NEURAL-NETWORK-BASED ADAPTIVE SINGLE-POLE AUTORECLOSURE TECHNIQUE FOREHV TRANSMISSION-SYSTEMS

Adaptive single-pole autoreclosure offers many advantages over convent ional approaches. In this paper an adaptive single-pole autoreclosure technique is developed using artificial neural networks. The data gene ration, data preprocessing, and feature extraction process required to set up the training/test data for the neutral network, and the implem entation of the latter are described in detail. A non-fully connected three-layer perceptron is trained by the Extended-Delta-Bar-Delta lear ning algorithm. The test results demonstrate the ability of this netwo rk to distinguish reliably between permanent and transient faults, and in the latter case, the ability to determine the exact arc extinction time. The outcome of the study indicates that neural network approach can be used as an attractive and effective means of realising an adap tive autoreclosure scheme.