Bearing damage diagnosis by means of the linear discriminant analysis of stator current feature

Bearing damage is the most common failure in electrical machines. It can be detected by vibration analysis. However, this diagnosis method is costly or not always accessible due to the location of the equipment and the choice of the implemented sensors. An alternative method is provided with the electrical monitoring using the stator current of the electrical machine. This work aims at developing a diagnostic system based on the current feature generated by a frequency selection in the stator current spectrum. The features are evaluated by means of the linear discriminant analysis (LDA) and the fault diagnosis is performed with the Bayes classifier. The proposed method is evaluated by two types of damages at different load cases. The results show that the damaged bearings can be distinguished from the healthy bearing depending on the considered load cases.