Abstract: For problem of inaccurate detection of characteristic signal in coal mining operation because it is difficult to capture nonlinear stochastic variation of abnormal signal with traditional associated clustering algorithm, a mining method of signal of coal and gas outburst based on feature-based association mining algorithm was proposed. The method uses wavelet transform to extract status signal characteristics of coal mine work area to provide a basis for signal mining of coal and gas outburst, and calculates degree of association between the status signal characteristics of coal mine work area to achieve mining of signal of coal and gas outburst. The experimental results show that the method can improve accuracy of mining of signal of coal and gas outburst.