改进EWT_MPE模型在矿山微震信号特征提取中的应用

PDF(1734 KB)

振动与冲击 ›› 2021, Vol. 40 ›› Issue (9) : 92-101.

论文

程铁栋，易其文，吴义文，戴聪聪，蔡改贫，杨丽荣，尹宝勇

作者信息 +

Application of improved EWT_MPE model in feature extraction of mine micro-seismic signals

CHENG Tiedong, YI Qiwen, WU Yiwen, DAI Congcong, CAI Gaipin, YANG Lirong, YIN Baoyong

Author information +

文章历史 +

摘要

针对矿山微震与爆破振动信号难以自动辨识的问题，提出了一种基于改进EWT_MPE（经验小波变换_多尺度排列熵）的信号特征提取方法，并应用于矿山微震信号特征提取中。针对EWT在以往处理复杂信号频谱出现的过切分问题提出了新的改进方法，并采用仿真信号验证了改进算法的可行性和准确性。将实际采集到的微震与爆破信号进行改进EWT分解，借助相关性分析从分解得到的本征模态函数（intrinsic mode function, IMF）分量中筛选出最优分量IMF1~IMF5。进而将筛选到的IMF分量进行重构，并计算重构信号的MPE值。应用GK模糊聚类算法对岩体微震与爆破振动信号进行分类识别。结果表明，微震信号的MPE值要小于爆破信号的MPE值，且当嵌入维数m=5，尺度因子s=12，延迟时间τ=1时，两种信号的MPE值差异最大。基于改进EWT_MPE_GK模糊聚类算法的分类识别准确率达到93.5%，平均模糊熵（E）更接近0、分类系数（C）更接近1，与传统EWT_MPE_GK模糊聚类和EMD_MPE_GK模糊聚类相比，其聚类效果更优、识别准确率分别提高了3%和5.5%。

Abstract

Here, aiming at the problem of mine micro-seismic and blast vibration signals being difficult to automatically identify, a signal feature extraction method based on improved EWT_MPE (experience wavelet transform _multi-scale permutation entropy) was proposed, and applied in mine micro-seismic signal feature extraction.Firstly, a new improved method was proposed for the over-segmentation problem of EWT in previous processing complex signal spectra, and the feasibility and correctness of the improved algorithm were verified using simulated signals.Secondly, the actual collected micro-seismic and blast signals were decomposed using the improved EWT, and by means of correlation analysis, the optimal components IMF1-IMF5 were selected from the decomposed IMF (intrinsic mode function) components.The selected IMF components were used to reconstruct a signal, and calculate its MPE value.Finally, the GK fuzzy clustering algorithm was used to classify and identify micro-seismic and blast vibration signals of rock mass.The results showed that micro-seismic signal’s MPE value is smaller than blast signal’s; when the embedding dimension m=5, the scale factor s=12, and the time delay =1, the difference of the two signals’ MPE values is the largest; the classification recognition correctness rate based on the improved EWT_MPE_GK fuzzy clustering algorithm reaches 93.5%, and the average fuzzy entropy (E) is closer to 0, and the classification coefficient (C) is closer to 1; compared with the traditional EWT_MPE_GK fuzzy clustering and EMD_MPE_GK fuzzy clustering, the improved EWT_MPE_GK fuzzy clustering algorithm’s effect is better and its recognition correctness rate rises by 3% and 5.5%, respectively.

导出引用

程铁栋，易其文，吴义文，戴聪聪，蔡改贫，杨丽荣，尹宝勇. 改进EWT_MPE模型在矿山微震信号特征提取中的应用[J]. 振动与冲击, 2021, 40(9): 92-101

CHENG Tiedong, YI Qiwen, WU Yiwen, DAI Congcong, CAI Gaipin, YANG Lirong, YIN Baoyong. Application of improved EWT_MPE model in feature extraction of mine micro-seismic signals[J]. Journal of Vibration and Shock, 2021, 40(9): 92-101

参考文献

［1］尚雪义, 李夕兵, 彭康,等.基于EMD_SVD的矿山微震与爆破信号特征提取及分类方法［J］.岩土工程学报,2016,38(10):1849-1858.
SHANG Xueyi, LI Xibing, PENG Kang, et al.Feature extraction and classification of mine microseism and blast based on EMD-SVD［J］.Chinese Journal of Geotechnical Engineering,2016,38(10):1849-1858.
［2］赵国彦, 邓青林, 马举.基于FSWT时频分析的矿山微震信号分析与识别［J］.岩土工程学报,2015,37(2):306-312.
ZHAO Guoyan, DENG Qinglin, MA Ju, et al.Recognition of mine microseismic signals based on FSWT time-frequency analysis［J］.Chinese Journal of Geotechnical Engineering,2015,37(2):306-312.
［3］江飞飞, 周辉,刘畅,等.地下金属矿山岩爆研究进展及预测与防治［J］.岩石力学与工程学报,2019,38(5): 956-972.
JIANG Feifei, ZHOU Hui, LIU Chang, et al.Progress，prediction and prevention of rockburst in underground metal mines［J］.Chinese Journal of Rock Mechanics and Engineering,2019,38(5): 956-972.
［4］唐礼忠, 杨承祥, 潘长良.大规模深井开采微震监测系统站网布置优化［J］.岩石力学与工程学报,2006,25(10):2036-2042.
TANG Lizhong, YANG Chengxiang, PAN Changliang.Optimization of microseismic monitoring
Network for large-scale deep well mining［J］.Chinese Journal of Rock Mechanics and Engineering,2006, 25(10):2036-2042.
［5］董陇军, 李夕兵, 唐礼忠, 等.无需预先测速的微震震源定位的数学形式及震源参数确定［J］.岩石力学与工程学报,2011,30(10):2057-2067.
DONG Longjun, LI Xibing, TANG Lizhong, et al.Mathematical functions and parameters for microseismic source location without pre-measuring speed［J］.Chinese Journal of Rock Mechanics and Engineering,2011,30(10):2057-2067.
［6］尚雪义, 李夕兵, 彭康, 等.FSWT-SVD模型在岩体微震信号特征提取中的应用［J］.振动与冲击,2017, 36(14):52-60.
SHANG Xueyi, LI Xibing, PENG Kang, et al.Application of FSWT-SVD model in the feature extraction of rock mass microseismic signals［J］.Journal of Vibration and Shock,2017,36(14):52-60.
［7］程铁栋, 吴义文, 罗小燕, 等.基于EWT_Hankel_SVD的矿山微震信号特征提取及分类方法［J］.仪器仪表学报,2019,40(6):181-191.
CHENG Tiedong, WU Yiwen, LUO Xiaoyan, et al.Feature extraction and classification method of mine microseismic signals based on EWT_Hankel_SVD［J］.Chinese Journal of Scientific Instrument, 2019, 40(6):181-191.
［8］WANG C L. Identification of early-warning key point for rockmass instability using acoustic emission/microseismicactivity monitoring［J］.International Journal of Rock Mechanics and Mining Sciences， 2014，71:171-175.
［9］马春驰, 李天斌, 张航,等.基于EMS微震参数的岩爆预警方法及探讨［J］.岩土力学,2018,39(2):765- 774.
MA Chunchi, LI Tianbin, ZHANG Hang, et al.An evaluation and early warning method for rockburst based on EMS microseismic source parameters［J］.Rock and Soil Mechanics,2018,39(2):765-774.
［10］李伟.基于LMD和模式识别的矿山微震信号特征提取及分类方法［J］.煤炭学报,2017,42(5):1156- 1164.
LI Wei. Feature extraction and classification method of mine microseismic signals based on LMD and pattern recognition［J］.Journal of China Coal Society,2017,42(5):1156-1164.
［11］曹安业, 窦林名, 秦玉红, 等.高应力区微震监测信号特征分析［J］.采矿与安全工程学报，2007，24(2): 146-149.
CAO Anye, DOU Linming, QIN Yuhong, et al.Characteristic of microseismic monitoring signal in high stressed zone ［J］.Journal of Mining & Safety Engineering,2007,24(2):146-149.
［12］陆菜平, 窦林名, 吴兴荣, 等.煤岩冲击前兆微震频谱演变规律的试验与实证研究［J］.岩石力学与工程学报,2008,27(3):519-525.
LU Caiping, DOU Linming, WU Xingrong, et al.Experimental and empirical research on frequency spectrum evolvement rule of rock burst precursory microseismic signals of coal-rock［J］.Chinese Journal of Rock Mechanics and Engineering,2008,27(3):519-525.
［13］赵毅鑫,姜耀东,王涛, 等.“两硬”条件下冲击地压微震信号特征及前兆识别［J］.煤炭学报,2012,37 (12):1960-1966． 
ZHAO Yixin, JIANG Yaodong, WANG Tao, et al.Features of microseismic events and precursors of rock burst in underground coal mining with hard roof［J］.Journal of China Coal Society,2012，37(12):1960-1966.
［14］ALLMANN B P, SHEARER P M, HAUKSSON E.Spectral discrimination be tween quarry blasts and earthquakes in Southern California［J］.Bulletin of the Seismological Society of America,2008,98(4):2073-2079.
［15］吴响, 钱建生, 王海燕, 等.微震信号多尺度非线性特征提取与辨识研究［J］.仪器仪表学报,2014,35 (5):969-975.
WU Xiang, QIAN Jiansheng, WANG Haiyan, et al.Study on multi-scale nonlinear feature extraction and signal identification for microseismic signal［J］.Chinese Journal of Scientific Instrument,2014,35(5):969-975.
［16］朱权洁, 姜福兴, 于正兴, 等.爆破震动与岩石破裂微震信号能量分布特征研究［J］.岩石力学与程学报，2012,31(4):723-730.
ZHU Quanjie, JIANG Fuxing, YU Zhengxing, et al.Study on energy distribution characters about blasting vibration and rock fracture microseismic signal［J］.Chinese Journal of Rock Mechanics and Engineering,2012,31(4):723-730.
［17］唐守锋, 童敏明, 潘玉祥, 等.煤岩破裂微震信号的小波特征能谱系数分析法［J］.仪器仪表学报，2011，32(7):1521-1527.
TANG Shoufeng, TONG Minming, PAN Yuxiang, et al.Energy spectrum coefficient analysis of wavelet features for coal rupture microseismicsignal［J］.Chinese Journal of Scientific Instrument,2011,32(7):1521-1527.
［18］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):2036-2042.
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):2036-2042.
［19］GILLES J. Empirical wavelet transform ［J］.IEEE Transactions on Signal Processing,2013,61(16):3999-4010 .
［20］李志农, 朱明, 褚福磊, 等.基于经验小波变换的机械故障诊断方法研究［J］.仪器仪表学报,2014,35 (11):2423-2432.
LI Zhinong, ZHU Ming, CHU Fulei, et al.Mechanical fault diagnosis method based on empirical wavelet transform［J］.Chinese Journal of Scientific Instrument,2014,35(11):2423-2432.
［21］张瑞, 邓艾东, 司晓东, 等.一种新的声发射信号消噪及故障诊断方法［J］.振动与冲击,2018,37(4): 75-81.
ZHANG Rui, DENG Aidong, SI Xiaodong, et al.A new method for acoustic emission signal de-noised and fault diagnosis［J］.Journal of Vibration and Shock,2018,37(4):75-81.
［22］MERAINANI B, RAHMOUNE C, BENAZZOUZ D, et al.A novel gearbox fault feature extraction and classification using Hilbert empirical wavelet transform, singular value decomposition, and SOM neural network［J］.Journal of Vibration and Control,2018,24(12):2512-2531.
［23］陈东宁, 张运东, 姚成玉, 等.基于FVMD多尺度排列熵和GK模糊聚类的故障诊断［J］.机械工程学报2018,54(14):16-27.
CHEN Dongning, ZHANG Yundong, YAO Chengyu, et al.Fault diagnosis based on FVMD multi-scale permutation entropy and GK fuzzy clustering［J］.Journal of Mechanical Engineering,2018,54(14):16-27.
［24］郑小霞, 周国旺, 任浩瀚, 等.基于变分模态分解和排列熵的滚动轴承故障诊断［J］.振动与冲击,2017,36 (22):22-28.
ZHENG Xiaoxia, ZHOU Guowang, REN Haohan, et al.Rolling bearing fault diagnosis method based on variational mode decomposition and permutation entropy［J］.Journal of Vibration and Shock,2017,36(22):22-28.
［25］郑近德, 程军圣, 杨宁.多尺度排列熵及其在滚动轴承故障诊断中的应用［J］.中国机械工程,2013,24 (19):2641-2646.
ZHENG Jinde, CHENG Junsheng, YANG Ning.Multi-scale permutation entropy and its applications to rolling bearing fault diagnosis［J］.China Mechanical Engineering,2013, 24(19):2641-2646.
［26］徐海翔, 崔正湃, 吴林林, 等.基于最大熵谱估计的风电功率周期特性研究［J］.太阳能学报,2018,39 (9):2425-2431.
XU Haixiang, CUI Zhengpai, WU Linlin, et al.Study on periodicity of wind power based on maximum entropy spectrum estimation［J］.Acta Energiae Solari Sinica, 2018,39(9):2425-2431.
［27］胡玉伟, 马萍, 杨明, 等.一种时频结合分析的仿真结果动态一致性检验方法［J］.系统工程与电子技术,2013,35(3):643-649.
HU Yuwei, MA Ping, YANG Ming, et al.Dynamic consistency test method combining time domain with frequency domain for simulation results［J］.Systems Engineering and Electronics,2013,35(3):643-649.
［28］AZIZ W, ARIF M.Multiscale permutation entropy of physiological time series［C］∥Proceeding of IEEE International Multi-topic Conference.IN-MIC,2005.
［29］戴聪聪, 程铁栋, 宗路, 等.基于改进EEMD的红砂岩声发射信号的频谱特性研究［J］.振动与冲击，2018,37(16):118-123.
DAI Congcong, CHEN Tiedong, ZONG Lu, et al.A study on spectrum characteristics of red sandstone acoustic emission signals based on improved EEMD［J］.Journal of Vibration and Shock,2018, 37(16):118-123.
［30］DAVARI A, MARHABAN M H, NOOR S B M, et al.Parameter estimation of K-distributed sea clutter based on fuzzy inference and Gustafson-Kessel clustering［J］.Fuzzy Sets and Systems,2011,163(1): 45-53.
［31］陈学军, 杨永明.采用经验小波变换的风力发电机振动信号消噪［J］.浙江大学学报(工学版),2018,52(5):988-995.
CHEN Xuejun, YANG Yongming.De-noising for vibration signals of wind power generator using empirical wavelet transform［J］.Journal of Zhejiang University (Engineering Science),2018,52(5):988-995.
［32］LUO Zhijun, LIU Tao, YAN Shaoze, et al.Revised empirical wavelet transform based on auto-regressive power spectrum and its application to the mode decomposition of deployable structure［J］.Journal of Sound and Vibration, 2018, 431:70-87.
［33］PU Shi, YANG Wenxian, SHENG Meiping, et al.An enhanced empirical wavelet transform for features extraction from wind turbine condition monitoring signals［J］.Energies, 2017,10(7):972.
［34］徐峰, 刘云飞.基于EMD-SVD的声发射信号特征提取及分类方法［J］.应用基础与工程科学学报,2014, 22(6):1238-1247.
XU Feng, LIU Yunfei.Feature extraction and classification method of acoustic emission signals generated from plywood damage based on EMD-SVD［J］.Journal of Basic Science and Engineering,2014,22(6):1238-1247.