Using neuro-wavelet technique for adaptive single phase autoreclosure of transmission lines

Adaptive single pole autoreclosure (SPAR) offers many advantages over conventional techniques. In the case of transient faults, the secondary arc time can be accurately determined, and in the case of permanent faults, breaker reclosure can be avoided. This paper describes, in some detail, the design of a SPAR technique based on the discrete wavelet transform (DWT) and artificial neural networks (ANN). The technique uses information extracted from the residual voltage of the opened phase using DWT. Simulation work for fault cases including transient and permanent single phase to ground faults in both medium and long extra high voltage (EHV) transmission systems have been carried out using the ATP-EMTP program. The validity of the proposed technique is checked through simulation and actual records obtained from the Egyptian 500 kV transmission system. The outcome of this study indicates that the neural network based DWT technique (neuro-wavelet) can be used as an attractive and effective means of achieving an adaptive autoreclosure scheme.