An Artificial Neural Network Based Digital Differential Protection Scheme for Synchronous Generator Stator Winding Protection

Abstract

This research depicts another artificial neural network (ANN) based digital differential protection scheme for generator stator winding protection. The scheme incorporates two feedforward neural networks (FNNs). One ANN is utilized for flaw recognition and the other is utilized for inward deficiency grouping. This structure utilizes current examples from the line-side and the unbiased end notwithstanding tests from the field current. Essential and/or second consonant present in the field current during an issue help the ANN, utilized for flaw location, to separate between generator states (typical, outside issue and interior deficiency states). Results demonstrating the performance of the protection scheme are displayed and show that it is quick and solid.