This paper describes a fault detector that uses artificial neural networks (ANN). It represents the Brst step toward the development of a neural distance relay for protecting transmission lines. We envisage the fault defection problem as a pattern classification process. Our suggested approach Is based on the fact that when a fault occurs, a change In the system Impedance takes place and, as a consequence, the current phase and amplitude change. The ANN-based fault detector trained to detect them changes as Indicators of the Instant of fault inception. Results showing the performance of fault detector am presented In the paper, Indicating that It Is that robust and accurate.