A NEURO-FUZZY TECHNIQUE FOR DISCRIMINATION BETWEEN INTERNAL FAULTS AND MAGNETIZING INRUSH CURRENTS IN TRANSFORMERS

Abstract

This paper presents the application of the fuzzy-neuro method to<br />investigate transformer inrush current. Recently, the frequency environment of<br />power systems has been made more complicated and the magnitude of the second<br />harmonic in inrush current has been decreased because of the improvement of cast<br />steel. Therefore, traditional approaches will likely mal-operate in the case of<br />magnetizing inrush with low second component and internal faults with high<br />second harmonic. The proposed scheme enhances the inrush detection sensitivity of<br />conventional techniques by using a fuzzy-neuro approach. Details of the design<br />procedure and the results of performance studies with the proposed detector are<br />given in the paper. The results of performance studies show that the proposed<br />algorithm is fast and accurate.