Misalignment characteristic analysis based on Kernel principal component analysis

Huimin Li; Xiaojian Ma; Yanbing Wang; Lawrence A. Bergman

doi:10.1109/CSO.2011.167

Misalignment characteristic analysis based on Kernel principal component analysis

Huimin Li, Xiaojian Ma, Yanbing Wang, Lawrence A. Bergman

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

A new method based kernel principal component analysis (KPCA) is used to extract interesting misalignment features from a dynamical system. In this method, the projections (PCs) of the image of a test point with misalignment onto the nonlinear principal components in normal condition in featured space F are computed to represent the misalignment characteristics. It is shown in this work that the exploitation of the projections combination can improve the detection results. Even the varying trends of misalignment fault could be identified by use of this detection method. The method is illustrated on an experimental example of an auxiliary magnetic bearing rotor system.

Original language	English (US)
Title of host publication	Proceedings - 4th International Joint Conference on Computational Sciences and Optimization, CSO 2011
Pages	293-296
Number of pages	4
DOIs	https://doi.org/10.1109/CSO.2011.167
State	Published - 2011
Externally published	Yes
Event	4th International Joint Conference on Computational Sciences and Optimization, CSO 2011 - Kunming, Lijiang, Yunnan, China Duration: Apr 15 2011 → Apr 19 2011

Publication series

Name	Proceedings - 4th International Joint Conference on Computational Sciences and Optimization, CSO 2011

Other

Other	4th International Joint Conference on Computational Sciences and Optimization, CSO 2011
Country/Territory	China
City	Kunming, Lijiang, Yunnan
Period	4/15/11 → 4/19/11

Keywords

Angular misalignment
Fault diagnose
Kernel PCA

ASJC Scopus subject areas

Computer Science (miscellaneous)
Control and Optimization

Online availability

10.1109/CSO.2011.167

Library availability

Discover UIUC Full Text

Cite this

Li, H., Ma, X., Wang, Y., & Bergman, L. A. (2011). Misalignment characteristic analysis based on Kernel principal component analysis. In Proceedings - 4th International Joint Conference on Computational Sciences and Optimization, CSO 2011 (pp. 293-296). Article 5957664 (Proceedings - 4th International Joint Conference on Computational Sciences and Optimization, CSO 2011). https://doi.org/10.1109/CSO.2011.167

Misalignment characteristic analysis based on Kernel principal component analysis. / Li, Huimin; Ma, Xiaojian; Wang, Yanbing et al.
Proceedings - 4th International Joint Conference on Computational Sciences and Optimization, CSO 2011. 2011. p. 293-296 5957664 (Proceedings - 4th International Joint Conference on Computational Sciences and Optimization, CSO 2011).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Li, H, Ma, X, Wang, Y & Bergman, LA 2011, Misalignment characteristic analysis based on Kernel principal component analysis. in Proceedings - 4th International Joint Conference on Computational Sciences and Optimization, CSO 2011., 5957664, Proceedings - 4th International Joint Conference on Computational Sciences and Optimization, CSO 2011, pp. 293-296, 4th International Joint Conference on Computational Sciences and Optimization, CSO 2011, Kunming, Lijiang, Yunnan, China, 4/15/11. https://doi.org/10.1109/CSO.2011.167

Li H, Ma X, Wang Y, Bergman LA. Misalignment characteristic analysis based on Kernel principal component analysis. In Proceedings - 4th International Joint Conference on Computational Sciences and Optimization, CSO 2011. 2011. p. 293-296. 5957664. (Proceedings - 4th International Joint Conference on Computational Sciences and Optimization, CSO 2011). doi: 10.1109/CSO.2011.167

@inproceedings{66213b5b4f6047c883e7f61944912146,

title = "Misalignment characteristic analysis based on Kernel principal component analysis",

abstract = "A new method based kernel principal component analysis (KPCA) is used to extract interesting misalignment features from a dynamical system. In this method, the projections (PCs) of the image of a test point with misalignment onto the nonlinear principal components in normal condition in featured space F are computed to represent the misalignment characteristics. It is shown in this work that the exploitation of the projections combination can improve the detection results. Even the varying trends of misalignment fault could be identified by use of this detection method. The method is illustrated on an experimental example of an auxiliary magnetic bearing rotor system.",

keywords = "Angular misalignment, Fault diagnose, Kernel PCA",

author = "Huimin Li and Xiaojian Ma and Yanbing Wang and Bergman, {Lawrence A.}",

year = "2011",

doi = "10.1109/CSO.2011.167",

language = "English (US)",

isbn = "9780769543352",

series = "Proceedings - 4th International Joint Conference on Computational Sciences and Optimization, CSO 2011",

pages = "293--296",

booktitle = "Proceedings - 4th International Joint Conference on Computational Sciences and Optimization, CSO 2011",

note = "4th International Joint Conference on Computational Sciences and Optimization, CSO 2011 ; Conference date: 15-04-2011 Through 19-04-2011",

}

TY - GEN

T1 - Misalignment characteristic analysis based on Kernel principal component analysis

AU - Li, Huimin

AU - Ma, Xiaojian

AU - Wang, Yanbing

AU - Bergman, Lawrence A.

PY - 2011

Y1 - 2011

N2 - A new method based kernel principal component analysis (KPCA) is used to extract interesting misalignment features from a dynamical system. In this method, the projections (PCs) of the image of a test point with misalignment onto the nonlinear principal components in normal condition in featured space F are computed to represent the misalignment characteristics. It is shown in this work that the exploitation of the projections combination can improve the detection results. Even the varying trends of misalignment fault could be identified by use of this detection method. The method is illustrated on an experimental example of an auxiliary magnetic bearing rotor system.

AB - A new method based kernel principal component analysis (KPCA) is used to extract interesting misalignment features from a dynamical system. In this method, the projections (PCs) of the image of a test point with misalignment onto the nonlinear principal components in normal condition in featured space F are computed to represent the misalignment characteristics. It is shown in this work that the exploitation of the projections combination can improve the detection results. Even the varying trends of misalignment fault could be identified by use of this detection method. The method is illustrated on an experimental example of an auxiliary magnetic bearing rotor system.

KW - Angular misalignment

KW - Fault diagnose

KW - Kernel PCA

UR - http://www.scopus.com/inward/record.url?scp=80051979803&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=80051979803&partnerID=8YFLogxK

U2 - 10.1109/CSO.2011.167

DO - 10.1109/CSO.2011.167

M3 - Conference contribution

AN - SCOPUS:80051979803

SN - 9780769543352

T3 - Proceedings - 4th International Joint Conference on Computational Sciences and Optimization, CSO 2011

SP - 293

EP - 296

BT - Proceedings - 4th International Joint Conference on Computational Sciences and Optimization, CSO 2011

T2 - 4th International Joint Conference on Computational Sciences and Optimization, CSO 2011

Y2 - 15 April 2011 through 19 April 2011

ER -

Misalignment characteristic analysis based on Kernel principal component analysis

Abstract

Publication series

Other

Keywords

ASJC Scopus subject areas

Online availability

Library availability

Related links

Fingerprint

Cite this