Application of FSWT_SVD Model for Feature Extraction of Rock Mass Microseismic Signal
SHANG Xueyi1 LI Xibing1 PENG Kang2,3 WANG Zewei1 WENG Lei1
1. School of Resources and Safety Engineering, Central South University, Changsha, Hu’nan 410083, China;
2. State Key Laboratory of Coal Mine Disaster Dynamics and Control, Chongqing University, Chongqing 400044, China;
3. College of Resources and Environmental Science, Chongqing University, Chongqing 400030, China
To solve the problem that it is difficult to identify rock mass fracturing signals and blasting vibration signals, the Fourier transform (FT) was applied to gain their spectrum distributions and six frequency bands were needed for the feature extraction analysis. Then the rock mass fracturing signals were divided and reconstructed by frequency slice wavelet transform (FSWT), and the singular value decomposition (SVD) was employed to obtain singular values of matrixes composed of the six reconstructed components, thus the feature extraction of rock mass fracturing signals was implemented. Furthermore, 120 sets of rock mass fracturing signals and 120 sets of blasting vibration signals obtained from Yongshaba mine were analysed using the FSWT_SVD method. Finally, the back propagation (BP) neural network was adopted to train, classify and recognize the eigenvectors obtained from the singular values. The results show that: (1) There are large differences of , comparatively large differences of , , and , and little differences of between rock mass fracturing signals and blasting vibration signals, and the best pattern recognition was obtained when is eight with an accuracy rate of 86.67%. (2) The classification result based on BP neural network is the best among the BP, Logistic Regression (LR), Bayes and Fisher based methods, the feature matrix obtained by the SVD is better than that obtained by the energy ratio and correlation coefficient matrix, and the feature matrix obtained from FSWT is better than that of discrete wavelet transform (DWT). Furthermore, the BP classifier based on FSWT_SVD achieves a correct identification rate of 91%. In conclusion, the BP classifier based on FSWT_SVD provides a new way for feature extraction and pattern recognition of rock mass fracturing signal and blasting vibration signal.
尚雪义1 李夕兵1 彭 康2,3 王泽伟1 翁 磊1. 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 Xueyi1 LI Xibing1 PENG Kang2,3 WANG Zewei1 WENG Lei1. Application of FSWT_SVD Model for Feature Extraction of Rock Mass Microseismic Signal. JOURNAL OF VIBRATION AND SHOCK, 2017, 36(14): 52-60.
[1] Dong L, Li X, Xie G. Nonlinear methodologies for identifying seismic event and nuclear explosion using random forest, support vector machine, and naive Bayes classification[J]. Abstract and Applied Analysis, 2014, 2014: 459137.
[2] Dong L, Wesseloo J, Potvin Y, et al. Discrimination of Mine Seismic Events and Blasts Using the Fisher Classifier, Naive Bayesian Classifier and Logistic Regression[J]. Rock Mechanics and Rock Engineering, 2016, 49(1): 183-211.
[3] Gulia L. Detection of quarry and mine blast contamination in European regional catalogues[J]. Natural hazards, 2010, 53(2): 229-249.
[4] 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 Quan-jie, JIANG Fu-xing, 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.
[5] Yıldırım E, Gülbağ A, Horasan G, et al. Discrimination of quarry blasts and earthquakes in the vicinity of Istanbul using soft computing techniques[J]. Computers & Geosciences, 2011, 37(9): 1209-1217.
[6] 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 An-ye, DOU Lin-ming, QIN Yu-hong, et al. Characteristic of Microseismic Monitoring Signal in High Stressed Zone[J]. Journal of Mining & Safety Engineering, 2007, 24(2): 146-149.
[7] Allmann B P, Shearer P M, Hauksson E. Spectral discrimination between quarry blasts and earthquakes in Southern California[J]. Bulletin of the Seismological Society of America, 2008, 98(4): 2073-2079.
[8] 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 Cai-ping, DOU Lin-ming, WU Xing-rong, et al. Experimental and empirical research on frequency- spectrum evolvement rule of rockburst precursory microseismic signals of coal-rock [J]. Chinese Journal of Rock Mechanics and Engineering, 2008, 27(3): 519-525.
[9] 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 Shou-feng, TONG Min-ming, PAN Yu-xiang, et al. Energy spectrum coefficient 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, 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 Quan-jie, JIANG Fu-xing, YU Zheng-xing, 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.
[11] 毕明霞, 黄汉明, 边银菊, 等. 天然地震与人工爆破波形信号HHT特征提取和SVM识别研究[J]. 地球物理学进展, 2011, 26(4): 1157-1164.
BI Ming-xia, HUANG Han-ming, BIAN Yin-ju, et al. A study on seismic signal HHT features extraction and SVM recognition of earthquake and explosion[J]. Progress in Geophysics, 2011, 26(4): 1157-1164.
[12] 毕明霞, 黄汉明, 边银菊, 等. 基于经验模态分解的地震波特征提取的研究[J]. 地球物理学进展, 2013, 27(5): 1890-1896.
BI Ming-xia, HUANG Han-ming, BIAN Yin-ju, et al. Study on seismic signal features extraction based on EM D[J]. Progress in Geophysics, 2012, 27(5): 1890-1896.
[13] 李舜酩, 郭海东, 李殿荣. 振动信号处理方法综述[J]. 仪器仪表学报, 2013, 34(8): 1907-1915.
LI Shun-ming, GUO Hai-dong, LI Dian-rong. Review of vibration signal processing methods[J]. Chinese Journal of Scientific Instrument, 2013, 34( 8): 1907-1915.
[14] Huang N E, Shen Z, Long S R, Wu M C, Shih H H, Zhang Q, Yen N C, Tung C C Liu H H. The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis[C]//Proceedings of the Royal Society of London A: Mathematical, Physical and Engineering Sciences. The Royal Society, 1998, 454(1971): 903-995.
[15] Yan Z, Miyamoto A, Jiang Z. Frequency slice wavelet transform for transient vibration response analysis[J]. Mechanical Systems & Signal Processing, 2009, 23(5): 1474–1489.
[16] Yan Z, Miyamoto A, Jiang Z, Liu X. An overall theoretical description of frequency slice wavelet transform[J]. Mechanical Systems and Signal Processing, 2010, 24(2): 491-507.
[17] Yan Z, Miyamoto A, Jiang Z. Frequency slice algorithm for modal signal separation and damping identification[J]. Computers & structures, 2011, 89(1): 14-26.
[18] 钟先友, 赵春华 陈保家, 等. 基于形态自相关和时频切片分析的轴承故障诊断方法[J]. 振动与冲击, 2014, 33(4): 11-16.
ZHONG Xian-you, ZHAO Chun-hua, CHEN Bao-jia, et al. Bearing fault diagnosis method based on morphological filtering, time-delayed autocorrelation and time-frequency slice analysis[J]. Journal of Vibration and Shock, 2014, 33(4): 11-16.
[19] 郭涛, 方向, 谢全民, 等. 频率切片小波变换在爆破振动信号时频特征精确提取中应用[J]. 振动与冲击, 2013, 32(22): 73-78.
GUO Tao, FANG Xiang, XIE Quan-min, et al. Application of FSWT in accurate extraction of time-frequency features for blasting vibration signals[J]. Journal of Vibration and Shock, 2013, 32(22): 73-78.
[20] 段晨东，高 强．基于时频切片分析的故障诊断方法及应用[J]. 振动与冲击, 2011, 30 (9): 1-5.
DUAN Chen-dong, GAO Qiang. Noval fault diagnosis approach using time-frequency slice analysis and its application[J]. Journal of Vibration and Shock, 2011, 30 (9): 1-5.
[21] 段晨东, 高强, 徐先峰. 频率切片小波变换时频分析方法在发电机组故障诊断中的应用[J]. 中国电机工程学报, 2013, 33(32): 96-103.
DUAN Chen-dong, GAO Qiang, XU Xian-feng. Generator unit fault diagnosis using the frequency slice wavelet transform time-frequency analysis method[J]. Proceedings of the CSEE, 2013, 33(32): 96-103.
[22] Ai L, Wang J, Yao R. Classification of parkinsonian and essential tremor using empirical mode decomposition and support vector machine[J]. Digital Signal Processing, 2011, 21(4): 543-550.
[23] 徐锋, 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 Yun-fei. 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.
[24] 徐锋, 刘云飞, 宋军. 基于中值滤波-SVD和EMD的声发射信号特征提取[J]. 仪器仪表学报, 2011, 32(12): 2712-2719.
XU Feng, LIU Yun-fei, SONG Jun. Feature extraction of acoustic emission signals based on median filter-SVD and EMD[J]. Chinese Journal of Scientific Instrument, 2011, 32(12): 2712-2719.
[25] 丁建明, 王晗, 林建辉, 等. 基于 EMD-Hankel-SVD 的高速列车万向轴动不平衡检测[J]. 振动与冲击, 2015, 34(9): 164-170.
DING Jian-ming, WANG Han, LIN Jian-hui, et al. Detection of dynamic imbalance due to cardan shaft in high-speed train based on EMD-Hankel-SVD method[J]. Journal of Vibration and Shock, 2015, 34(9): 164-170.
[26] 丁建明, 林建辉, 赵洁. 高速列车万向轴动不平衡检测的 EEMD-Hankel-SVD 方法[J]. 机械工程学报, 2015, 51(10): 143-151.
DING Jian-ming LIN Jian-hui ZHAO Jie. Detection of the dynamic imbalance with cardan shaft in high-speed train applying EEMD-Hankel-SVD[J]. Journal of Mechanical Engineering, 2015, 51(10): 143-151.
[27] Zhang Y, Zuo H, Bai F. Classification of fault location and performance degradation of a roller bearing[J]. Measurement, 2013, 46(3): 1178-1189.
[28] Yang Z X, Zhong J H. A Hybrid EEMD-Based SampEn and SVD for Acoustic Signal Processing and Fault Diagnosis[J]. Entropy, 2016, 18(4): 112.
[29] 姜久亮, 刘文艺, 侯玉洁, 等. 基于内积延拓 LMD 及 SVM 的轴承故障诊断方法研究[J]. 振动与冲击, 2016, 35(6): 104-108.
JIANG Jiu-liang, LIU Wen-yi, HOU Yu-jie, et al. Bearing fault diagnosis based on integral waveform extension LMD and SVM[J]. Journal of Vibration and Shock, 2016, 35(6): 104-108.
[30] Tian Y, Ma J, Lu C, et al. Rolling bearing fault diagnosis under variable conditions using LMD-SVD and extreme learning machine[J]. Mechanism and Machine Theory, 2015, 90: 175-186.
[31] 赵学智, 叶邦彦, 陈统坚. 基于小波—奇异值分解差分谱的弱故障特征提取方法[J]. 机械工程学报, 2012, 48(7): 37-48.
ZHAO Xue-zhi YE Bang-yan CHEN Tong-jian. Extraction method of faint fault feature based on Wavelet-SVD difference spectrum. Journal of Mechanical Engineering, , 2012, 48(7): 37-48.
[32] Jiang Y, Tang B, Qin Y, et al. Feature extraction method of wind turbine based on adaptive Morlet wavelet and SVD[J]. Renewable energy, 2011, 36(8): 2146-2153.
[33] 朱军, 闵祥敏, 孔凡让, 等. 基于分量筛选奇异值分解的滚动轴承故障诊断方法研究[J]. 振动与冲击, 2015, 34(20): 61-65.
ZHU Jun, MIN Xiang-min, KONG Fan-rang, et al. Rolling bearing fault diagnosis based on component screening singular value decomposition[J]. Journal of Vibration and Shock, 2015, 34(20): 61-65.
[34] Liu H, Wang X, Lu C. Rolling bearing fault diagnosis under variable conditions using Hilbert-Huang transform and singular value decomposition[J]. Mathematical Problems in Engineering, 2014, 2014: 765621.
[35] McGill R, Tukey J W, Larsen W A. Variations of box plots[J]. The American Statistician, 1978, 32(1): 12-16.
[36] McClelland J L, Rumelhart D E, PDP Research Group. Parallel distributed processing[M]. IEEE,1988.
[37] Rumelhart D E, Hinton G E, Williams R J. Learning internal representations by error propagation[R]. In Parallel distributed processing: explorations in the microstructure of cognition, vol. 1. Cambridge, MA, USA: MIT Press, 1986:318-362.
[38] 赵志宏, 杨绍普, 申永军. 基于独立分量分析与相关系数的机械故障特征提取[J]. 振动与冲击, 2013, 32(6): 67-72.
ZHAO Zhi-hong, YANG Shao-pu, SHEN Yong-jun. Machinery fault feature extraction based on independent component analysis and correlation coefficient [J]. Journal of Vibration and Shock, 2013, 32(6): 67-72.
