摘要:In recent years, with the increase in mining depth and strength, coal‐rock gas dynamic disasters, such as coal and gas outburst, have shown an increasing trend. Acoustic emission (AE) technology has been viewed as a promising method that can effectively forecast coal and gas dynamic disasters. This paper first tests the AE characteristics of coal and rock samples during loading. Then, self‐developed AE continuous monitoring and early warning equipment is used to monitor and predict the coal and gas outburst dynamic disasters on the working face. And it is found that the coal samples primarily show ductile failure, and the AE exhibits the evolutionary characteristics of “rise‐peak‐fall”. The rock samples primarily exhibit brittle failure, and the AE evolution mode is almost no falling stage. Coal and gas outbursts occur after the stress peak. Before coal and gas outbursts occur, there is a clear increasing trend in the AE ahead of the gas concentration variation. When the gas‐bearing coal is damaged by the load, the coal body first breaks due to the stress, and the AE value increases. Then, due to the fracture of the coal body, the crack penetrates, gas rushes out, and the gas concentration increases. The research results can provide an advanced technical method for the monitoring and early warning of coal–rock gas dynamic disasters, and improve the prediction accuracy for dynamic disasters.