Fault Diagnostics of Oil-immersed Power Transformer via SMOTE and GWO-SVM

Xinghui Li; Yuan Li; Yaoyu Xu; Rui Li; Guanjun Zhang

doi:10.1109/AEEES54426.2022.9759595

Fault Diagnostics of Oil-immersed Power Transformer via SMOTE and GWO-SVM

Xinghui Li
, Yuan Li
, Yaoyu Xu
, Rui Li
, Guanjun Zhang

School of Electrical Engineering

Xi'an Jiaotong University

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

7 Scopus citations

Abstract

Dissolved gas analysis (DGA) is an effective method for fault detection of power transformer. Transformer fault data are typically unbalanced, because the probabilities of different faults are different. This imbalance will cause a decrease in the recognition rate of minority class. In this paper, synthetic minority over-sampling technique (SMOTE) is used to balance the unbalanced fault samples set of power transformer, then Grey Wolf Optimization (GWO) is used to optimize the parameter of support vector machine (SVM). Incorporating above two procedures, the transformer fault diagnosis model is established. The case analysis shows that compared with the original model, the recognition rate of the model established is significantly improved in minority faults, and the overall recognition rate is increased by 7.5%, reaching 86.67%.

Original language	English
Title of host publication	2022 4th Asia Energy and Electrical Engineering Symposium, AEEES 2022
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	935-939
Number of pages	5
ISBN (Electronic)	9781665479141
DOIs	https://doi.org/10.1109/AEEES54426.2022.9759595
State	Published - 2022
Event	4th Asia Energy and Electrical Engineering Symposium, AEEES 2022 - Chengdu, China Duration: 25 Mar 2022 → 28 Mar 2022

Publication series

Name	2022 4th Asia Energy and Electrical Engineering Symposium, AEEES 2022

Conference

Conference	4th Asia Energy and Electrical Engineering Symposium, AEEES 2022
Country/Territory	China
City	Chengdu
Period	25/03/22 → 28/03/22

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 7 Affordable and Clean Energy

Keywords

DGA in transformer
GWO-SVM
SMOTE
fault diagnosis
unbalance samples

Access to Document

10.1109/AEEES54426.2022.9759595

Cite this

Li, X., Li, Y., Xu, Y., Li, R., & Zhang, G. (2022). Fault Diagnostics of Oil-immersed Power Transformer via SMOTE and GWO-SVM. In 2022 4th Asia Energy and Electrical Engineering Symposium, AEEES 2022 (pp. 935-939). (2022 4th Asia Energy and Electrical Engineering Symposium, AEEES 2022). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/AEEES54426.2022.9759595

@inproceedings{9707ac62f69048d3b9e325c7b067600c,

title = "Fault Diagnostics of Oil-immersed Power Transformer via SMOTE and GWO-SVM",

abstract = "Dissolved gas analysis (DGA) is an effective method for fault detection of power transformer. Transformer fault data are typically unbalanced, because the probabilities of different faults are different. This imbalance will cause a decrease in the recognition rate of minority class. In this paper, synthetic minority over-sampling technique (SMOTE) is used to balance the unbalanced fault samples set of power transformer, then Grey Wolf Optimization (GWO) is used to optimize the parameter of support vector machine (SVM). Incorporating above two procedures, the transformer fault diagnosis model is established. The case analysis shows that compared with the original model, the recognition rate of the model established is significantly improved in minority faults, and the overall recognition rate is increased by 7.5\%, reaching 86.67\%.",

keywords = "DGA in transformer, GWO-SVM, SMOTE, fault diagnosis, unbalance samples",

author = "Xinghui Li and Yuan Li and Yaoyu Xu and Rui Li and Guanjun Zhang",

note = "Publisher Copyright: {\textcopyright} 2022 IEEE.; 4th Asia Energy and Electrical Engineering Symposium, AEEES 2022 ; Conference date: 25-03-2022 Through 28-03-2022",

year = "2022",

doi = "10.1109/AEEES54426.2022.9759595",

language = "英语",

series = "2022 4th Asia Energy and Electrical Engineering Symposium, AEEES 2022",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "935--939",

booktitle = "2022 4th Asia Energy and Electrical Engineering Symposium, AEEES 2022",

}

Li, X, Li, Y, Xu, Y, Li, R & Zhang, G 2022, Fault Diagnostics of Oil-immersed Power Transformer via SMOTE and GWO-SVM. in 2022 4th Asia Energy and Electrical Engineering Symposium, AEEES 2022. 2022 4th Asia Energy and Electrical Engineering Symposium, AEEES 2022, Institute of Electrical and Electronics Engineers Inc., pp. 935-939, 4th Asia Energy and Electrical Engineering Symposium, AEEES 2022, Chengdu, China, 25/03/22. https://doi.org/10.1109/AEEES54426.2022.9759595

Fault Diagnostics of Oil-immersed Power Transformer via SMOTE and GWO-SVM. / Li, Xinghui; Li, Yuan; Xu, Yaoyu et al.
2022 4th Asia Energy and Electrical Engineering Symposium, AEEES 2022. Institute of Electrical and Electronics Engineers Inc., 2022. p. 935-939 (2022 4th Asia Energy and Electrical Engineering Symposium, AEEES 2022).

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

TY - GEN

T1 - Fault Diagnostics of Oil-immersed Power Transformer via SMOTE and GWO-SVM

AU - Li, Xinghui

AU - Li, Yuan

AU - Xu, Yaoyu

AU - Li, Rui

AU - Zhang, Guanjun

PY - 2022

Y1 - 2022

N2 - Dissolved gas analysis (DGA) is an effective method for fault detection of power transformer. Transformer fault data are typically unbalanced, because the probabilities of different faults are different. This imbalance will cause a decrease in the recognition rate of minority class. In this paper, synthetic minority over-sampling technique (SMOTE) is used to balance the unbalanced fault samples set of power transformer, then Grey Wolf Optimization (GWO) is used to optimize the parameter of support vector machine (SVM). Incorporating above two procedures, the transformer fault diagnosis model is established. The case analysis shows that compared with the original model, the recognition rate of the model established is significantly improved in minority faults, and the overall recognition rate is increased by 7.5%, reaching 86.67%.

AB - Dissolved gas analysis (DGA) is an effective method for fault detection of power transformer. Transformer fault data are typically unbalanced, because the probabilities of different faults are different. This imbalance will cause a decrease in the recognition rate of minority class. In this paper, synthetic minority over-sampling technique (SMOTE) is used to balance the unbalanced fault samples set of power transformer, then Grey Wolf Optimization (GWO) is used to optimize the parameter of support vector machine (SVM). Incorporating above two procedures, the transformer fault diagnosis model is established. The case analysis shows that compared with the original model, the recognition rate of the model established is significantly improved in minority faults, and the overall recognition rate is increased by 7.5%, reaching 86.67%.

KW - DGA in transformer

KW - GWO-SVM

KW - SMOTE

KW - fault diagnosis

KW - unbalance samples

UR - https://www.scopus.com/pages/publications/85129575635

U2 - 10.1109/AEEES54426.2022.9759595

DO - 10.1109/AEEES54426.2022.9759595

M3 - 会议稿件

AN - SCOPUS:85129575635

T3 - 2022 4th Asia Energy and Electrical Engineering Symposium, AEEES 2022

SP - 935

EP - 939

BT - 2022 4th Asia Energy and Electrical Engineering Symposium, AEEES 2022

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 4th Asia Energy and Electrical Engineering Symposium, AEEES 2022

Y2 - 25 March 2022 through 28 March 2022

ER -

Fault Diagnostics of Oil-immersed Power Transformer via SMOTE and GWO-SVM

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this