Neural Network–Based Fault Direction Discrimination for High-Speed Transmission Line Protection

Detection of the direction of a fault on a transmission line is essential to the proper performance of a power system. W ith the advent of large generating stations and highly interconnected power systems, shorter fault clearing times are becoming necessary. To classify forward and backward faults on a given line rapidly, a neural network's abilities in pattern recognition and classification could be considered as a solution. To demonstrate the applicability of this solution, neural network technique is employed to design two different fault direction discrimination modules. Results of performance studies with the proposed networks are presented in this paper. Results obtained indicate that the direction of fault on a transmission line can be identified rapidly and correctly by the proposed approaches.