Current Transformer Saturation Detection Method Based on Artificial Neural Network

When current transformer is saturated, mainly due to the presence of an exponentially decaying DC component in fault current, its secondary has a distinctive distorted waveform which significantly differs from primary (true) waveform. It leads underestimation value calculated by relay protection compared true value. Thus, turn, results trip time delay or even devices operation failure, since settings and algorithms are designed on assumption that sinusoidal proportional primary. And since, when using classical electromagnetic transformer, it impossible exclude possibility saturation, detection such abnormal condition urgent technical problem. The article proposes use artificial neural network for this purpose, which, together with traditional method saturation based adjacent samples comparison, allows implementing fast reliable detector. details stages practical implementation network. MATLAB-Simulink environment was used assess proposed detector operation. experiments had been performed confirmed provides accurate within wide range power system parameters change.