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 t o the proper performance of a pourer system. With the advent of large gener ating stations and highly interconnected power systems, shorter fault clear ing times are becoming necessary. To classify forward and backward faults o n a given line rapidly, a neural networks abilities in pattern recognition and classification could be considered as a solution. To demonstrate the ap plicability of this solution, neural network technique is employed to desig n two different fault direction discrimination modules. Results of performa nce studies with the proposed networks are presented in this paper. Results obtained indicate that the direction of fault on a transmission line can b e identified rapidly and correctly by the proposed approaches.