New Method to Identify Transformer Inrush Current Based on FFT and SVM

Abstract:

To improve transformer longitudinal differential protections reliability, this paper deeply analyzes generation mechanism and characteristic of transformer inrush current, and uses PSCAD/EMTDC software to simulate 188 kinds of transformer operation states. They are including internal fault current, inrush current and no-load closing with internal fault. On the background of those simulations, it proposes a simple and accurate method to identify inrush current based on SVM. SVM selects Gaussion Kernel, and takes three-phase differential current, fundamental, secondary harmonic and third harmonic as characteristic quantities. Many cross-validation results verify that the training SVM has high accuracy. This method can identify inrush current and internal fault current (including no-load closing with internal fault current) rapidly and accurately. It takes less time, and is easy to perform.

• Periodical: Applied Mechanics and Materials (Volumes 313-314)
• Pages: 887-890
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.313-314.887
• Online since: March 2013
• Authors: Mao Fa Gong, Guo Liang Li, Wen Hua Xia, Hong Lin Yan, Jing Wen Qu, Xiao Yu Wang
• Keywords: FFT, Inrush Current, Internal Fault Current, Support Vector Machine (SVM), Transformer Protection

References

[1] Phadke A G, T horp J S. A new computer-based flux-restrained current-differential relay for power transformer protection, IEEE Transactions on Power Apparatus and Systems, vol 102, pp.3624-3629, (1983)

DOI: 10.1109/tpas.1983.317711

[2] HUA Huangsheng, YOU Dahai, WANG Yangguang, et al. Performance Analysis and Criterion Improvement for Transformer Protection Theory Based on Transformer Equivalent Circuit, Automation of Electric Power Systems,vol 34, pp.72-76, 2010.

[3] Yabe K. Power differential method for discriminating between fault and magnetizing inrush current in transformers, IEEE Transactions on Power Delivery, vol 12, pp.1109-1118, 1997.

DOI: 10.1109/61.636909

[4] Jiao Shaohua, Liu Wanshun. A NOVEL SCHEME TO DISCRIMINATE INRUSH CURRENT AND FAULT CURRENT BASED ON INTEGRATING THE WAVEFORM, Proceedings of the Csee, vol 19, pp.35-38, 1999.

[5] DU Ling, LI Bo. A new algorithm based on symmetry principle of current waveforms, Power System Protection and Control, vol 37, pp.22-25, 2009.

[6] AN Yuan, LIU Jia-jun. A Method to Identify Inrush Current of Transformer Based on Wavelet Theory and Multiresolution Analysis, Power System Technology, vol 31, pp.21-25, 2007.

[7] LI Hai-feng, WANG Gang, LI Xiao-hua. DISTINGUISH BETWEEN INRUSH AND INTERNAL FAULT OF TRANSFORMER BASED ON ADAPTIVE WAVELET NEURAL NETWORK, Proceedings of the CSEE, vol 25, pp.144-150, 2005.

[8] Bastard P, Meunier M, Regal H. Neural-network-based algorithm for power transformer differential relays, IEE Proc., Generation, Transmission and Distribution,vol 142, pp.386-392, 1995.

DOI: 10.1049/ip-gtd:19951817

[9] Mao P L, Aggarwal R K. A novel approach to the classification of the transient phenomena in power transformer using combined wavelet transform and neural network, IEEE Trans. on Power Delivery, vol 16, pp.654-660, 2001.

DOI: 10.1109/61.956753

[10] V. Vapnik. The Nature of Statistical Learning Theory, New York: Springer Verlag, 1995.