Prediction Research of Transformer Fault Based on Regular Extreme Learning Machine

Abstract:

To predict the concentration of dissolved gas in transformer oil, and then realize the transformer latent fault prediction, can effectively prevent unnecessary loss caused by the transformer faults .In order to improve the transformer fault prediction ability,this paper proposes a new transformer fault prediction model--Regular Extreme Learning Machine (RELM) prediction model。RELM algorithm introduce structure risk minimization principle on the basis of traditional ELM, using the balance factor to weigh the empirical risk and the risk of structure size, further enhance the generalization performance of ELM. Verified by examples, the proposed prediction model based on the RELM in this paper achieve better generalization performance and prediction accuracy in the forecast of gases concentration dissolved in transformer oil.

• Periodical: Advanced Materials Research (Volumes 1049-1050)
• Pages: 1205-1209
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.1049-1050.1205
• Online since: October 2014
• Authors: Xue Zhen Chen, Yong Li Zhu, Fei Pei
• Keywords: Balance Factor, Regular Extreme Learning Machine, Structural Risk Minimization, Transformer Fault Prediction

References

[1] W. Zhao, Y. Zhu, X. Zhang. Proceedings of the CSEE, 2008, 28(25), p.14.

[2] Yaoye Zhu. Prediction research of transformer fault based on oil dissolved gas. Beijing North China Electric Power University, (2013).

[3] Y. Zhang and B. Zhang. International Conference on Computer Engineering and Technology 2010, p.513.

[4] Hanbo Zheng. Research on condition assessment and fault diagnosis method of the power transformer. Chongqing University, (2012).

[5] Qinghua Wu. Diagnosis and prediction research of power transformer fault based on the LS - SVM. Xihua University, (2010).

[6] Tingfang Yang, Pei Liu, Zhe Li, etc. Proceedings of the CSEE, 2008, 28 (31), p.108.

[7] Jianxin Lian. Transformer fault diagnosis and forecasting application research on the basis of RVM and hybrid optimization algorithm. Taiyuan university of technology, (2012).

[8] Guangbin Huang, Qinyu Zhu and Chee-Kheong Siew.  Proceedings of International Joint Conference on Neural Networks (IJCNN2004), Budapest, Hungary, 2004, p.985.

[9] Wanyu Deng, Qinghua Zheng, Lin Chen, etc. Chinese Journal of Computers, 2010(2), p.279.

[10] Chen Xia, Yangdong Zhao, Xu Yan. IEEE Transactions on Power Systems, 2012, p. (2055).

[11] T. Cheng, S. Zhou, S. Li, etc. Electric Power Science and Engineering, 2013, 29 (4), p.24.

[12] H. uaxian Pan, G. Cheng, L. Cai. Computer Engineering and Science, 2010, 32 (2), p.131.