Condition Evaluation and Fault Diagnosis of Power Transformer Based on GAN-CNN

Xu Haoran; Wang Ziyi

doi:10.23977/jeeem.2023.060302

Condition Evaluation and Fault Diagnosis of Power Transformer Based on GAN-CNN

Download as PDF

DOI: 10.23977/jeeem.2023.060302 | Downloads: 31 | Views: 599

Author(s)

Xu Haoran ¹, Wang Ziyi ²

Affiliation(s)

¹ School of Computer Science, Beijing Institute of Technology, Beijing, 102400, China
² Department of Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, 650000, China

Corresponding Author

Xu Haoran

ABSTRACT

Power transformer is one of the most important components of power system. Maintaining its stable operation is an important guarantee for the normal operation of the power system. In recent years, prognostics and health management (PHM) has been introduced into the health management of power transformers. The key information about its operation is obtained by sensors, which provides a platform for intelligent management. At present, for the fault diagnosis and condition assessment of power transformers, due to the lack of original data feature parameters, the lack of data, and the uneven classification of existing data fault types, it is easy to distort the training model. To overcome the above difficulties, this paper proposes a power transformer condition assessment and fault diagnosis method based on generative adversarial network (GAN) and convolutional neural network (CNN). Through GAN, the original data feature parameters are amplified and generate the artificial data set. The data is trained together through CNN. Finally, the validity and superiority of the proposed method are verified by the measured data and the comparative experiment.

KEYWORDS

State Assessment, Fault Diagnosis, Convolutional Neural Network, Generative Adversarial Network

CITE THIS PAPER

Xu Haoran, Wang Ziyi, Condition Evaluation and Fault Diagnosis of Power Transformer Based on GAN-CNN. Journal of Electrotechnology, Electrical Engineering and Management (2023) Vol. 6: 8-16. DOI: http://dx.doi.org/10.23977/jeeem.2023.060302.

REFERENCES

[1] Sun Jianfeng, Ge Rui, Zheng Li, Hu Chaofan. Analysis of the safe operation of the national power grid in 2010[J]. China Electric Power, 2011, 44(05):1-4.
[2] Yin JL. Research on fault diagnosis method of oil-immersed power transformers based on correlation vector machine [D]. North China University of Electric Power, 2013.
[3] Wang Shouxiang, Ge Leijiao, Zhang Qi, Zhuang Jian, Jiang Ling. Analysis of factors influencing distributed energy acceptance capacity of distribution networks[J]. Power supply,2016,33(04):2-7+63.
[4] Xie P. Research on the health management system of oil-immersed power transformers based on data and models[D]. South China University of Technology, 2020.
[5] Jardine A K S, Lin D, Banjevic D . A review on machinery diagnostics and prognostics implementing condition-based maintenance[J]. Mechanical Systems & Signal Processing, 2006, 20(7):1483-1510.
[6] Tsui K L, Chen N, Zhou Q, et al. Prognostics and Health Management: A Review on Data-Driven Approaches[J]. Mathematical Problems in Engineering,2015,(2015-5-19), 2015, 2015(PT.8):1-17.
[7] Xu Jing, Wang Jing, Gao Feng, et al. A review of the research on condition maintenance technology of power equipment[J]. Power Grid Technology, 2000(08): 48-52.
[8] Zhang Han, Liu Weidong, Pan Zhimin, Li Juan. Health condition assessment of transformers based on adaptive probabilistic neural networks[J]. High Voltage Electronics,2022,58(02):103-110.
[9] Dong M, Meng Yy, Xu Changhang, Yan Zhang. A fault diagnosis model for large power transformers based on support vector machine and dissolved gas analysis in oil[J]. Chinese Journal of Electrical Engineering,2003(07):88-92.
[10] Yong Mingchao, Lu Man, Zhou Zhong, Mu Jiqing, Mao Lina. Research on fault diagnosis method of power transformer based on plain Bayesian algorithm[J]. Electrical Applications,2017,36(14):32-35.
[11] Gao W.S., Qian Zheng, Yan Zhang. Fault diagnosis method of power transformer based on decision tree neural network model[J]. Journal of Xi'an Jiaotong University,1999(06):14-19.
[12] Li Kunpeng. Deep learning-based fault diagnosis method for oil-immersed transformers[D]. North China University of Electric Power, 2021.
[13] Sun Jingchao, Kong Maiying, Pal Subhadip (22 June 2021). "The Modified-Half-Normal distribution: Properties and an efficient sampling scheme". Communications in Statistics - Theory and Methods: 1–23. ISSN 0361-0926. S2CID 237919587.
[14] Dimitrova DS, Kaishev VK, Tan S (2020). "Computing the Kolmogorov–Smirnov Distribution when the Underlying cdf is Purely Discrete, Mixed or Continuous". Journal of Statistical Software. 95 (10): 1–42.

Subscription

E-Mail Alert

Downloads:	2068
Visits:	97381

Condition Evaluation and Fault Diagnosis of Power Transformer Based on GAN-CNN

Author(s)

Affiliation(s)

Corresponding Author

ABSTRACT

KEYWORDS

CITE THIS PAPER

REFERENCES

RESOURCES

JOIN US

PUBLICATION SERVICES

CONTACT US