Classification of Transient Phenomena in Power Transformers Based on a Wavelet-ANN Approach

This paper presents an efficient wavelet and neural network (WNN) based approach for distinguishing magnetizing inrush currents from internal fault currents in three phase power transformers. The wavelet transform is applied first to decompose the current signals of the power transformer into a series of detailed wavelet components. The values of the detailed coefficients obtained can discriminate between an internal fault and magnetizing inrush currents in power transformers. The detailed coefficients are further used to train an Artificial Neural Network (ANN). The trained ANN clearly distinguishes an internal fault current from magnetizing inrush current. The simulation results obtained show that the proposed approach is more reliable and accurate. It provides a high operating sensitivity for internal faults and remains stable for inrush currents of the power transformers. KeywordsPower Transformer, Differential Protection, Wavelet Transform, Artificial Neural Network.

[1]  A. Wiszniewski,et al.  A multi-criteria differential transformer relay based on fuzzy logic , 1995 .

[2]  M. S. Sachdev,et al.  Online identification of magnetizing inrush and internal faults in three-phase transformers , 1992 .

[3]  A.G. Phadke,et al.  A Microprocessor Based Three-Phase Transformer Differential Relay , 1982, IEEE Transactions on Power Apparatus and Systems.

[4]  M. R. Zaman,et al.  Artificial neural network based protection of power transformers , 1998 .

[5]  R. K. Aggarwal,et al.  A Novel Approach to the Classification of the Transient Phenomena in Power Transformers Using Combined Wavelet Transform and Neural Network , 2001, IEEE Power Engineering Review.

[6]  Okan Ozgonenel.  Wavelet based ANN Approach for Transformer Protection , 2008 .

[7]  Sanguthevar Rajasekaran,et al.  Neural networks, fuzzy logic, and genetic algorithms : synthesis and applications , 2003 .

[8]  A. Ebenezer Jeyakumar,et al.  Wavelet and ANN Based Relaying for Power Transformer Protection , 2007 .

[9]  B. Jeyasurya,et al.  A state-of-the-art review of transformer protection algorithms , 1988 .

[10]  Anant Oonsivilai,et al.  Probabilistic neural network classification for model β-Glucan suspensions , 2007 .

[11]  J. Faiz,et al.  A novel wavelet-based algorithm for discrimination of internal faults from magnetizing inrush currents in power transformers , 2006, IEEE Transactions on Power Delivery.

[12]  Eugeniusz Rosolowski,et al.  A self-organizing fuzzy logic based protective relay-an application to power transformer protection , 1997 .

[13]  G. Onbilgin,et al.  Wavelet based transformer protection , 2004, Proceedings of the 12th IEEE Mediterranean Electrotechnical Conference (IEEE Cat. No.04CH37521).

[14]  M. S. Sachdev,et al.  Using a neural network for transformer protection , 1995, Proceedings 1995 International Conference on Energy Management and Power Delivery EMPD '95.

[15]  D. Signorini,et al.  Neural networks , 1995, The Lancet.