A novel method for automatic identification of rock fracture signals in microseismic monitoring

Abstract

Microseismic (MS) monitoring technology is able to offer 3-dimensional and real-time rupture characteristics of rocks by capturing and analyzing detectable elastic waves released from rock fracture, which has been widely applied in rock/mining engineering. The prerequisite of MS analysis is to identify MS signals with high efficiency and accuracy. However, the identification work is inevitably disturbed by vibration signals from the blasting activities involved in rock/mining engineering. Currently, the classification work of MS and blasting signals is mainly carried out by the on-site operators based on their own experience, which is time-consuming and subjectively sensitive. In this work, a new discriminant method is developed to automatically recognize these signals based on their time-frequency spectrum characteristics to offer more reliable data for MS monitoring analysis. Singular value decomposition is adopted to reduce data volume and obtain unique features. Random Forest (RF) is applied to achieve automatic recognition and get the most important features based on the variation of ‘out-of-bag’ error and Gini Index. These most important features can be used to optimize the RF classifier. The numerical experiments are conducted to verify our new method. The results prove that the method reaches 95.99%±0.1% accuracy in 100 repetitions for events collected from the field, and the optimized RF produces a more accurate result (97%) using fewer characteristics, which is higher than the methods reported in the previous literature. The proposed method diminishes the sensitivity of operators in the classification and promotes the accuracy and efficiency of the identification of MS signals data in the application of MS monitoring technology. Moreover, this strategy also offers a new strategy to process the acquired monitoring signals in other monitoring techniques.