A transformer differential protection based on finite impulse response artificial neural network

This paper presents the application of a finite impulse response artificial neural network (FIRANN) on digital differential protection design for a th ree-phase transformer. The neural network inputs are normalized sampled cur rent data Any pre-processing signal as in other neural network applications is not needed. The network was trained to identify external fault on load side besides internal fault as in the other differential protection. The FI RANN has 6 inputs and 2 outputs. The first output goes on when there is an internal fault while the second output goes on in case of external fault. T he simulated system used to get data for training and testing the neural ne twork is presented. The neural network architecture and some of the obtaine d results are reported. (C) 1999 Elsevier Science Ltd. All rights reserved.