Discrimination of Inter-turn Faults from Magnetizing Inrush Currents in Transformers : A Wavelet Transform Approach (original) (raw)

Power transformers are designed to transmit and distribute electrical power. Depending on the size of a transformer, replacement costs can range from a few hundred dollars to millions of dollars. Performing invasive tests also add to the replacement cost. Hence, there is an increasing need to move from traditional schedule-based maintenance programs to condition-based maintenance. A focused approach is required for diagnostics. Considering the long service life of a power transformer and prevalent use of human judgment (expert), there is a need to develop a knowledge base expert system. This paper proposes a noninvasive approach, using digital signal processing wavelet-based artificial neural network technique for monitoring non stationary variations in order to distinguish between transformer inrush currents and transformer inter-turn faults. The performance of this algorithm is demonstrated on custom-built three-phase transform. Keywords— Transformer, Inrush, Interturn fault, Wave...