In this paper, a novel online and non-destructive algorithm is proposed to detect inter-turn short circuit faults in the stator windings of an induction motor. This fault detection algorithm is based on the features extracted from infrared images taken from the hottest region of the motor surface. Feature extraction method from infrared thermal images has been developed based on histogram of temperature profile, correlation between fault severity and the hottest region on the motor body, and comparison with healthy motor features. Experiments are conducted to demonstrate the effectiveness of the proposed method using a 2-hp induction motor.
All Science Journal Classification (ASJC) codes
- Electronic, Optical and Magnetic Materials
- Atomic and Molecular Physics, and Optics
- Condensed Matter Physics