Comparative Study of Time-Frequency Methods for the Detection and Categorization of Intermittent Faults in Electrical Drives

The detection of non-catastrophic faults in conjunction with other factors can be used to determine the condition and remaining life of an electric drive. As the frequency and severity of these faults increase, the working life of the drive decreases, leading to eventual failure. In this work, four methods to identify developing electrical faults are presented and compared. They are based on the short-time Fourier transform, undecimated wavelet analysis, Wigner and Choi Williams distribution of the field oriented currents in PMAC drives. The different fault types are classified by developing a linear discriminant classifier based on the transform coefficients. The comparison is based on the number of correct classifications and Fisher's discriminant ratio.