Abstract
This paper presents the practical implementation of a novel fault diagnosis scheme for the protection of interior permanent magnet (IPM) motors using wavelet transform and artificial neural network (ANN). The preprocessing of fine currents of different faulted and normal unfaulted conditions of an IPM motor are carried out by the wavelet packet transform (WPT) in order to minimize the structure and timing of the neural network. The WPT coefficients of second level high frequency details (dd(2)) of line currents are able to differentiate between the healthy and faulted conditions. These are used as the input sets of a three-layer feed-forward neural network. The performance of this newly devised diagnosis scheme is evaluated by simulation results as well as by experimental results. The scheme is evaluated and tested on-fine on a laboratory 1-hp IPM motor using the ds1102 digital signal processor board. Three types of faults such as single tine to ground (L-G) fault, tine-to-line (L-L) fault, and single phasing fault are investigated. In an the tests carried out, the type of fault are classified and identified promptly and properly, and the tripping action is initiated almost at the instant or within one cycle of the fault occurrence based on a 60 Hz system.