Classification of partial discharge events in GILBS using discrete wavelet transform and probabilistic neural networks

Ming Shou Su; Jiann-Fuh Chen; Chien Yi Chen; Cheng-Chi Tai; Yu Hsun Lin

doi:10.1109/CMD.2012.6416314

Classification of partial discharge events in GILBS using discrete wavelet transform and probabilistic neural networks

Ming Shou Su, Jiann-Fuh Chen, Chien Yi Chen, Cheng-Chi Tai, Yu Hsun Lin

Department of Electrical Engineering

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

Abstract

This paper proposes an approach to determining classification of partial discharge (PD) events in Gas Insulated Load Break Switches (GILBS). Discrete wavelet transform (DWT) is employed to suppress noises of measured signals by the high-frequency current transformer (HFCT). Three kinds of different defects are designed and placed inside three GILBS individually. For accurately determination of the different defect, feature extraction and statistics analysis of the measured signals are used in the proposed method. Finally, experimental results validate that the proposed approach can effectively discriminate the PD events in GILBS.

Original language	English
Title of host publication	Proceedings of 2012 IEEE International Conference on Condition Monitoring and Diagnosis, CMD 2012
Pages	963-966
Number of pages	4
DOIs	https://doi.org/10.1109/CMD.2012.6416314
Publication status	Published - 2012 Dec 1
Event	2012 IEEE International Conference on Condition Monitoring and Diagnosis, CMD 2012 - Bali, Indonesia Duration: 2012 Sept 23 → 2012 Sept 27

Publication series

Name	Proceedings of 2012 IEEE International Conference on Condition Monitoring and Diagnosis, CMD 2012

Other

Other	2012 IEEE International Conference on Condition Monitoring and Diagnosis, CMD 2012
Country/Territory	Indonesia
City	Bali
Period	12-09-23 → 12-09-27

All Science Journal Classification (ASJC) codes

Safety, Risk, Reliability and Quality

Access to Document

10.1109/CMD.2012.6416314

Cite this

Su, M. S., Chen, J.-F., Chen, C. Y., Tai, C.-C., & Lin, Y. H. (2012). Classification of partial discharge events in GILBS using discrete wavelet transform and probabilistic neural networks. In Proceedings of 2012 IEEE International Conference on Condition Monitoring and Diagnosis, CMD 2012 (pp. 963-966). Article 6416314 (Proceedings of 2012 IEEE International Conference on Condition Monitoring and Diagnosis, CMD 2012). https://doi.org/10.1109/CMD.2012.6416314

Su, Ming Shou ; Chen, Jiann-Fuh ; Chen, Chien Yi et al. / Classification of partial discharge events in GILBS using discrete wavelet transform and probabilistic neural networks. Proceedings of 2012 IEEE International Conference on Condition Monitoring and Diagnosis, CMD 2012. 2012. pp. 963-966 (Proceedings of 2012 IEEE International Conference on Condition Monitoring and Diagnosis, CMD 2012).

@inproceedings{e49b583054934d98b8f2dc3b65a50335,

title = "Classification of partial discharge events in GILBS using discrete wavelet transform and probabilistic neural networks",

abstract = "This paper proposes an approach to determining classification of partial discharge (PD) events in Gas Insulated Load Break Switches (GILBS). Discrete wavelet transform (DWT) is employed to suppress noises of measured signals by the high-frequency current transformer (HFCT). Three kinds of different defects are designed and placed inside three GILBS individually. For accurately determination of the different defect, feature extraction and statistics analysis of the measured signals are used in the proposed method. Finally, experimental results validate that the proposed approach can effectively discriminate the PD events in GILBS.",

author = "Su, {Ming Shou} and Jiann-Fuh Chen and Chen, {Chien Yi} and Cheng-Chi Tai and Lin, {Yu Hsun}",

year = "2012",

month = dec,

day = "1",

doi = "10.1109/CMD.2012.6416314",

language = "English",

isbn = "9781467310208",

series = "Proceedings of 2012 IEEE International Conference on Condition Monitoring and Diagnosis, CMD 2012",

pages = "963--966",

booktitle = "Proceedings of 2012 IEEE International Conference on Condition Monitoring and Diagnosis, CMD 2012",

note = "2012 IEEE International Conference on Condition Monitoring and Diagnosis, CMD 2012 ; Conference date: 23-09-2012 Through 27-09-2012",

}

Su, MS, Chen, J-F, Chen, CY, Tai, C-C & Lin, YH 2012, Classification of partial discharge events in GILBS using discrete wavelet transform and probabilistic neural networks. in Proceedings of 2012 IEEE International Conference on Condition Monitoring and Diagnosis, CMD 2012., 6416314, Proceedings of 2012 IEEE International Conference on Condition Monitoring and Diagnosis, CMD 2012, pp. 963-966, 2012 IEEE International Conference on Condition Monitoring and Diagnosis, CMD 2012, Bali, Indonesia, 12-09-23. https://doi.org/10.1109/CMD.2012.6416314

Classification of partial discharge events in GILBS using discrete wavelet transform and probabilistic neural networks. / Su, Ming Shou; Chen, Jiann-Fuh; Chen, Chien Yi et al.
Proceedings of 2012 IEEE International Conference on Condition Monitoring and Diagnosis, CMD 2012. 2012. p. 963-966 6416314 (Proceedings of 2012 IEEE International Conference on Condition Monitoring and Diagnosis, CMD 2012).

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

TY - GEN

T1 - Classification of partial discharge events in GILBS using discrete wavelet transform and probabilistic neural networks

AU - Su, Ming Shou

AU - Chen, Jiann-Fuh

AU - Chen, Chien Yi

AU - Tai, Cheng-Chi

AU - Lin, Yu Hsun

PY - 2012/12/1

Y1 - 2012/12/1

N2 - This paper proposes an approach to determining classification of partial discharge (PD) events in Gas Insulated Load Break Switches (GILBS). Discrete wavelet transform (DWT) is employed to suppress noises of measured signals by the high-frequency current transformer (HFCT). Three kinds of different defects are designed and placed inside three GILBS individually. For accurately determination of the different defect, feature extraction and statistics analysis of the measured signals are used in the proposed method. Finally, experimental results validate that the proposed approach can effectively discriminate the PD events in GILBS.

AB - This paper proposes an approach to determining classification of partial discharge (PD) events in Gas Insulated Load Break Switches (GILBS). Discrete wavelet transform (DWT) is employed to suppress noises of measured signals by the high-frequency current transformer (HFCT). Three kinds of different defects are designed and placed inside three GILBS individually. For accurately determination of the different defect, feature extraction and statistics analysis of the measured signals are used in the proposed method. Finally, experimental results validate that the proposed approach can effectively discriminate the PD events in GILBS.

UR - http://www.scopus.com/inward/record.url?scp=84874235027&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84874235027&partnerID=8YFLogxK

U2 - 10.1109/CMD.2012.6416314

DO - 10.1109/CMD.2012.6416314

M3 - Conference contribution

AN - SCOPUS:84874235027

SN - 9781467310208

T3 - Proceedings of 2012 IEEE International Conference on Condition Monitoring and Diagnosis, CMD 2012

SP - 963

EP - 966

BT - Proceedings of 2012 IEEE International Conference on Condition Monitoring and Diagnosis, CMD 2012

T2 - 2012 IEEE International Conference on Condition Monitoring and Diagnosis, CMD 2012

Y2 - 23 September 2012 through 27 September 2012

ER -

Su MS, Chen JF, Chen CY, Tai CC, Lin YH. Classification of partial discharge events in GILBS using discrete wavelet transform and probabilistic neural networks. In Proceedings of 2012 IEEE International Conference on Condition Monitoring and Diagnosis, CMD 2012. 2012. p. 963-966. 6416314. (Proceedings of 2012 IEEE International Conference on Condition Monitoring and Diagnosis, CMD 2012). doi: 10.1109/CMD.2012.6416314

Classification of partial discharge events in GILBS using discrete wavelet transform and probabilistic neural networks

Abstract

Publication series

Other

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this