Theory of multi-resolution singular value decomposition and its application to signal processing and fault diagnosis

被引：0

作者：

Zhao X. ^{[1
]}

Ye B. ^{[1
]}

Chen T. ^{[1
]}

机构：

[1] School of Mechanical and Automotive Engineering, South China University of Technology

来源：

Jixie Gongcheng Xuebao/Journal of Mechanical Engineering | 2010年 / 46卷 / 20期

关键词：

Feature extraction; Multi-resolution analysis; Multi-resolution SVD; Signal processing; Singular value decomposition; Singularity detection;

D O I：

10.3901/JME.2010.20.064

中图分类号：

学科分类号：

摘要：

The concept of multi-resolution singular value decomposition (MRSVD) is put forward. Based on the principle of dichotomy and recursion creation of matrix, a signal is decomposed into a series of approximation and detail signals with different resolution by singular value decomposition, and then the overview and detail features of original signal can be shown at different levels. The decomposition and reconstruction algorithm of MRSVD is given, and the property of multi-resolution analysis of this method is proved theoretically. The signal processing results show that MRSVD can detect the accurate position of singular point in signal, thus the defect of wavelet detection, i.e. the position deviation of singular point, is overcome. In addition, MRSVD can achieve good noise reduction effect without phase shift and distortion. Another function of MRSVD is to extract the faint fault feature, and the processing result for a bearing vibration signal shows that the hidden periodical impulses are well extracted by MRSVD, and then the fault of bearing is precisely diagnosed. The comparative study carried out with wavelet transform demonstrates that MRSVD has good application prospect in signal processing and fault diagnosis domain. © 2010 Journal of Mechanical Engineering.

引用

页码：64 / 75

页数：11

共 21 条

[1]

Phillips R.D., Watson L.T., Wynne R.H., Et al., Feature reduction using a singular value decomposition for the iterative guided spectral class rejection hybrid classifier, ISPRS Journal of Photogrammetry and Remote Sensing, 64, 1, pp. 107-116, (2009)

[2]

Ahmed S.M., Alzoubi Q., Abozahhad M., A hybrid ECG compression algorithm based on singular value decomposition and discrete wavelet transform, Journal of Medical Engineering and Technology, 31, 1, pp. 54-61, (2007)

[3]

Vanlanduit S., Cauberghe B., Guillaume P., Reduction of large frequency response function data sets using robust singular value decomposition, Computers and Structures, 84, 12, pp. 808-822, (2006)

[4]

Vozalis M.G., Margaritis K.G., Using SVD and demographic data for the enhancement of generalized collaborative filtering, Information Sciences, 177, 15, pp. 3017-3037, (2007)

[5]

Williams T., Ahmadi M., Miller W.C., Design of 2D FIR and IIR digital filters with canonical signed digit coefficients using singular value decomposition and genetic algorithms, Circuits Systems and Signal Processing, 26, 1, pp. 69-89, (2007)

[6]

Lehtola L., Karsikas M., Koskinen M., Et al., Effects of noise and filtering on SVD-based morphological parameters of the T wave in the ECG, Journal of Medical Engineering and Technology, 32, 5, pp. 400-407, (2008)

[7]

Yang W., Jiang J., Study on the singular entropy of mechanical signal, Chinese Journal of Mechanical Engineering, 36, 12, pp. 9-13, (2000)

[8]

Mark B., Jiang D., Noise reduction in multiple-echo data sets using singular value decomposition, Magnetic Resonance Imaging, 24, 2, pp. 849-856, (2006)

[9]

Liu H., Li J., Zhao Y., Et al., Improved singular value decomposition technique for detecting and extracting periodic impulse component in a vibration signal, Chinese Journal of Mechanical Engineering, 17, 3, pp. 340-345, (2004)

[10]

Cempel C., Generalized singular value decomposition in multidimensional condition monitoring of machines - A proposal of comparative diagnostics, Mechanical Systems and Signal Processing, 23, 3, pp. 701-711, (2009)

← 1 2 3 →