NEURAL Network based Area and Distance Estimation for Earthfaults in High Ohmic Earthed Power Systems

摘要

The objective of this paper is to answer the question, whe-ther artificial neural networks (ANN) are suitable to locate earthfaults in electrical power Systems. A neural network based approach for an earthfault relay has been developed. After fault detection and classification the earthfault is located by analyzing the transient voltage signals of the three phases V_a, V_b, V_c and the zero sequence voltage V_0, independent of the faulty phase. No signals of currents are used for the fault distance estimation.