Towards Machine Learning based Real-time Fault Identification and Classification in High Power Induction Motors
- Resource Type
- Conference
- Authors
- Ali, Usman; Hafiz, Rehan; Tauqeer, Tauseef; Younis, Usman; Ali, Waqas; Ahmad, Asrar
- Source
- 2020 5th International Conference on Robotics and Automation Engineering (ICRAE) Robotics and Automation Engineering (ICRAE), 2020 5th International Conference on. :46-53 Nov, 2020
- Subject
- Robotics and Control Systems
Induction motors
Rotors
Stator windings
Vibrations
Machine learning
Bars
Air gaps
Motor current signature analysis
Fast Fourier transform
vibration analysis
induction motor
- Language
Motor current signature analysis and vibration analysis techniques have been used for the identification and classification of faults in high power induction motors. Fast fourier transform has been applied to the time domain stator current signal and vibration signal of the induction motor. A comparison of the frequency spectrum has been performed between healthy and unhealthy motor current and vibration signals. Five different machine learning classification algorithms have been used to evaluate the performance of the induction motor. The developed system provides a cost-effective and real-time alternative to the conventional off-line induction motor condition monitoring systems.