Bearing initial fault feature extraction via sparse representation based on dictionary learning
YU Fa-jun1,2,ZHOU Feng-xing1,YAN Bao-kang1
1.Metallurgical Automation and Detection Technology ERC of Education Ministry, Wuhan university of Science and Technology, Wuhan 430081,China; 2.College of Information & Business, Zhongyuan University of Technology, Zhengzhou 451191,China
As initial fault occurs in rolling bearing of low-speed and heavy-duty machinery, the impulse component, reflecting the fault feature in vibration signal, is difficult to extract for it is relatively weak and easily corrupted by strong background noise. The authors attempt to extract the impulse component from vibration signal with sparse representation method. However, it is difficult to construct the accurate dictionary which matches the impulse component since operating conditions of bearing is not stable. Hence, a method of extracting the initial fault feature, which is based on dictionary learning, is proposed here. Firstly, an adaptive dictionary is obtained by the developed K-SVD dictionary learning algorithm. Then, Orthogonal Matching Pursuit (OMP) algorithm is utilized for sparse decomposition of the vibration signal, and all kurtosis values of approximation signal of iterations are calculated .Finally, the corresponding approximation signal of maximal kurtosis value will be reconstructed and analyzed with envelope spectrum to diagnose the fault type. The test results of simulate data and bearing vibration signal demonstrate that the proposed method, which can extract the feature component more accurately than other methods, meets the demand of real-time bearing condition monitor.
[1] 刘永斌.基于非线性信号分析的滚动轴承状态监测诊断研究[D].合肥:中国科学技术大学,2011:8-9.
[2] Lin J, Qu L. Feature extraction based on Morlet wavelet and its application for mechanical fault diagnosis[J]. Journal of Sound and Vibration, 2000, 234(1):135-148.
[3] Wang S B, Huang W G, Zhu Z K. Transient modeling and parameter identification based on wavelet and correlation filtering for rotating machine fault diagnosis[J]. Mechanical Systems and Signal Processing,2011, 25(4):1299-1320.
[4] Kankar P K, Sharma S C, Harsha S P. Fault diagnosis of rolling element bearing using cyclic autocorrelation and wavelet transform[J]. Neurocomputing, 2013, 110 :9-17.
[5] Cheng J S, Yu D J, Tang J S, et al. Application of frequency family separation method based upon EMD and local Hilbert energy spectrum method to gear fault diagnosis[J]. Mechanism and Machine Theory, 2008, 43:712-723.
[6] Li Y J, Tsea P W, Yang X. EMD-based fault diagnosis for abnormal clearance between contacting components in a diesel engineer[J].Mechanical Systems and Signal Processing, 2010, 24:193-210.
[7] Peng F Q, Yu D J, Luo J S. Sparse signal decomposition method based on multi-scale chirplet and its application to the fault diagnosis of gearboxes[J]. Mechanical Systems and Signal Processing,2011, 25:549-557.
[8] Mallat S G, Zhang Z. Matching pursuits with time-frequency dictionaries[J]. IEEE Transactions on Signal Processing,1993, 41(12): 3397-3415.
[9] Wang Xin-qing, Zhu Hui-jie, Wang Dong. The diagnosis of rolling bearing based on the parameters of pulse atoms and degree of cyclostationarity[J]. Journal of Vibroengineering, 2013, 15(3):1560-1575.
[10]严保康,周凤星. 基于相干累积量正交匹配追踪算法的轴承早期故障稀疏特征提取[J]. 机械工程学报,2014, 50(13): 88-94.
YAN Bao-kang, ZHOU Feng-xing.Initial fault identification of bearing based on coherent cumulant stagewise orthogonal matching pursuit[J]. Journal of Mechanical Engineer,2014, 50(13):88-94.
[11] Engan K, Aase S O, Husoy J H. Method of optimal directions for frame design[J].Proceedings ICASSP' 99- IEEE International Conference on Acoustics, Speech, and Signal Processing, 1999,5:2443-2446.
[12] Aharon M, Elad M, Bruckstein A M.The K-SVD: an algorithm for designing of overcomplete dictionaries for sparse representation[J].IEEE Transactions on Signal Processing,2006, 54(11): 4311-4322.
[13] Zhou Yan, Zhao He-ming, Shang Li. Immune K-SVD algorithm for dictionary learning in speech denoising[J]. Neurocomputing, 2014, 137:223-233.
[14] Elad M, Aharon M. Image denoising via sparse and redundant representations over learned dictionaries[J]. IEEE Transactions on Image Processing,2006,15(12):3736-3745.
[15]王国栋,阳建宏,黎敏,等. 基于自适应稀疏表示的宽带噪声去除算法[J]. 仪器仪表学报, 2011,32(8): 1818-1823.
WANG Guo-dong, YANG Jian-hong, LI Min, et al. Wideband noise removing algorithm based on adaptive sparse representation[J]. Chinese Journal of Scientific Instrument, 2011,32(8): 1818-1823.
[16]苏文胜,王奉涛,张志新.EMD降噪和谱峭度法在滚动轴承早期故障诊断中的应用[J].振动与冲击,2010,29(3):18-22.
SU Wen-sheng,WANG Feng-tao,ZHANG Zhi-xin.Application of EMD denoising and spectral kurtosis in early fault diagnosis of rolling element bearings[J]. Journal of Vibration and Shock,2010,29(3):18-22.
[17]李洋,李双田. 压缩感知下的稀疏表示语音恢复模型与算法[J].信号处理,2014,30(8):914-923.
LI Yang, LI Shuang-tian. Speech recovery model and algorithm over sparse representation based on compressive sensing[J].Journal of Signal Processing, 2014,30(8):914-923.
[18]苗中华,周广兴,刘海宁,等.基于稀疏编码的振动信号特征提取算法与实验研究[J].振动与冲击,2014,33(15):76-81.
MIAO Zhong-hua,ZHOU Guang-xing, LIU Hai-ning, et al. Tests and feature extraction algorithm of vibration signals based on sparse coding[J].Journal of Vibration and Shock, 2014,33(15):76-81.