Multi-Classification of Complex Microseismic Waveforms Using Convolutional Neural Network: A Case Study in Tunnel Engineering
Due to the complexity of the various waveforms of microseismic data, there are high requirements on the automatic multi-classification of such data; an accurate classification is conducive for further signal processing and stability analysis of surrounding rock masses. In this study, a microseismic...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-10-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/21/20/6762 |
_version_ | 1797513211994439680 |
---|---|
author | Hang Zhang Jun Zeng Chunchi Ma Tianbin Li Yelin Deng Tao Song |
author_facet | Hang Zhang Jun Zeng Chunchi Ma Tianbin Li Yelin Deng Tao Song |
author_sort | Hang Zhang |
collection | DOAJ |
description | Due to the complexity of the various waveforms of microseismic data, there are high requirements on the automatic multi-classification of such data; an accurate classification is conducive for further signal processing and stability analysis of surrounding rock masses. In this study, a microseismic multi-classification (MMC) model is proposed based on the short time Fourier transform (STFT) technology and convolutional neural network (CNN). The real and imaginary parts of the coefficients of microseismic data are inputted to the proposed model to generate three classes of targets. Compared with existing methods, the MMC has an optimal performance in multi-classification of microseismic data in terms of <i>Precision</i>, <i>Recall</i>, and <i>F1-score</i>, even when the waveform of a microseismic signal is similar to that of some special noise. Moreover, semisynthetic data constructed by clean microseismic data and noise are used to prove the low sensitivity of the MMC to noise. Microseismic data recorded under different geological conditions are also tested to prove the generality of the model, and a microseismic signal with <i>M<sub>w</sub></i> ≥ 0.2 can be detected with a high accuracy. The proposed method has great potential to be extended to the study of exploration seismology and earthquakes. |
first_indexed | 2024-03-10T06:13:30Z |
format | Article |
id | doaj.art-8c81f64999f44af4a8adae14b254749c |
institution | Directory Open Access Journal |
issn | 1424-8220 |
language | English |
last_indexed | 2024-03-10T06:13:30Z |
publishDate | 2021-10-01 |
publisher | MDPI AG |
record_format | Article |
series | Sensors |
spelling | doaj.art-8c81f64999f44af4a8adae14b254749c2023-11-22T19:57:04ZengMDPI AGSensors1424-82202021-10-012120676210.3390/s21206762Multi-Classification of Complex Microseismic Waveforms Using Convolutional Neural Network: A Case Study in Tunnel EngineeringHang Zhang0Jun Zeng1Chunchi Ma2Tianbin Li3Yelin Deng4Tao Song5State Key Laboratory of Geohazard Prevention and Geoenvironment Protection, Chengdu University of Technology, Chengdu 610059, ChinaState Key Laboratory of Geohazard Prevention and Geoenvironment Protection, Chengdu University of Technology, Chengdu 610059, ChinaState Key Laboratory of Geohazard Prevention and Geoenvironment Protection, Chengdu University of Technology, Chengdu 610059, ChinaState Key Laboratory of Geohazard Prevention and Geoenvironment Protection, Chengdu University of Technology, Chengdu 610059, ChinaState Key Laboratory of Geohazard Prevention and Geoenvironment Protection, Chengdu University of Technology, Chengdu 610059, ChinaState Key Laboratory of Geohazard Prevention and Geoenvironment Protection, Chengdu University of Technology, Chengdu 610059, ChinaDue to the complexity of the various waveforms of microseismic data, there are high requirements on the automatic multi-classification of such data; an accurate classification is conducive for further signal processing and stability analysis of surrounding rock masses. In this study, a microseismic multi-classification (MMC) model is proposed based on the short time Fourier transform (STFT) technology and convolutional neural network (CNN). The real and imaginary parts of the coefficients of microseismic data are inputted to the proposed model to generate three classes of targets. Compared with existing methods, the MMC has an optimal performance in multi-classification of microseismic data in terms of <i>Precision</i>, <i>Recall</i>, and <i>F1-score</i>, even when the waveform of a microseismic signal is similar to that of some special noise. Moreover, semisynthetic data constructed by clean microseismic data and noise are used to prove the low sensitivity of the MMC to noise. Microseismic data recorded under different geological conditions are also tested to prove the generality of the model, and a microseismic signal with <i>M<sub>w</sub></i> ≥ 0.2 can be detected with a high accuracy. The proposed method has great potential to be extended to the study of exploration seismology and earthquakes.https://www.mdpi.com/1424-8220/21/20/6762microseismic waveformsmulti-classificationconvolutional neural networksimilarity |
spellingShingle | Hang Zhang Jun Zeng Chunchi Ma Tianbin Li Yelin Deng Tao Song Multi-Classification of Complex Microseismic Waveforms Using Convolutional Neural Network: A Case Study in Tunnel Engineering Sensors microseismic waveforms multi-classification convolutional neural network similarity |
title | Multi-Classification of Complex Microseismic Waveforms Using Convolutional Neural Network: A Case Study in Tunnel Engineering |
title_full | Multi-Classification of Complex Microseismic Waveforms Using Convolutional Neural Network: A Case Study in Tunnel Engineering |
title_fullStr | Multi-Classification of Complex Microseismic Waveforms Using Convolutional Neural Network: A Case Study in Tunnel Engineering |
title_full_unstemmed | Multi-Classification of Complex Microseismic Waveforms Using Convolutional Neural Network: A Case Study in Tunnel Engineering |
title_short | Multi-Classification of Complex Microseismic Waveforms Using Convolutional Neural Network: A Case Study in Tunnel Engineering |
title_sort | multi classification of complex microseismic waveforms using convolutional neural network a case study in tunnel engineering |
topic | microseismic waveforms multi-classification convolutional neural network similarity |
url | https://www.mdpi.com/1424-8220/21/20/6762 |
work_keys_str_mv | AT hangzhang multiclassificationofcomplexmicroseismicwaveformsusingconvolutionalneuralnetworkacasestudyintunnelengineering AT junzeng multiclassificationofcomplexmicroseismicwaveformsusingconvolutionalneuralnetworkacasestudyintunnelengineering AT chunchima multiclassificationofcomplexmicroseismicwaveformsusingconvolutionalneuralnetworkacasestudyintunnelengineering AT tianbinli multiclassificationofcomplexmicroseismicwaveformsusingconvolutionalneuralnetworkacasestudyintunnelengineering AT yelindeng multiclassificationofcomplexmicroseismicwaveformsusingconvolutionalneuralnetworkacasestudyintunnelengineering AT taosong multiclassificationofcomplexmicroseismicwaveformsusingconvolutionalneuralnetworkacasestudyintunnelengineering |