A Hybrid Wavelet--ANN Approach in Transformer Protection

This paper presents the development of a wavelet-based algorithm, for distinguishing between magnetizing inrush and internal faults of the power transformer. The proposed technique consists of a preprocessing unit based on Continuous wavelet transform (CWT) in combination with an artificial neural network (ANN) for detecting and classifying faults. The CWT acts as an extractor of distinctive features in the transient current signals at the relay location. This information is then fed into an ANN for classifying fault, normal and magnetizing inrush conditions. The results presented clearly showed that the proposed technique is very fast, computationally efficient and intelligent enough to accurately discriminate between magnetizing inrush, normal and faults in the transformer.