Codes for: Transformer Fault Prognosis Using Deep Recurrent Neural Network Over Vibration Signals (under review)
Vibration analysis is considered as a cost-efficient and non-destructive technique to monitor the transformer operating conditions and evaluate the transformer mechanical integrity. This method enables transformer fault prognosis before insulation catastrophic failure. In this work, the possibility of using deep neural networks in capturing the hidden patterns of vibration time-series to predict the transformer under and over excitation and inter-turn fault progress prediction in early stages is examined. This focus is warranted because deep learning techniques lend themselves to integrating the feature extraction into the predictive model construction stage. In this regard, deep recurrent neural network (RNN) architecture including unidirectional and bidirectional gated recurrent units (GRUs) and long short-term memory (LSTM) models are adopted. The constructed RNN for predicting excitation voltage exhibits a remarkable performance with a Relative Absolute Error of 0.56%. Predicting the inter-turn fault proved to be a more challenging problem and the constructed RNN for this purpose showed an RAE of 17.58%. The source code for implementing all constructed models is available at: https://github.com/azollanvari/FaultPrognosisDL https://github.com/azollanvari/FaultPrognosisDL.