Microseismic event waveform classification using CNN-based transfer learning models

• Published in: International journal of mining science and technology Vol. 33; no. 10; pp. 1203 - 1216
• Main Authors: Dong, Longjun, Shu, Hongmei, Tang, Zheng, Yan, Xianhang
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 01.10.2023; School of Resources and Safety Engineering,Central South University,Changsha 410083,China%School of Resources and Safety Engineering,Central South University,Changsha 410083,China; International College of Digital Innovation,Chiang Mai University,Chiang Mai 50200,Thailand; Elsevier
• Subjects: Image identification and classification; Machine learning; Microseismic events; Mine safety; Transfer learning; Waveform classification; Waveform classification; Mine safety; Transfer learning; Microseismic events; Image identification and classification; Machine learning
• ISSN: 2095-2686
• DOI: 10.1016/j.ijmst.2023.09.003

The efficient processing of large amounts of data collected by the microseismic monitoring system (MMS), especially the rapid identification of microseismic events in explosions and noise, is essential for mine disaster prevention. Currently, this work is primarily performed by skilled technicians, which results in severe workloads and inefficiency. In this paper, CNN-based transfer learning combined with computer vision technology was used to achieve automatic recognition and classification of multi-channel microseismic signal waveforms. First, data collected by MMS was generated into 6-channel original waveforms based on events. After that, sample data sets of microseismic events, blasts, drillings, and noises were established through manual identification. These datasets were split into training sets and test sets according to a certain proportion, and transfer learning was performed on AlexNet, GoogLeNet, and ResNet50 pre-training network models, respectively. After training and tuning, optimal models were retained and compared with support vector machine classification. Results show that transfer learning models perform well on different test sets. Overall, GoogLeNet performed best, with a recognition accuracy of 99.8%. Finally, the possible effects of the number of training sets and the imbalance of different types of sample data on the accuracy and effectiveness of classification models were discussed.