基于RST&mdash;NMF模型的微震信号时频分析和识别

PDF(2052 KB)

振动与冲击 ›› 2019, Vol. 38 ›› Issue (17) : 1-7.

论文

基于RST—NMF模型的微震信号时频分析和识别

张法全 1,2 ，王海飞 1，王国富 1,2，叶金才 1,2

作者信息 +

Time-frequency analysis and identification for micro-seismic signals based on RST-NMF model

ZHANG Faquan1,2,WANG Haifei1, WANG Guofu1,2,YE Jincai1,2

Author information +

文章历史 +

摘要

针对微震信号难以精确识别的问题，提出一种基于RST—NMF微震信号时频分析和分类方法。首先对微震信号进行S变换得到时频矩阵，然后在频率方向上进行重排，再借助非负矩阵分解技术得到时、频域的分解向量，从中提取宏观、微观统计量构造信号的特征空间，最后采用SVM进行分类。在三道沟井田的试验结果表明，RST时频分析方法对频域分散的能量团有很好的聚集性，时频矩阵经NMF分解最大程度上获取微震信号的局部特征和内在联系，提取分解向量的宏观和微观统计量保证了信号特征空间的完备性，有效地避免了分类时过拟合的发生，分类准确率达到了94%。

Abstract

Aiming at the problem of micro-seismic signals being difficult to accurately identify, a time-frequency analysis and classification method based on RST-NMF model was proposed.Firstly, S-transform was performed for a micro-seismic signal to obtain a time-frequency matrix, and this matrix was rearranged in frequency direction.The non-negative matrix factor (NMF) technique was used to obtain resolved vectors in time domain and frequency one.Macro and micro statistics were extracted from these vectors to construct the signal’s feature space, and SVM was used to do classification.The test results of SAN Daogou minefield showed that the time-frequency analysis method of RST has a good clustering for frequency domain dispersed energy groups; local characteristics and internal relations of a micro-seismic signal are obtained to the greatest extent from the time-frequency matrix with the NMF technique; extracting macro and micro statistics of resolved vectors can ensure the completeness of a signal feature space and effectively avoid the occurrence of over-fitting during classification; the correct rate of classification can reach 94%.

导出引用

张法全 1,2,王海飞 1，王国富 1,2，叶金才 1,2. 基于RST—NMF模型的微震信号时频分析和识别[J]. 振动与冲击, 2019, 38(17): 1-7

ZHANG Faquan1,2,WANG Haifei1, WANG Guofu1,2,YE Jincai1,2. Time-frequency analysis and identification for micro-seismic signals based on RST-NMF model[J]. Journal of Vibration and Shock, 2019, 38(17): 1-7

参考文献

[1]李楠，王恩元，CE Mao-chen. 微震监测技术及其在煤矿的应用现状与展望[J]. 煤炭学报，2017, 42(S1):83-96
Li Nan, Wang Enyuan, Ge Maochen. Microseismic monitoring technique and its applications at coal mines: present status and future prospercts [J]. Journal of China Society, 2017, 42(S1)：83-96.
[2]HE M C, MIAO J L, FENG J L. Rock burst process of limestone and acoustic emission characteristics under true-trivial unloading conditions [J]. International Journal of Rock Mechanics and Mining Sciences, 2010, 47(2): 286-298.
[3]Mark C.Coal burst in the deep longwall mines of the United States[J]. International Journal of Coal Science & Technology,2016,3(1):1-9.
[4]郭超，陈蓥. 矿山震动信号预处理及其对时频的影响[J]. 煤炭学报，2016, 41(7):1859-1865.
Guo Chao, Chen Ying. Filtering technique for mining vibration signals and its affection on the signals’ time-frequency characteristics [J]. Journal of China Coal Society, 2016, 41(7):1859-1865.
[5]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]. 岩石力学与工程学报，2012, 31(4): 723-730.
Zhu Quanjie, Jiang Fuxing, Yu Zhengxing, et al. Study on energy distribution characters about blasting vibration and rock Mechanics and Engineering [J], Chinese Journal of Geotechnical Engineering.2012, 31(4): 723 – 730.(in Chinese)
[6]江文武，杨作林，谢建敏，等. FFT频谱分析在微震信号识别中的应用[J]. 科技导报，2015, 33(2):86-90
Jiang Wenwu, YANG Zuolin, XIE Jianmin, et al. Applyication of FFT spectrum analysis to identify microseismic signals [J]. Science &Technology Review , 2015, 33(2):86-90
[7]Ma J, Zhao G Y,Dong L J,et al. A comparison of mine seismic discriminators based on features of source parameters to waveform characteristic[J]. Shock and Vibration,2015,25(10): 3410-3420
[8]尚雪义，李夕兵，彭康. 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):53-59
Shang Xue-yi, 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):53-59
[9]唐守峰，童敏明，潘玉祥，等. 煤岩破裂微震信号的小波特征能量谱系数分析法[J]. 仪器仪表学报，2011, 32(7): 1521-1527.
Tang Shoufeng, Tong Minming, PAN Yuxiang, et al. Energy spectrum confficient analysis of wavelet features for coal rupture microseismic signal [J]. Chinese Journal of Scientific Instrument, 2011, 32(7): 1522-1527.
[10]朱权洁，姜福兴，尹永明，等. 基于小波分型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 Yong-ming, 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
[11]唐礼忠，陈资南，张君，等. 矿山微震信号小波分析与研究 [J]. 科技导报，2013, 31(32):29-31.
Tang Lizhong, Chen Zinan, Zhang Jun, et al. Research and Analysis on Wavelet of Mine Microseismic Signals [J]. Science &Technology Review, 2013, 31(32):29-31.
[12]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]. 岩土力学与工程学报. 2015, 34(2):4072-4078
Jiang Peng, Dai Feng, Xu Nuwen, et al. Identification of microseismic signal in underground powerhouse based on ST time-frequency analisis [J]. Chinese Journal of Rock Mechanics and engineering. 2015, 34(2):4072-4078.
[13]Huang K, Sidiropoulos N D, Swami A. NMF revisited: New uniqueness results and algorithms.[C] //Proceddings of 2013 IEEE Internation Conference on Acoustics, Speech and Signal Processing(ICASSP). Vancouver: ICASSP, 2013:4524-4528.
[14]PENG Y, CHEN X, Ye Q X, et al. Fault detection and classification in chemical processes usiong NMFSC and structral SVMs[J].The Candian Journal of Chemical Engineering,2014,92(6):1016-1023.
[15]吴兴扬，卫志农，孙国强，等. 基于非负矩阵分解的同调机群识别方法[J]. 2013,37(14):59-63.
Wu Xingyang, Wei Zhinong, Sun Guoqiang. A Method for Identifying Coherators Based on Non-negative Matrix Factorization [J]. Automation of Electric Power Systems, 2013, 37(14):59-63
[16]LI X B, YANG Y P,ZHANG W D. Statistical process monitoring via geberalized non-negative matrix projection[J].Chemomeyrics & Intelligent Laboratory Systems,2013,121(7):15-25.
[17]李臣明，张师明，李昌利. 非负矩阵分解的一个约束稀疏算法[J]. 2015,47(2):109-111.
Li Chenming, Zhang Shiming, Li Changli. A Constrained Sparse Algorithm for Nonnegative Matrix Factorization [J]. JOURNAL OF SICHUAN UNIVERSITY (ENGINEERING SCIENCE EDITION), 2015, 47(2):109-111.
[18]吴小羊，刘天佑. 基于时频重排的地震信号Wigner-Ville分布时频分析[J]. 石油地球物理勘探，2009, 44(2):201-205.
Wu Xiaoyang, Liu Tianyou. Time-frequency analysis on Wigner-ville distribution of seismic signal based on time-frequency rearrangement [J]. OGP, 2009, 44(2):201-205
[19]严峰，陈晓，王新民等. 改进的离散化小波-优化极限学习机在倾转旋翼机故障诊断中的应用[J]. 2014, 35(11):1915-1921.
Yan Feng, Chen Xiao, Wang Xinmin, et al. Fault Diagnosis of Tiltrotor Aircraft via Improved Discrete Wavelet-OMELM [J]. ACTA ARMAMENTARII, 2014, 35(11):1915-1921.
[20]LI X B, YANG Y P, ZHANG W D. Fault detection method for non-Gaussian processes based on non-negative matrix factorization[J]. Asia-Pacific Journal of Chemical Engineering, 2013,8(8):362-370
[21]周志华. 机器学习[M]. 北京：清华大学出版社，2016.
Zhou Zhihua. MACHINE LEARNING [M]. Beijing: TSINGHUA UNIVERSITY PRESS, 2016.
[22]赵国彦，邓青林. 基于LCD分解的微震信号分析与识别[J]. 科技导报，2014, 32(27):49-54
Zhao Guoyan, Deng Qinglin. Analysis and Differentiation of Micro-seismic Signal Based on LCD Decomposition [J]. Science &Technology Review[J]. 2014,32(27):49-54
[23]TIAN Y, MA J, LU C, et al. Rolling bearing fault diagnosis under vareable conditions usiong LMD-SVD and extreme learning machine[J]. Mechanism and Machine Theory, 2015, 90:175-186.