Open Access Open Access  Restricted Access Subscription or Fee Access

Discrimination of Magnetic Inrush and Phase to Phase Fault in Transformer using Probabilistic Neural Network

S. Arun Prakash, M. Geetha


In this paper, the probabilistic neural network (PNN) is proposed as the classifier to discriminate between the magnetizing inrush and the phase to phase fault of a power transformer. The probabilistic neural network (PNN), is investigated for the protection of power transformer. Current waveforms due to different types of events, such as phase to phase faults and circuit breaker switching were generated using power transformer simulated in MATLAB simulation software. Simulated data were used to train the classifiers. To evaluate the developed algorithm for various operating condition of the transformer, including internal faults, are obtained by modeling the transformer in MATLAB Simulink. The data from the simulation are trained and tested by using Probabilistic Neural Network for discrimination of magnetic inrush and phase to phase fault.


Inrush Current, Phase to Phase Fault (Internal Fault), Power Transformer, Probabilistic Neural Network (PNN)

Full Text:



Tripathy, R. P. Maheshwari, and H. K. Verma, “Power Transformer Differential Protection Based on Optimal Probabilistic Neural Network,” IEEE Trans. Power Delivery, vol. 25,No;1, pp. 102-112, Jan 2010.

S. Sidhu and M. S. Sachdev, “On line identification of magnetizing inrush and internal faults in three phase transformers,” IEEE Trans. Power Del., vol. 7, no. 4, pp. 1885–1891, Oct 1992.

M. Tripathy, R. P. Maheshwari, and H. K. Verma, “Advances in transform protection: A review,” Elect. Power Compon. Syst., vol. 33, no. 11, pp. 1203–1209, Nov. 2005

R. L. Sharp andW. E. Glassburn, “A transformer differential relay with second harmonic restraint,” Trans. AIEE, vol. 77, pp. 884–892, 1958.

K. Yabe, “Power differential method for discrimination between fault and magnetizing inrush current in transformers,” IEEE Trans. Power Del., vol. 12, no. 3, pp. 1109–1118, Jul. 1997

L. G. Perez, A. J. Flechsig, J. L. Meador, and Z. Obradoviic, “Training an artificial neural network to discriminate betweenmagnetizing inrush and internal faults,” IEEE Trans. Power Del., vol. 9, no. 1, pp. 434–441, Jan. 1994.

Á. L. Orille-Fernández, N. K. I. Ghonaim, and J. A. Valencia, “A FIRANN as a differential relay for three phase power transformer protection,” IEEE Trans. Power Del., vol. 16, no. 2, pp. 215–218, Apr. 2001.

M. R. Zaman andM. A. Rahman, “Experimental testing of the artificial neural network based protection of power transformers,” IEEE Trans. Power Del., vol. 13, no. 2, pp. 510–517, Apr. 1998.

A. Wiszniewski and B. Kasztenny, “A multi-criteria differential transformer relay based on fuzzy logic,” IEEE Trans. Power Del., vol. 10, no. 4, pp. 1786–1792, Oct. 1995.

P. Arboleya, G. Diaz, J. G. Aleixandre, and C. G. Moran, “A solution to the dilemma inrush/fault in transformer differential relaying using MRA and wavelets,” Elect. Power Syst. Res., vol. 34, no. 3, pp.285–301, Mar. 2006.

H. Zhang, J. F.Wen, P. Liu, and O. P. Malik, “Discrimination between fault and magnetizing inrush current in transformer using short-time correlation transform,” Elect. Power Energy Syst., vol. 24, no. 7, pp. 557–562, Oct. 2002B.

K. C. Tan and H. J. Tang, “New dynamical optimal learning for linear multilayer FNN,” IEEE Trans. Neural Netw., vol. 15, no. 6, pp. 1562–1568, Nov. 2004.

Z. Moravej, D. N. Vishwakarma, and S. P. Singh, “Application of radial basis function neural network for differential relaying of a power transformer,” Comput. Elect. Eng., vol. 29, no. 3, pp. 421–434, May 2003.

D. F. Specht, “Probabilistic neural network,” Neural Netw., vol. 3, no. 1, pp. 190–118, 1990.

E. Parzen, “On the estimation of a probability density function and mode,” Ann. Math. Statist., vol. 3, pp. 1065–1076, 1962.

N. K. Bose and P. Liang, Neural Network Fundamentals With Graphs, Algorithms, and Applications, International ed. New York:McGraw-Hill, 1996.

D. F. Specht and P. D. Shapiro, “Generalization accuracy of probabilistic neural networks compared with back-propagation networks,”in Proc. IEEE Int. Joint Conf. Neural Networks, Seattle, WA, 1991,vol. 1, pp. 887–892.

M. Geethanjali, S. Mary Raja Slochanal, R. Bhavani, “PSO trained ANN-based differential protection scheme for power transformer”, ScienceDirect, Neurocomputing 71, pp. 904-918, 2008.



  • There are currently no refbacks.

Creative Commons License
This work is licensed under a Creative Commons Attribution 3.0 License.