dentification of blasting vibration and coal-roc fracturing microseismic signals

针对微震监测系统中煤岩破裂微震信号与爆破震动信号难以辨识的问题,提出了基于变分模态分解的微震信号特征提取及分类辨识方法。首先,采用VMD将原始信号分解为一系列按频率从高到低的变分模态分量,其次,提取各模态分量占原信号的能量百分比值构成特征向量,计算能量分布重心系数;最后,利用决策树桩法实现对煤岩破裂微震信号与爆破震动信号的分类辨识。实验结果表明:VMD可实现信号各分量的有效分离,其中,煤岩破裂微震信号的能量主要集中于u_4～u_6分量中,爆破震动信号的能量主要集中于u_1～u_3分量中,对比由能量分布特征向量降维后的能量分布重心系数,可实现对两类微震波形的分类辨识。通过与EMD、小波包分解方法的对比分析,验证了该方法的优越性。

A new method based on variational mode decomposition （VMD） is proposed to distinguish between coal-rock fracturing and blasting vibration microseismic signals. First, the signals are decomposed to obtain the variational mode components, which are ranked by frequency in descending order. Second, each mode component is extracted to form the eigenvector of the energy of the original signal and calculate the center of gravity coefficient of the energy distribution plane. Finally, the coal-rock fracturing and blasting vibration signals are classified using a decision tree stump. Experimental results suggest that VMD can effectively separate the signal components into coal-rock fracturing and blasting vibration signals based on frequency. The contrast in the energy distribution center coefficient after the dimension reduction of the energy distribution eigenvector accurately identifies the two types of microseismic signals. The method is verified by comparing it to EMD and wavelet packet decomposition.