Fault Isolation and Diagnosis of Induction Motor Based on Multi-Sensor Data Fusion

Electric motors of alternating current (AC) are widely used in different industrial applications, and this makes their fault detection very important. One of the most usual induction motor faults is the stator winding inter-turn short circuit. This paper presents a data fusion approach for stator winding fault diagnosis in induction motors using fuzzy measure and fuzzy integral theory. Features are extracted from motor stator current signals, and a techniq ue is used to select some appropriate features from total features. The fuzzy c-mean analysis method is employed to classify induction motor different modes. It is used to option the membership values of each feature group of classes. Different features are fused at feature level using fuzzy measure and fuzzy integral data fusion technique to produce diagnostic results. Results show that the proposed approach performs very well for fault diagnosis of a 4hp laboratory induction motor.