Investigation of Combined Electrical Modalities for Fault Diagnosis on a Wound-Rotor Induction Generator

Abstract

An online method for fault diagnosis on a wound rotor induction generator using stator voltage and current, and rotor current are investigated. The diagnostic method comprises processing of the generators signals and classification of the machine's condition according to healthy or specific fault type. The signal processing phase of the intelligent fault diagnosis process extracts features, which are frequency-based, interrelated to specific fault modes, i.e., stator winding, rotor winding, and brush faults. Finite element modeling of a wound-rotor induction generator is carried out under normal and different fault conditions for the purpose of conducting preliminary design and testing of the classification system. An experimental setup is then used to validate the computational results and verify the diagnostic method. The results indicate that the stator voltage, stator current, and rotor current modalities exhibit patterned sensitivities to the investigated faults. It is found that the classifier works well with a large number of features offered by the combination of these modalities yielding a best overall diagnostic accuracy of 99% in an experimental setting.