Eventos Anais de eventos
COBEM 2019
25th International Congress of Mechanical Engineering
VIBRATION-BASED CONDITION MONITORING OF INDUCTION MOTORS USING A FEATURE SELECTION AND ARTIFICIAL NEURAL NETWORKS
Submission Author:
Aline Treml , PR
Co-Authors:
Aline Treml
Presenter: Aline Treml
doi://10.26678/ABCM.COBEM2019.COB2019-2203
Abstract
Induction motors are very used in electromechanical energy conversion equipment, as they are robust and reliable machines. One of the main techniques for identifying incipient faults in these rotary machines is vibration-based condition monitoring. This paper consists of the development of a computational tool dedicated to a diagnostic system for broken rotor bars in Three Phase Induction Motors. Artificial Neural Networks and Feature Extraction for multi-class classification and detection were configured to receive indices derived from the processing of mechanical signals and then identify normal motors and faulty motors. Besides that, the fault severity is also diagnosed, which represented by the number of broken rotor bars. Experimental data was tested in order to evaluate the proposed method. Signals were obtained from induction motors operating with different torque levels. The results demonstrate the effectiveness of the computational tools developed the diagnostic system since the indices correlated with fault phenomenon.
Keywords
Fault Diagnosis, Induction Motors, Vibration-Based Condition Monitoring, Feature Selection, Artificial neural networks
