A Deep Learning Based Methodology Development for Fault Classification in Transmission Lines

This work proposes a methodology based on Deep Learning, such as recurrent neural networks (RNN) and long-short-term memory networks (LSTM) to classify faults in transmission lines in power systems. The implemented neural network is trained using data from the measurements of electric currents during the presence of faults that were obtained by simulation. The trained neural network is able to correctly classify faults using the current signature.