Header menu link for other important links
Outer Race Bearing Fault Identification of Induction Motor based on Nonlinear Signal Detection and Time Frequency Representation
, G.N.Mulay, J B Helonde
Published in IJERT
Volume: . 6
Issue: 5.0
Pages: 331.0 - 338.0
Paper presents outer race bearing fault detectionsystem in an induction motor based on nonlineardecomposition and Time frequency representation. Overalllife of any machine is based on its timely identification of faultscenario and the appropriate corrective action taken for it.The paper referrers to timely identification of bearing faultbehavior of an induction motor using stator current analysis.It is the combination of regular stator current, noise andrequired component of faulty bearing signature. The faultsignature is carried out by comparing a set of two bearingsmainly healthy and faulty bearing on the same machine.Testing is carried out for obtaining dataset of currents forhealthy and faulty bearing operated for different loadconditions. This detection is inscrutable as change in theobtained current wave is very small for different energylevels as well as frequency. Separating noise pattern andfault pattern is critical. Using Hilbert VibrationDecomposition (HVD) method Current wave is decomposedinto number of mono components keeping phase informationintact. For accelerating further process of identification, timeinformation of decomposed components should beunchanged. Smoothed Pseudo Wigner-Ville distribution(SPWVD) with reassignment is applied to decomposedcomponents for localizing fault zone in current wave. As anext step, feature extraction is followed by localization offault part. At last training is obtained for the featuresextracted from the wave and for this process, Support VectorMachine (SVM) classifier is used for training dataset. Intesting phase the system gives binary output i.e. faulty ornon-faulty bearing. The result analysis shows that theproposed method can detect bearing fault correctly.Performance analysis of propose
About the journal
JournalInternational Journal of Engineering Research and Technology
Open AccessYes