[1] Wang Fei, Xu Feiyun, Wang Haijun,. Local hierarchical non-negative tensor factorizationand its application in machinery fault diagnosis [J]. Journal of Southeast University (English Edition), 2011, 27 (4): 394-399. [doi:10.3969/j.issn.1003-7985.2011.04.010]

Copy

Local hierarchical non-negative tensor factorizationand its application in machinery fault diagnosis()

Share：

Journal of Southeast University (English Edition)[ISSN:1003-7985/CN:32-1325/N]

Volumn:

27

Issue:

2011 4

Page:

394-399

Research Field:

Automation

Publishing date:

2011-12-31

Info

Title:

Local hierarchical non-negative tensor factorizationand its application in machinery fault diagnosis

Author(s):

Wang Fei¹;  Xu Feiyun²;  Wang Haijun²

School of Mechanical Engineering, Southeast University, Nanjing 211189, China

Keywords:

non-negative tensor factorization;  bispectrum;  feature extraction;  air compressor;  BP neural network

PACS:

TP206.3

DOI:

10.3969/j.issn.1003-7985.2011.04.010

Abstract:

Aiming at the slow convergence and low accuracy problems of the traditional non-negative tensor factorization, a local hierarchical non-negative tensor factorization method is proposed by applying the local objective function theory to non-negative tensor factorization and combining the three semi-non-negative matrix factorization(NMF)model. The effectiveness of the method is verified by the facial feature extraction experiment. Through the decomposition of a series of an air compressor’s vibration signals composed in the form of a bispectrum by this new method, the basis images representing the fault features and corresponding weight matrices are obtained. Then the relationships between characteristics and faults are analyzed and the fault types are classified by importing the weight matrices into the BP neural network. Experimental results show that the accuracy of fault diagnosis is improved by this new method compared with other feature extraction methods.

References:

[1] Hazan T, Polak S, Shashua A. Sparse image coding using a 3D non-negative tensor factorization[C]//Proceedings of the Tenth IEEE International Conference on Computer Vision. Beijing, China, 2005:50-57.
[2] Cichocki A, Phan A H, Caiafa C. Flexible HALS algorithms for sparse non-negative matrix/tensor factorization[C]//Proceedings of 2008 IEEE International Workshop on Machine Learning for Signal Processing. Cancun, Mexico, 2008: 73-78.
[3] Heiler M, Schnörr C. Controlling sparseness in non-negative tensor factorization [C]//The Ninth European Conference on Computer Vision. Graz, Austria, 2006: 56-67.
[4] Park S W, Savvides M. Estimating mixing factors simultaneously in multilinear tensor decomposition for robust face recognition and synthesis [C]//Proceedings of the 2006 IEEE Conference on Computer Vision and Pattern Recognition Workshop. New York, USA, 2006: 49-55.
[5] Peng Sen. Research on mechanical fault feature extraction based on non-negative tensor factorization[D]. Nanjing: School of Mechanical Engineering of Southeast University, 2010.(in Chinese)
[6] Zhang Q, Wang H, Plemmons R J, et al. Tensor methods for hyperspectral data analysis: a space object material identification study[J]. Journal of the Optical Society of America A: Optics, Image Science, and Vision, 2008, 25(12): 3001-3012.
[7] Ji Jinlu. Research on mechanical fault feature extraction theories and methods based on non-negative factorization[D]. Nanjing: School of Mechanical Engineering of Southeast University, 2011.(in Chinese)
[8] Cichocki A, Zdunek R, Amari S I. Hierarchical ALS algorithms for nonnegative matrix and 3D tensor factorization[C]//Proceedings of the Seventh International Conference on Independent Component Analysis and Signal Separation. London, UK, 2007:169-176.
[9] Zhang Jianzhong. The common typical faults’ mechanism and characteristics analysis of the rotating machinery[J]. Guangxi Light Industry, 2008(7): 32-33.(in Chinese)
[10] Ma Jiancang, Niu Yilong, Chen Haiyang. Blind signal processing[M]. Beijing: National Defence Industry Press, 2006:38-44.(in Chinese)

Memo

Memo:

Biographies: Wang Fei(1985—), male, graduate; Xu Feiyun(corresponding author), male, doctor, professor, fyxu@seu.edu.cn.
Foundation items: The National Natural Science Foundation of China(No.50875078), the Natural Science Foundation of Jiangsu Province(No.BK2007115), the National High Technology Research and Development Program of China(863 Program)(No.2007AA04Z421).
Citation: Wang Fei, Xu Feiyun, Wang Haijun.Local hierarchical non-negative tensor factorization and its application in machinery fault diagnosis[J].Journal of Southeast University(English Edition), 2011, 27(4):394-399.[doi:10.3969/j.issn.1003-7985.2011.04.010]

Common functions