A new approach to detect stator fault in permanent magnet synchronous motors

Abstract

In this paper, detection of the stator winding inter-turn short circuit fault (SWISCF) in surface-mounted permanent magnet synchronous motors (SPMSMs) and classification of the fault severity via pattern recognition system (PRS) are presented. In order to automatically detect stator winding short circuit fault and to estimate severity of this fault, artificial neural network (ANN) based PRS has been used. It has been observed that the amplitude of the 3 <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">rd</sup> harmonics of the current is the most distinctive characteristic for detecting the short circuit fault ratio of the SPMSM. To increase the fault clasification accuracy of PRS both fundamental (1 <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">st</sup> ) and 3 <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">rd</sup> harmonics are used. In order to validate proposed method experimental results are presented.