|
|
|
| Research on automatic pattern recognition algorithm of micro-seismic waveform characteristics in mines |
| HU Jingyun1，ZHANG Ru2，REN Li2，PENG Fuhua1，WU Fei3，CAO Weiliang4 |
(1. State Key Laboratory of Safety Technology for Metal Mines，Changsha Institute of Mining Research Co.，Ltd，Changsha，Hunan 410012，China；2. Key Laboratory of Deep Earth Science and Engineering，Ministry of Education，Sichuan University，Chengdu，
Sichuan 610065，China；3. Jiangxi Xiushui Xianglushan Tungsten Industry Co.，Ltd.，Jiujiang，Jiangxi 423000，
China；4. Hunan Aocheng Technology Co.，Ltd.，Changsha，Hunan 410012，China) |
|
|
|
|
Abstract The application of the micro-seismic monitoring technology in mines is increasing，but the automatic identification of effective signals and noise signals has not been realized，which seriously restricts its application and popularization. Six main pattern categories in the mine strong noise environment，including drilling，trackless equipment running，mine shaft dumping，electromagnetic interference，blasting and effective signal，are investigated，and the effective signal patterns are divided into two subsets of small-energy events and large-energy events. The generation mechanism of each pattern class is studied in detail. By collecting a large number of samples of each pattern class，the identifying characteristics extracted for the above six pattern classes are respectively the waveform interval time，the waveform duration，the combination of the total duration with the number of individual events，the waveform duration or the main frequency，the combination of the waveform duration and the main frequency，and the waveform duration and the exclusion method. The distribution probabilities of the recognition characteristic values are calculated and counted by using the pre-processing method. A decision function with excellent recognition performance is constructed，and an automatic pattern recognition algorithm of mine micro-seismic waveform characteristic is established. Based on the above algorithms，a software of automatic pattern recognition is developed. Through the field test in a typical mine，the recognition accuracy of the effective signal of the developed algorithm is 90.8%，showing a good field application.
|
|
|
|
|
|
[1] MU D W，LEE E，CICOTTI P，et al. Deep learning for seismic template recognition[J]. ACM International Conference Proceeding Series，2018，7(22)：67–85.
[2] CLARA E Y，OSSIAN O R，KARIANNE J B，et al. Earthquake detection through computationally efficient similarity search[J]. Science Advances，2015，12(4)：1–13.
[3] KOHN D，DE N D，HAGREY S A，et al. A combination of waveform inversion and reverse-time modelling for microseismic event characterization in complex salt structures[J]. Environmental Earth Sciences，2016，9(1)：946–957.
[4] GRIGOLI F，CESCA S，AMOROSO O，et al. Automated seismic event location by waveform coherence analysis[J]. Geophysical Journal International，2014，(3)：1 742–1 753.
[5] 程玉胜，邱家兴，刘 振，等. 水声被动目标识别技术挑战与展望[J]. 应用声学，2019，38(4)：653–659.(CHENG Yusheng，QIU Jiaxing，LIU Zhen，et al. Challenges and prospects of underwater acoustic passive target recognition technology[J]. Journal of Applied Acoustics，2019，38(4)：653–659.(in Chinese))
[6] 张 扬，杨建华，侯 宏. 基于EK-NN的水声目标识别算法研究[J]. 声学技术，2016，35(1)：15–19.(ZHANG Yang，YANG Jianhua，HOU Hong. K-NN based underwater acoustic target recognition algorithm[J]. Technical Acoustics，2016，35(1)：15–19.(in Chinese))
[7] 胡 桥，郝保安，吕林夏，等. 基于组合支持向量机的水声目标智能识别研究[J]. 应用声学，2009，28(6)：421–430.(HU Qiao，HAO Baoan，LV Linxia，et al. Intelligent underwater-acoustic-target recognition based on combination support vector machine[J]. Applied Acoustics，2009，28(6)：421–430.(in Chinese))
[8] 张振华，吴 宁，俞 剑. 一种特征模板匹配的水声识别系统的设计与实现[J]. 计算机与数字工程，2018，46(11)：2 274–2 278. (ZHANG Zhenhua，WU Ning，LU Jian. Design and implementation of underwater acoustic identification system based on feature template matching[J]. Computer and Digital Engineering，2018，46(11)：2 274–2 278.(in Chinese))
[9] LAWRENCE R R，RONALD W S. 数字语音处理理论与应用[M]. 刘 加，张卫强，何 亮，等译. 北京：电子工业出版社，2016：345–353.(LAWRENCE R R，RONALD W S. Theory and applications of digital speech processing[M]. Translated by LIU Jia，ZHANG Weiqiang，HE Liang，et al. Beijing：Electronic Industry Press，2016：345–353.(in Chinese))
[10] 姜 鹏，戴 峰，徐奴文，等. 基于ST时频分析的地下厂房微震信号识别研究[J]. 岩石力学与工程学报，2015，34(2)：4 071–4 079. (JIANG Peng，DAI Feng，XU Nuwen，et al. Identification of microseismic signal in underground powerhouse based on ST time-frequency analysis[J]. Chinese Journal of Rock Mechanics and Engineering，2015，34(2)：4 071–4 079.(in Chinese))
[11] 伍梦蝶. 岩石破裂信号辨识及自动识别方法研究[硕士学位论文][D]. 武汉：湖北工业大学，2018.(WU Mengdie. Study on identification and automatic identification method of rock fracture signal[M. S. Thesis][D]. Wuhan：Hubei University of Technology，2018.(in Chinese))
[12] 赵国彦，邓青林，李夕兵，等. 基于EMD和形态分形维数的微震波形识别[J]. 中南大学学报：自然科学版，2017，48(1)：162–167. (ZHAO Guoyan，DENG Qinglin，LI Xibing，et al. Recognition of microseismic waveforms based on EMD and morphological fractal dimension[J]. Journal of Central South University：Science and Technology，2017，48(1)：162–167.(in Chinese))
[13] 马 举. 基于波形特征的矿山微震与爆破信号模式识别[硕士学位论文][D]. 长沙：中南大学，2014.(MA Ju. Pattern recognition of mine blasts and microseismic events based on waveform features[M. S. Thesis][D]. Changsha：Central South University，2014.(in Chinese))
[14] 李保林. 煤矿微震与爆破信号特征提取及识别研究[硕士学位论文][D]. 徐州：中国矿业大学，2016.(LI Baolin. Feature extraction and recognition of coal mine microseismic and blast signals[M. S. Thesis][D]. Xuzhou：China University of Mine Technology，2016.(in Chinese))
[15] 董陇军，孙道元，李夕兵，等. 微震与爆破事件统计识别方法及工程应用[J]. 岩石力学与工程学报，2016，35(7)：1 423–1 433. (DONG Longjun，SUN Daoyuan，LI Xibing，et al. A statistical method to identify blasts and microseismic events and its engineering application[J]. Chinese Journal of Rock Mechanics and Engineering，2016，35(7)：1 423–1 433.(in Chinese))
[16] 姜福兴，尹永明，朱权洁，等. 单事件多通道微震波形的特征提取与联合识别研究[J]. 煤炭学报，2014，39(2)：229–237.(JIANG Fuxing，YIN Yongming，ZHU Quanjie，et al. Feature extraction and classification of mining microseismic waveforms via multi-channels analysis[J]. Journal of China Coal Society，2014，39(2)：229–237.(in Chinese))
[17] 朱权洁，姜福兴，尹永明，等. 基于小波分形特征与模式识别的矿山微震波形识别研究[J]. 岩土工程学报，2012，34(11)：2 036–2 042. (ZHU Quanjie，JIANG Fuxing，YIN Yongming，et al. Classification of mine microseismic events based on wavelet-fractal method and pattern recognition[J]. Chinese Journal of Geotechnical Engineering，2012，34(11)：2 036–2 042.(in Chinese))
[18] 李庶林，尹贤刚. 矿山微震震源机制的初步研究[J]. 矿业研究与开发，2006，4(增1)：141–146.(LI Shulin，YIN Xiangang. Primary study on focal mechanism of micro-seismic in mine[J]. Mining Research and Development，2006，4(Supp.1)：141–146.(in Chinese))
[19] 王永庆. 人工智能原理与方法[M]. 西安：西安交通大学出版社，2001：244–268.(WANG Yongqin. Principles and methods of artificial intelligence[M]. Xian：Southwest Jiaotong University Press，2001：244–268.(in Chinese))
[20] BAILEY C D，PLESS W M. Acoustic Emission used to NDT determine crack location in aircraft structural fatigue specimen[C]// Proceeding of 9th Symposium on NDE. New York：Oxford University Press，1973：224.
[21] 胡静云，林 峰，彭府华，等．香炉山钨矿残采区地压灾害微震监测技术应用研究[J]. 中国地质灾害与防治学报，2010，21(4)：109–115.(HU Jingyun，LIN Feng，PENG Fuhua，et al. Research on application of Microseismic monitoring technology on ground pressure hazard of residual are in Xianglushan tungsten mine[J]. The Chinese Journal of Geological Hazard and Control，2010，21(4)：109–115.(in Chinese))
[22] DONG L J，TANG Z，LI X B，et al. Discrimination of mining microseismic events and blasts using convolutional neural networks and original waveform[J]. Journal of Central South University，2020，27(10)：3 078–3 089. |
| [1] |
LI Botao1, 2, 3, TAN Yuxuan1, LIN Haifei4, 5*, WEI Jianping1, 2, 3, ZHANG Hongtu1, 2, 3, LI Shugang4, 5, WEI Zongyong4, 5, WANG Pei4, LUO Rongwei4, LIU Yanwei1, 2, 3. Mechanical properties and mesoscopic damage evolution of coal under liquid-nitrogen freezing at different initial temperatures[J]. , 2026, 45(6): 1757-1772. |
|
|
|
|
2022, Vol. 41 
