Paper Information

Title: 

DETECTION OF BROKEN ROTOR BARS IN CAGE INDUCTION MACHINES USING NEURAL NETWORKS

Type: PAPER
Author(s): RAFIMANZELAT M.R.,ARAABI B.N.,FAIZ J.,SHARIFI E.
 
 
 
Name of Seminar: INTERNATIONAL POWER SYSTEM CONFRENCE
Type of Seminar:  CONFERENCE
Sponsor:  SHERKATE TAVANIR
Date:  2004Volume 19
 
 
Abstract: 

CONSIDERING THE IMPORTANCE AND WIDE USE OF INDUCTION MACHINES IN INDUSTRIAL APPLICATIONS, DETECTION OF THEIR FAULTS AT AN EARLY STAGE TO AVOID UNEXPECTED AND CATASTROPHIC FAILURES IS OF HIGH SIGNIFICANCE. IN THIS PAPER, A FAULT DETECTION METHOD IS PROPOSED FOR REVEALING BROKEN BARS, A COMMON MECHANICAL FAULT IN CAGE INDUCTION MACHINES, USING FEATURE EXTRACTION TECHNIQUES AND A NEURAL NETWORK CLASSIFIER. THE PROPOSED ALGORITHM USES THE STATOR CURRENT AND MOTOR SPEED AS INPUTS TO ASSESS THE MOTOR CONDITION. FAST FOURIER TRANSFORM IS UTILIZED TO OBTAIN THE FREQUENCY SPECTRUM OF THE CURRENT SIGNAL. A NEW EFFICIENT ALGORITHM IS THEN DEVELOPED TO EXTRACT SUITABLE FEATURES OUT OF THE FREQUENCY SPECTRUM OF THE SIGNAL. THE RELEVANCE OF THE FEATURES FOR THE PURPOSE OF FAULT DETECTION IS INVESTIGATED AND VERIFIED. A NEURAL NETWORK CLASSIFIER IS THEN DEVELOPED AND APPLIED TO DISTINGUISH DIFFERENT MOTOR CONDITIONS. A SERIES OF DATA COLLECTED FROM EXPERIMENTS ON A THREE PHASE 3 HP CAGE INDUCTION MACHINE PERFORMED IN DIFFERENT LOAD AND FAULT CONDITIONS ARE USED FOR TRAINING AND THEN TESTING THE CLASSIFIER. EXPERIMENTAL RESULTS CONFIRM THE EFFECTIVENESS OF THE PROPOSED ALGORITHM FOR DETECTION OF BROKEN BAR FAULT.

 
Keyword(s): FAULT DIAGNOSIS, BROKEN BAR, INDUCTION MACHINE, NEURAL NETWORKS, PATTERN RECOGNITION
 
Yearly Visit 16   tarjomyar
 
Latest on Blog
Enter SID Blog