A new approach to identify inrush current based on generalized S-transform

A novel approach to identify inrush current and internal fault current for power transformer protection based on generalized S-transform is presented. Generalized S-transform is a very powerful tool for non-stationary signal analysis giving the information of transient currents both in time and in frequency domains. It is used to extract patterns from inrush current and internal faults. The time-frequency contours are obtained after generalized S-transform, it is found that the time-frequency contours in case of inrush current are different from that in case of internal faults. The spectral energy and standard deviation from the generalized S-transform of signal are computed, classification of inrush current and internal faults is done by BP neural networks. Simulation results and dynamic test results indicate that this technique is effective under different fault conditions.