Adaptive multiple fault detection and alarm processing with probabilistic network

This paper presents the fault detection and alarm processing with fault detection system (FDS). FDS consists of adaptive architecture with probabilistic neural network (PNN). Training PNN uses the primary/back-up information of protective devices to create the training sets. However when network topology changes, adaptation capability becomes important in neural network application. PNN can be retained and estimated effectively. With a looped system, computer simulations were conducted to show the effectiveness of the proposed system, and PNNs adapt network topology changes.

[1]  M. T. Schilling,et al.  Fault location in electrical power systems using intelligent systems techniques , 2001 .

[2]  B. Kulicke,et al.  Multi neural network based fault area estimation for high speed protective relaying , 1996 .

[3]  Hong-Tzer Yang,et al.  A new neural networks approach to on-line fault section estimation using information of protective relays and circuit breakers , 1994 .

[4]  D. F. Specht,et al.  Probabilistic neural networks for classification, mapping, or associative memory , 1988, IEEE 1988 International Conference on Neural Networks.

[5]  Tsutomu Oyama,et al.  Fault section estimation in power system using Boltzmann machine , 1993, [1993] Proceedings of the Second International Forum on Applications of Neural Networks to Power Systems.

[6]  Tianshu Bi,et al.  Distributed adaptive fault section estimation system for large-scale power networks , 2002, 2002 IEEE Power Engineering Society Winter Meeting. Conference Proceedings (Cat. No.02CH37309).

[7]  Donald F. Specht,et al.  A general regression neural network , 1991, IEEE Trans. Neural Networks.