A Classification Method for Microseisms and Blasts in Mine Based on Time and Frequency Domains Analysis

Microseismic monitoring is one of the important means for monitoring and early warning of mine ground pressure disasters. Due to the complex geological conditions of the mine and the numerous goaf areas, rock fracture signals undergo deformation, making it difficult to distinguish them from signals generated by artificial explosions. In this case, we conducted time-domain and frequency-domain analysis of the microseismic signals and artificial blasting signals collected by the BSN microseismic monitoring system, and obtain signal informations, including P-wave arrival, first peak, maximum peak, frequency spectrum of signal and P-wave. 8 typical features are extracted from the informations to build a classification model of microseismic and blast signals based on SVM with Gaussian function as the kernel function. The field data are collected by BSN microseism monitoring system of a metal mine in Guangxi, which are used to train and test the classification model. The results show that the accuracy rate of microseismic signals is larger than 80
^%
, which can help signals classification automatically in a certain extent.