Fault diagnosis in an induction motor by pattern recognition methods

This paper presents the application of pattern recognition methods in order to detect broken bars and stator unbalance in an induction motor. Some time or frequency dependent parameters, which are relevant for fault detection, are described. They are used to build up a pattern vector. Then two decision methods are proposed. The first one is based on the k-nearest neighbors (kNN) rule. The second one based on linear discriminant functions determination. The principles of two decision rules are introduced and the diagnosis results obtained are compared.