A neural network based fault detector for power distribution systems
This paper presents a fault detector for power distribution systems based on the use of feedforward neural networks. The described method is successfully tested through several simulations. The efficiency of the algorithm to recognize faulty feeders without measuring any voltage in the network and without any threshold is emphasized. Moreover, the sampling frequency of signals and the errors that measuring instruments may introduce do not interfere with the right functionning of the detector.
Unable to display preview. Download preview PDF.
- 1.D. Niebur, “An Overview of ANN applications in power systems industries”, Proceedings of ICANN'95, Session 8, Power Systems, pp. 1–9.Google Scholar
- 2.H. Régal, et al. “A Neural Network classifier for the analysis of power transformer differential current”, in Proceedings of ISAP'94, Vol. 2, pp. 673–680.Google Scholar
- 3.T.S.Sidhu, et al. “An artificial Neural Network for directional comparison relaying of transmission lines”, in Proceedings of DPSP'97, pp. 282-285.Google Scholar
- 4.W. Qi, et al., “Distance protection using an artificial neural network”, in Proceedings of DPSP'97, pp. 286–290.Google Scholar
- 5.D. Griffel, et al., “Nouvelles techniques de mise à la terre du neutre sur le réseau MT”, Revue Générale d'Electricit6, n°11/94, December 1994, pp. 34–44.Google Scholar
- 6.Y. Assef, et al., “Artificial Neural Network for Single Phase Fault Detection in Resonant Grounded Power Distribution Systems”, in Proceedings of T&D'96, pp. 566–572.Google Scholar