Power transmission lines fault direction estimation using artificial neural networks

The direction of a fault on a power transmission line needs to be identified rapidly and correctly. To classify forward and backward faults on a given line, a neural network's abilities in pattern recognition and classification could be considered as a solution. To demonstrate the applicability of this solution, a neural network technique is employed to design two different fault direction estimators. Details of the design procedure and results of performance studies with the proposed networks are given and compared.