Title :
Intelligent Diagnosis of Broken Bars in Induction Motors Based on New Features in Vibration Spectrum
Author :
Sadoughi, Alireza ; Ebrahimi, Mohammad ; Moalem, Mehdi ; Sadri, Saeid
Author_Institution :
Esfahan Univ. of Technol., Esfahan
Abstract :
This paper presents an intelligent method for diagnosing broken bars in induction motors. The method is based on training a neural network using new features extracted from vibration spectrum. These fault related features depend on slip. The exact value of slip can be determined using vibration spectrum; therefore, a vibration sensor is the only required sensor. The method has been able to diagnose correctly in all the laboratory tests.
Keywords :
computerised instrumentation; fault diagnosis; induction motors; neural nets; power engineering computing; sensors; vibration measurement; broken bar intelligent diagnosis; fault diagnosis; induction motor; neural network; vibration sensor; vibration spectrum; Bars; Fault diagnosis; Feature extraction; Frequency estimation; Induction motors; Laboratories; Rotors; Stators; Synchronous motors; Vibration measurement; Broken Bar; Fault Diagnosis; Induction Motor; Intelligent; Vibration;
Conference_Titel :
Diagnostics for Electric Machines, Power Electronics and Drives, 2007. SDEMPED 2007. IEEE International Symposium on
Conference_Location :
Cracow
Print_ISBN :
978-1-4244-1061-3
Electronic_ISBN :
978-1-4244-1062-0
DOI :
10.1109/DEMPED.2007.4393079
