An artificial neural network based digital differential protection scheme for synchronous generator stator winding protection

This paper describes a new Artificial Neural Network (ANN) based digital di fferential protection scheme for generator stator winding protection. The s cheme includes two Feedforward Neural Networks (FNNs). One ANN is used for fault detection and the other is used for internal fault classification. Th is design uses current samples from the line-side and the neutral-end in ad dition to samples from the field current. Fundamental and/or second harmoni c present in the field current during a fault help the ANN, used for fault detection, to differentiate between generator states (normal, external faul t and internal fault states). Results showing the performance of the protec tion scheme are presented and indicate that it is fast and reliable.