Abstract: Aiming at the problems of low real-time performance and lack of effective signal recognition function of existing mine microseismic monitoring system,this paper carried out the research on automatic identification method of mine microseismic and blasting signals based on energy distribution characteristics,in order to promote the development of fully automatic processing technology of mine microseismic monitoring.In this paper,the method of 8-layer wavelet decomposition and coefficient reconstruction is used to decompose the mine microseismic signal and blasting signal to understand the energy proportion characteristics of each layer wavelet coefficient reconstruction frequency domain.It is found that the blasting signal energy is mainly concentrated in the third layer and the fourth layer,and the microseismic signal energy is mainly concentrated in the fourth layer to the sixth layer.The energy proportion feature can be used to identify microseismic signals and blasting signals.This paper collects the production data of the mine for two weeks,selects 202 pieces of data,establishes the data sample set of energy proportion characteristics,adopts the principle of support vector machine,and uses radial basis function to learn and train the data sample set,and then obtains the signal recognition model.Finally,195 mine field data are collected for identification test,and the results show that the accuracy rate of identification is 86%,and the accuracy rate of microseismic identification is more than 90%,which indicates that the proposed signal identification method can effectively realize the identification of microseismic signal and blasting signal in mine field.