Deep Neural Network for Distinguishing Microseismic Signals and Blasting Vibration Signals Based on Deep Learning of Spectrum Features

• Published in: Journal of earthquake engineering : JEE Vol. 28; no. 14; pp. 3905 - 3924
• Main Authors: Liu, Shuai, Jia, Rui-Sheng, Hao, Xiao-Bo, Liu, Peng-Cheng, Deng, Yan-Hui, Sun, Hong-Mei
• Format: Journal Article
• Language: English
• Published: Abingdon Taylor & Francis 25.10.2024; Taylor & Francis Ltd
• Subjects: Artificial neural networks; Blasting; blasting vibration signals; Classification; Coal mines; Coal mining; Deep learning; deep neural network; Frequency ranges; Machine learning; Microseismic signals; Microseisms; Neural networks; Signal classification; spectrum features; supervised learning; Vibration; Vibration monitoring; Vibrations; Waveforms
• ISSN: 1363-2469; 1559-808X
• DOI: 10.1080/13632469.2024.2364698

Similar waveforms and overlapping frequency ranges make distinguishing blasting vibrations and microseismic signals challenging, causing interference with coal mine microseismic monitoring systems. To address this problem, we propose a spectrum dataset (MSData) reflecting the spectrum features of both signal types and present a signal classification network (SCNet) combining CNNs and Transformers for signal classification. The network can learn multi-dimensional features of both signals from MSData and automatically and efficiently identify the two signal types. Experimental results yield F1-scores of 0.991 for microseismic signals and 0.993 for blasting vibration signals, meeting engineering application requirements.