The research of sensor fault diagnosis based on genetic algorithm and one-against-one support vector machine

Lishuang Xu; Tao Cai; Fang Deng; Xin Liu

doi:10.1109/ICICIP.2011.6008360

The research of sensor fault diagnosis based on genetic algorithm and one-against-one support vector machine

Lishuang Xu^*, Tao Cai, Fang Deng, Xin Liu

^*Corresponding author for this work

Beijing Institute of Technology

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

2 Citations (Scopus)

Abstract

Fault diagnosis based on the wavelet packet decomposition, one-against-one support vector machine (SVM) and genetic algorithm (GA) is proposed in order to realize the real-time sensor fault diagnosis accurately. The input feature vectors of one-against-one SVM are produced by wavelet packet decomposition of the sensor output signal. GA is used to obtain optimal parameters of one-against-one SVM network model automatically, which can enhance the training speed and performance. The experiments of photoelectric encoder fault diagnosis show that the combination of these methods makes SVM own a better recognition rate and overall performance, which can improve the accuracy and time efficiency of fault diagnosis.

Original language	English
Title of host publication	Proceedings of the 2nd International Conference on Intelligent Control and Information Processing, ICICIP 2011
Pages	808-812
Number of pages	5
Edition	PART 2
DOIs	https://doi.org/10.1109/ICICIP.2011.6008360
Publication status	Published - 2011
Event	2nd International Conference on Intelligent Control and Information Processing, ICICIP 2011 - Harbin, China Duration: 25 Jul 2011 → 28 Jul 2011

Publication series

Name	Proceedings of the 2nd International Conference on Intelligent Control and Information Processing, ICICIP 2011
Number	PART 2

Conference

Conference	2nd International Conference on Intelligent Control and Information Processing, ICICIP 2011
Country/Territory	China
City	Harbin
Period	25/07/11 → 28/07/11

Access to Document

10.1109/ICICIP.2011.6008360

Cite this

Xu, L., Cai, T., Deng, F., & Liu, X. (2011). The research of sensor fault diagnosis based on genetic algorithm and one-against-one support vector machine. In Proceedings of the 2nd International Conference on Intelligent Control and Information Processing, ICICIP 2011 (PART 2 ed., pp. 808-812). Article 6008360 (Proceedings of the 2nd International Conference on Intelligent Control and Information Processing, ICICIP 2011; No. PART 2). https://doi.org/10.1109/ICICIP.2011.6008360

Xu, Lishuang ; Cai, Tao ; Deng, Fang et al. / The research of sensor fault diagnosis based on genetic algorithm and one-against-one support vector machine. Proceedings of the 2nd International Conference on Intelligent Control and Information Processing, ICICIP 2011. PART 2. ed. 2011. pp. 808-812 (Proceedings of the 2nd International Conference on Intelligent Control and Information Processing, ICICIP 2011; PART 2).

@inproceedings{a2819f5e4e4b4b0cb6ac7eacb47b8794,

title = "The research of sensor fault diagnosis based on genetic algorithm and one-against-one support vector machine",

abstract = "Fault diagnosis based on the wavelet packet decomposition, one-against-one support vector machine (SVM) and genetic algorithm (GA) is proposed in order to realize the real-time sensor fault diagnosis accurately. The input feature vectors of one-against-one SVM are produced by wavelet packet decomposition of the sensor output signal. GA is used to obtain optimal parameters of one-against-one SVM network model automatically, which can enhance the training speed and performance. The experiments of photoelectric encoder fault diagnosis show that the combination of these methods makes SVM own a better recognition rate and overall performance, which can improve the accuracy and time efficiency of fault diagnosis.",

author = "Lishuang Xu and Tao Cai and Fang Deng and Xin Liu",

year = "2011",

doi = "10.1109/ICICIP.2011.6008360",

language = "English",

isbn = "9781457708145",

series = "Proceedings of the 2nd International Conference on Intelligent Control and Information Processing, ICICIP 2011",

number = "PART 2",

pages = "808--812",

booktitle = "Proceedings of the 2nd International Conference on Intelligent Control and Information Processing, ICICIP 2011",

edition = "PART 2",

note = "2nd International Conference on Intelligent Control and Information Processing, ICICIP 2011 ; Conference date: 25-07-2011 Through 28-07-2011",

}

Xu, L, Cai, T , Deng, F & Liu, X 2011, The research of sensor fault diagnosis based on genetic algorithm and one-against-one support vector machine. in Proceedings of the 2nd International Conference on Intelligent Control and Information Processing, ICICIP 2011. PART 2 edn, 6008360, Proceedings of the 2nd International Conference on Intelligent Control and Information Processing, ICICIP 2011, no. PART 2, pp. 808-812, 2nd International Conference on Intelligent Control and Information Processing, ICICIP 2011, Harbin, China, 25/07/11. https://doi.org/10.1109/ICICIP.2011.6008360

The research of sensor fault diagnosis based on genetic algorithm and one-against-one support vector machine. / Xu, Lishuang; Cai, Tao ; Deng, Fang et al.
Proceedings of the 2nd International Conference on Intelligent Control and Information Processing, ICICIP 2011. PART 2. ed. 2011. p. 808-812 6008360 (Proceedings of the 2nd International Conference on Intelligent Control and Information Processing, ICICIP 2011; No. PART 2).

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

TY - GEN

T1 - The research of sensor fault diagnosis based on genetic algorithm and one-against-one support vector machine

AU - Xu, Lishuang

AU - Cai, Tao

AU - Deng, Fang

AU - Liu, Xin

PY - 2011

Y1 - 2011

N2 - Fault diagnosis based on the wavelet packet decomposition, one-against-one support vector machine (SVM) and genetic algorithm (GA) is proposed in order to realize the real-time sensor fault diagnosis accurately. The input feature vectors of one-against-one SVM are produced by wavelet packet decomposition of the sensor output signal. GA is used to obtain optimal parameters of one-against-one SVM network model automatically, which can enhance the training speed and performance. The experiments of photoelectric encoder fault diagnosis show that the combination of these methods makes SVM own a better recognition rate and overall performance, which can improve the accuracy and time efficiency of fault diagnosis.

AB - Fault diagnosis based on the wavelet packet decomposition, one-against-one support vector machine (SVM) and genetic algorithm (GA) is proposed in order to realize the real-time sensor fault diagnosis accurately. The input feature vectors of one-against-one SVM are produced by wavelet packet decomposition of the sensor output signal. GA is used to obtain optimal parameters of one-against-one SVM network model automatically, which can enhance the training speed and performance. The experiments of photoelectric encoder fault diagnosis show that the combination of these methods makes SVM own a better recognition rate and overall performance, which can improve the accuracy and time efficiency of fault diagnosis.

UR - http://www.scopus.com/inward/record.url?scp=80053201507&partnerID=8YFLogxK

U2 - 10.1109/ICICIP.2011.6008360

DO - 10.1109/ICICIP.2011.6008360

M3 - Conference contribution

AN - SCOPUS:80053201507

SN - 9781457708145

T3 - Proceedings of the 2nd International Conference on Intelligent Control and Information Processing, ICICIP 2011

SP - 808

EP - 812

BT - Proceedings of the 2nd International Conference on Intelligent Control and Information Processing, ICICIP 2011

T2 - 2nd International Conference on Intelligent Control and Information Processing, ICICIP 2011

Y2 - 25 July 2011 through 28 July 2011

ER -

Xu L, Cai T , Deng F , Liu X. The research of sensor fault diagnosis based on genetic algorithm and one-against-one support vector machine. In Proceedings of the 2nd International Conference on Intelligent Control and Information Processing, ICICIP 2011. PART 2 ed. 2011. p. 808-812. 6008360. (Proceedings of the 2nd International Conference on Intelligent Control and Information Processing, ICICIP 2011; PART 2). doi: 10.1109/ICICIP.2011.6008360

The research of sensor fault diagnosis based on genetic algorithm and one-against-one support vector machine

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this