A Novel Approach to Fault Classification and Fault Location for Medium Voltage Cables Based on Artificial Neural Network

A novel application of neural network approach to fault classification and fault location of Medium voltage cables is demonstrated in this paper. Different faults on a protected cable should be classified and located correctly. This paper presents the use of neural networks as a pattern classifier algorithm to perform these tasks. The proposed scheme is insensitive to variation of different parameters such as fault type, fault resistance, and fault inception angle. Studies show that the proposed technique is able to offer high accuracy in both of the fault classification and fault location tasks.

Authors:

• H. Khorashadi-Zadeh
• M. R. Aghaebrahimi

Keywords:

• Artificial neural networks
• cable
• fault location andfault classification.

References:

[1] Z. Q. Bo, A. T. Johns, "A new non-unit protection scheme based on fault
generated high frequency current signals," APSCOM-95, International
Conference on Advances in Power System Control, Operation &
Management, 9-11 November, 1995, Hong Kong.
[2] R.N. Mahanty, P.B.D Gupta, "Application of RBF neural network to
fault classification and location in transmission lines," IEE Proceedings
Generation, Transmission and Distribution, Vol. 151, 2 March 2004, pp.
201- 212.
[3] M. Oleskovicz, D.V. Coury, R.K. Aggarwal, "A complete scheme for
fault detection, classification and location in transmission lines using
neural networks," Developments in Power System Protection, 2001,
Seventh International Conference on (IEE), 9-12 April 2001, pp. 335-
338.
[4] H. Khorashadi-Zadeh, S. HOSSEINI "An accurate fault locator for
cable transmission using ANN," 12th IEEE Mediterranean IEEE
Electrotechnical Conference, Melcon2004, Dubrovink, Croatia, pp. 901-
904.
[5] H. Khorashadi-Zadeh, "Correction of capacitive voltage transformer
distorted secondary voltages using artificial neural networks," In
Proceedings Seventh Seminar on Neural Network Applications in
Electrical Engineering, Sep. 2004, Belgrad-serbia and Montenegro
(Neural 2004).
[6] M. Kezonuic, "A Survey of neural net application to protective relaying
and fault analysis," Eng. Int. Sys. vol. 5, no. 4, Dec. 1997, pp. 185-192.
[7] H. Khorashadi Zadeh, M. Sanaye-Pasand "Power transformer
differential protection scheme based on wavelet transform and artificial
neural network algorithms," Proc. of the 39nd International Universities
Power Engineering Conference, UPEC2004, 2004, pp. 747-753.
[8] H. Khorashadi Zadeh, "A novel approach to detection high impedance
faults using artificial neural network," Proc. of the 39nd International
Universities Power Engineering Conference, UPEC2004, Sep. 2004, pp.
373-377.
[9] H. Khorashadi-Zadeh, et. al. "AN ANN Based Approach to Improve the
Distance Relaying Algorithm," Proc. of 2004 IEEE Cybernetics and
Intelligent Systems Conference, Dec. 2004, Singapoure, (CIS2004).
[10] V. H. Ortiz, et. al. "Arcing faults patterns for based ANN relays for
transmission lines," Proc. 2003 IEEE PowerTech Conference, June 23-
26, Bologna, Italy.
[11] D.V. Coury, and D.C. Jorge, "Artificial neural network approach to
distance protection," IEEE Trans. on Power Delivery, vol. 13, no. 1,
1998, pp. 102-108.
[12] K. R. Cho, et. al "An ANN based approach to improve the speed of a
differential equation based distance relaying algorithm," IEEE Trans.
on Power Delivery, vol. 14, Apr. 1999, pp. 349-357.
[13] PSCAD/EMTDC User-s Manual, Manitoba HVDC Research Center,
Winnipeg, Manitoba, Canada.
[14] S. Haykin, Neural Networks, IEEE Press, New York, 1994.
[15] M. T. Hagan and M. B. Menhaj, "Training feedforward networks with
the Marquardt algorithm," IEEE Trans. on Neural Networks, vol. 5, no.
6, 1994, pp. 989-993.