Current Transformer Saturation Detection Method Based on Artificial Neural Network

Abstract

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