Partial Discharge Pattern Recognition of High Voltage GIS Defects by Using GWO-SVM Method

Tianbao Wu; Huan Bai; Jiayi Wang; Jianyang Huang; Yue Yu; Weiwang Wang

doi:10.1007/978-981-97-1072-0_67

Partial Discharge Pattern Recognition of High Voltage GIS Defects by Using GWO-SVM Method

Tianbao Wu
, Huan Bai
, Jiayi Wang
, Jianyang Huang
, Yue Yu
, Weiwang Wang

School of Electrical Engineering

Sichuan Shuneng Electric Power Co. Ltd. High-tech Branch
State Grid Corporation of China
Xi'an Jiaotong University

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

Abstract

This paper focuses on partial discharges (PD) pattern recognition of typical GIS defects by UHF sensor detection and intelligence fault algorithm. 4 typical PD defects, such as needle tip, air gap, particle, and suspension were simulated in the SF6 filled GIS chamber. The PD results indicated an obvious difference among the 4 PD defects. The corona discharge presented sharp discharge peaks during the 200–300°. According to the PRPD analysis, the eigenvalues of PD signals were calculated, including the skewness, the steepness, the local discharge factor, the cross-correlation coefficient, and the corrected cross-correlation coefficient etc. We employ a Grey Wolf Optimization algorithm (GWO) to optimize the parameter of kernel function in SVM algorithm. The proposed GWO-SVM method presents a better PD pattern recognition result. The predicted accuracy rate can be reached to 98.8%. This work can be used to guide GIS fault diagnosis.

Original language	English
Title of host publication	The proceedings of the 18th Annual Conference of China Electrotechnical Society - Volume VII
Editors	Qingxin Yang, Zewen Li, An Luo
Publisher	Springer Science and Business Media Deutschland GmbH
Pages	657-664
Number of pages	8
ISBN (Print)	9789819710713
DOIs	https://doi.org/10.1007/978-981-97-1072-0_67
State	Published - 2024
Event	18th Annual Conference of China Electrotechnical Society, ACCES 2023 - Nanchang, China Duration: 15 Sep 2023 → 17 Sep 2023

Publication series

Name	Lecture Notes in Electrical Engineering
Volume	1169 LNEE
ISSN (Print)	1876-1100
ISSN (Electronic)	1876-1119

Conference

Conference	18th Annual Conference of China Electrotechnical Society, ACCES 2023
Country/Territory	China
City	Nanchang
Period	15/09/23 → 17/09/23

Keywords

GIS
Grey Wolf optimization algorithm
PRPD
Partial discharge
SVM

Access to Document

10.1007/978-981-97-1072-0_67

Cite this

Wu, T., Bai, H., Wang, J., Huang, J., Yu, Y., & Wang, W. (2024). Partial Discharge Pattern Recognition of High Voltage GIS Defects by Using GWO-SVM Method. In Q. Yang, Z. Li, & A. Luo (Eds.), The proceedings of the 18th Annual Conference of China Electrotechnical Society - Volume VII (pp. 657-664). (Lecture Notes in Electrical Engineering; Vol. 1169 LNEE). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-981-97-1072-0_67

Wu, Tianbao ; Bai, Huan ; Wang, Jiayi et al. / Partial Discharge Pattern Recognition of High Voltage GIS Defects by Using GWO-SVM Method. The proceedings of the 18th Annual Conference of China Electrotechnical Society - Volume VII. editor / Qingxin Yang ; Zewen Li ; An Luo. Springer Science and Business Media Deutschland GmbH, 2024. pp. 657-664 (Lecture Notes in Electrical Engineering).

@inproceedings{8187af3a6b5143ee969a430bda79f173,

title = "Partial Discharge Pattern Recognition of High Voltage GIS Defects by Using GWO-SVM Method",

abstract = "This paper focuses on partial discharges (PD) pattern recognition of typical GIS defects by UHF sensor detection and intelligence fault algorithm. 4 typical PD defects, such as needle tip, air gap, particle, and suspension were simulated in the SF6 filled GIS chamber. The PD results indicated an obvious difference among the 4 PD defects. The corona discharge presented sharp discharge peaks during the 200–300°. According to the PRPD analysis, the eigenvalues of PD signals were calculated, including the skewness, the steepness, the local discharge factor, the cross-correlation coefficient, and the corrected cross-correlation coefficient etc. We employ a Grey Wolf Optimization algorithm (GWO) to optimize the parameter of kernel function in SVM algorithm. The proposed GWO-SVM method presents a better PD pattern recognition result. The predicted accuracy rate can be reached to 98.8\%. This work can be used to guide GIS fault diagnosis.",

keywords = "GIS, Grey Wolf optimization algorithm, PRPD, Partial discharge, SVM",

author = "Tianbao Wu and Huan Bai and Jiayi Wang and Jianyang Huang and Yue Yu and Weiwang Wang",

note = "Publisher Copyright: {\textcopyright} Beijing Paike Culture Commu. Co., Ltd. 2024.; 18th Annual Conference of China Electrotechnical Society, ACCES 2023 ; Conference date: 15-09-2023 Through 17-09-2023",

year = "2024",

doi = "10.1007/978-981-97-1072-0\_67",

language = "英语",

isbn = "9789819710713",

series = "Lecture Notes in Electrical Engineering",

publisher = "Springer Science and Business Media Deutschland GmbH",

pages = "657--664",

editor = "Qingxin Yang and Zewen Li and An Luo",

booktitle = "The proceedings of the 18th Annual Conference of China Electrotechnical Society - Volume VII",

}

Wu, T, Bai, H, Wang, J, Huang, J, Yu, Y & Wang, W 2024, Partial Discharge Pattern Recognition of High Voltage GIS Defects by Using GWO-SVM Method. in Q Yang, Z Li & A Luo (eds), The proceedings of the 18th Annual Conference of China Electrotechnical Society - Volume VII. Lecture Notes in Electrical Engineering, vol. 1169 LNEE, Springer Science and Business Media Deutschland GmbH, pp. 657-664, 18th Annual Conference of China Electrotechnical Society, ACCES 2023, Nanchang, China, 15/09/23. https://doi.org/10.1007/978-981-97-1072-0_67

Partial Discharge Pattern Recognition of High Voltage GIS Defects by Using GWO-SVM Method. / Wu, Tianbao; Bai, Huan; Wang, Jiayi et al.
The proceedings of the 18th Annual Conference of China Electrotechnical Society - Volume VII. ed. / Qingxin Yang; Zewen Li; An Luo. Springer Science and Business Media Deutschland GmbH, 2024. p. 657-664 (Lecture Notes in Electrical Engineering; Vol. 1169 LNEE).

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

TY - GEN

T1 - Partial Discharge Pattern Recognition of High Voltage GIS Defects by Using GWO-SVM Method

AU - Wu, Tianbao

AU - Bai, Huan

AU - Wang, Jiayi

AU - Huang, Jianyang

AU - Yu, Yue

AU - Wang, Weiwang

N1 - Publisher Copyright: © Beijing Paike Culture Commu. Co., Ltd. 2024.

PY - 2024

Y1 - 2024

N2 - This paper focuses on partial discharges (PD) pattern recognition of typical GIS defects by UHF sensor detection and intelligence fault algorithm. 4 typical PD defects, such as needle tip, air gap, particle, and suspension were simulated in the SF6 filled GIS chamber. The PD results indicated an obvious difference among the 4 PD defects. The corona discharge presented sharp discharge peaks during the 200–300°. According to the PRPD analysis, the eigenvalues of PD signals were calculated, including the skewness, the steepness, the local discharge factor, the cross-correlation coefficient, and the corrected cross-correlation coefficient etc. We employ a Grey Wolf Optimization algorithm (GWO) to optimize the parameter of kernel function in SVM algorithm. The proposed GWO-SVM method presents a better PD pattern recognition result. The predicted accuracy rate can be reached to 98.8%. This work can be used to guide GIS fault diagnosis.

AB - This paper focuses on partial discharges (PD) pattern recognition of typical GIS defects by UHF sensor detection and intelligence fault algorithm. 4 typical PD defects, such as needle tip, air gap, particle, and suspension were simulated in the SF6 filled GIS chamber. The PD results indicated an obvious difference among the 4 PD defects. The corona discharge presented sharp discharge peaks during the 200–300°. According to the PRPD analysis, the eigenvalues of PD signals were calculated, including the skewness, the steepness, the local discharge factor, the cross-correlation coefficient, and the corrected cross-correlation coefficient etc. We employ a Grey Wolf Optimization algorithm (GWO) to optimize the parameter of kernel function in SVM algorithm. The proposed GWO-SVM method presents a better PD pattern recognition result. The predicted accuracy rate can be reached to 98.8%. This work can be used to guide GIS fault diagnosis.

KW - GIS

KW - Grey Wolf optimization algorithm

KW - PRPD

KW - Partial discharge

KW - SVM

UR - https://www.scopus.com/pages/publications/85188686682

U2 - 10.1007/978-981-97-1072-0_67

DO - 10.1007/978-981-97-1072-0_67

M3 - 会议稿件

AN - SCOPUS:85188686682

SN - 9789819710713

T3 - Lecture Notes in Electrical Engineering

SP - 657

EP - 664

BT - The proceedings of the 18th Annual Conference of China Electrotechnical Society - Volume VII

A2 - Yang, Qingxin

A2 - Li, Zewen

A2 - Luo, An

PB - Springer Science and Business Media Deutschland GmbH

T2 - 18th Annual Conference of China Electrotechnical Society, ACCES 2023

Y2 - 15 September 2023 through 17 September 2023

ER -

Wu T, Bai H, Wang J, Huang J, Yu Y, Wang W. Partial Discharge Pattern Recognition of High Voltage GIS Defects by Using GWO-SVM Method. In Yang Q, Li Z, Luo A, editors, The proceedings of the 18th Annual Conference of China Electrotechnical Society - Volume VII. Springer Science and Business Media Deutschland GmbH. 2024. p. 657-664. (Lecture Notes in Electrical Engineering). doi: 10.1007/978-981-97-1072-0_67

Partial Discharge Pattern Recognition of High Voltage GIS Defects by Using GWO-SVM Method

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this