Abstract: In order to compensate the limitation of traditional contact-type coal and gas outburst prediction method, gas emission dynamic characteristics were used to forecast the coal and gas outburst to determine coal and gas outburst early-warning index system based on gas emission dynamic features and early-warning model of Xinyuan Mine, and the coal and gas outburst early warning system based on gas emission dynamic characteristics for Xinyuan Mine was established. Field validation shows that the system is able to achieve the real time, dynamic early-warning of outburst risk of Xinyuan Mine working face, and the warning accuracy is up to 79%. This system achieves the real-time online monitor, analysis, intelligent early-warning of coal and gas outburst disasters at working face in Xinyuan Mine, and it can promote the production safety in Xinyuan Mine.