A novel multi-segment feature fusion based fault classification approach for rotating machinery

Liang, J; Zhang, Y; Zhong, JH; Yang, H

A novel multi-segment feature fusion based fault classification approach for rotating machinery

Liang, J

Zhang, Y

Zhong, JH Yang, H

Permalink

Publication Type:: Journal Article
Citation:: Mechanical Systems and Signal Processing, 2019, 122 pp. 19 - 41
Issue Date:: 2019-05-01

Closed Access

	Filename	Description	Size
	A novel multi-segment feature fusion based fault classification approach for rotating machinery.pdf	Published Version	4.21 MB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Closed Access

This item is closed access and not available.

Full metadata record

Field	Value	Language
dc.contributor.author	Liang, J https://orcid.org/0000-0001-8549-0261	en_US
dc.contributor.author	Zhang, Y https://orcid.org/0000-0002-2674-1638	en_US
dc.contributor.author	Zhong, JH	en_US
dc.contributor.author	Yang, H https://orcid.org/0000-0002-4987-5794	en_US
dc.date.issued	2019-05-01	en_US
dc.identifier.citation	Mechanical Systems and Signal Processing, 2019, 122 pp. 19 - 41	en_US
dc.identifier.issn	0888-3270	en_US
dc.identifier.uri	http://hdl.handle.net/10453/134798
dc.description.abstract	© 2018 Elsevier Ltd Accurate and efficient rotating machinery fault diagnosis is crucial for industries to guarantee the productivity and reduce the maintenance cost. This paper systematically proposes a new fault diagnosis approach including signal processing techniques and pattern recognition method. In order to reveal more useful details in a fault residing signal, a novel automatic signal segmentation method named Grassmann manifold – angular central Gaussian distribution is proposed to divide a raw signal into several segments, resulting in a significant improvement of diagnosis accuracy. An improved empirical mode decomposition, wavelet transform – ensemble empirical mode decomposition, is also designed which could adequately solve the problems of mode mixing and end effects. Moreover, a morphological method usually used in image processing is investigated and adopted to change the shape of the intrinsic mode functions to further reveal the faulty impulses. In order to reduce the high dimension of the extracted features and improve the computational efficiency and accuracy, a deep belief network is designed to conduct information fusion, and compared with widely adopted kernel principal component analysis. For classification, a pairwise coupling strategy is proposed and combined with sparse Bayesian extreme learning machine. The experiments conducted using the proposed approach demonstrate the effectiveness of the proposed system.	en_US
dc.relation	http://purl.org/au-research/grants/arc/DP150102751
dc.relation.ispartof	Mechanical Systems and Signal Processing	en_US
dc.relation.isbasedon	10.1016/j.ymssp.2018.12.009	en_US
dc.subject.classification	Acoustics	en_US
dc.title	A novel multi-segment feature fusion based fault classification approach for rotating machinery	en_US
dc.type	Journal Article
utslib.citation.volume	122	en_US
utslib.for	0905 Civil Engineering	en_US
utslib.for	0913 Mechanical Engineering	en_US
utslib.for	0915 Interdisciplinary Engineering	en_US
pubs.embargo.period	Not known	en_US
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology/School of Computer Science
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology/School of Mechanical and Mechatronic Engineering
pubs.organisational-group	/University of Technology Sydney/Strength - CAI - Centre for Artificial Intelligence
pubs.organisational-group	/University of Technology Sydney/Students
utslib.copyright.status	closed_access
pubs.publication-status	Published	en_US
pubs.volume	122	en_US

Abstract:

© 2018 Elsevier Ltd Accurate and efficient rotating machinery fault diagnosis is crucial for industries to guarantee the productivity and reduce the maintenance cost. This paper systematically proposes a new fault diagnosis approach including signal processing techniques and pattern recognition method. In order to reveal more useful details in a fault residing signal, a novel automatic signal segmentation method named Grassmann manifold – angular central Gaussian distribution is proposed to divide a raw signal into several segments, resulting in a significant improvement of diagnosis accuracy. An improved empirical mode decomposition, wavelet transform – ensemble empirical mode decomposition, is also designed which could adequately solve the problems of mode mixing and end effects. Moreover, a morphological method usually used in image processing is investigated and adopted to change the shape of the intrinsic mode functions to further reveal the faulty impulses. In order to reduce the high dimension of the extracted features and improve the computational efficiency and accuracy, a deep belief network is designed to conduct information fusion, and compared with widely adopted kernel principal component analysis. For classification, a pairwise coupling strategy is proposed and combined with sparse Bayesian extreme learning machine. The experiments conducted using the proposed approach demonstrate the effectiveness of the proposed system.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/134798