined through 4 kinds of feature selection methods. A total of 160 collaborative prediction models of gas emission quantity were constructed by using 8 kinds of classical supervised machine learning algorithm and 20 characteristic parameter combinations. Determination coefficient, normalized mean square error, mean absolute percentage error range, Hill coefficient, mean absolute error, and the mean relative error indicators were used to verify and evaluate the performance of the collaborative forecasting model. As such, the high prediction accuracy of three kinds of machine learning algorithms and seven kinds of characteristic parameter combinations were screened out, and seven optimized collaborative forecasting models were finally determined. Results show that the judgement coefficients, normalized mean square error, mean absolute percentage error, and Hill inequality coefficient of the 7 optimized collaborative prediction models are 0.969–0.999, 0.001–0.050, 0.004–0.057, and 0.002–0.037, respectively. The determination coefficient of the final prediction sequence, the normalized mean square error, the mean absolute percentage error, the Hill inequality coefficient, the absolute error, and the mean relative error are 0.998%, 0.003%, 0.022%, 0.010%, 0.080%, and 2.200%, respectively. The multi-parameter, multi-algorithm, multi-combination, and multi-judgement index prediction model has high accuracy and certain universality that can provide a new idea for the accurate prediction of gas emission quantity.

Tectonic coal is a kind of soft coal that is generated during tectonic movement. Gas outbursts usually occur in seams containing both virgin coal and tectonic coal. To reveal the adsorption characteristics of this type of coal seam (containing both virgin coal and tectonic coal), both tectonic coal and virgin coal were collected from the same longwall face and a series of laboratory tests were conducted, including coal sorption tests and pore specific surface measurements. Both the tectonic coal and virgin coal were crushed into coal powder (0.18–0.25 mm) for the coal sorption tests. In these laboratory tests, different mass ratios between tectonic coal and virgin coal were tested. We found that with the increase of the percentage of tectonic coal, the adsorption volume showed a rising trend, reached its maximum value, and then decreased. The specific surface areas of the mixed coal samples had the same evolution trends as those of the adsorption volume. From the laboratory tests, we found that when the mass ratio of virgin coal to tectonic coal was 1:1, both the adsorption volume and the specific surface areas reached their maximum values. Due to the percentage variation of the tectonic coal in the panel with the advancement of the longwall face, when the tectonic coal accounted for 50% of the total coal, the gas content would rise. Thus, proper measures should be adopted for outburst hazards control. The mathematical model between the change of specific surface area and the stress and strain of pore expansion before and after gas adsorption was established, and the relationship between the change of pore structure and gas emission before and after gas adsorption was obtained. It provides a theoretical basis for further research on coal and gas outburst mechanisms.