Full Content is available to subscribers

Subscribe/Learn More  >

Analysis of Time, Frequency and Wavelet Based Features of Vibration and Current Signals for Fault Diagnosis of Induction Motors Using SVM

[+] Author Affiliations
Purushottam Gangsar, Rajiv Tiwari

Indian Institute of Technology Guwahati, Guwahati, India

Paper No. GTINDIA2017-4774, pp. V002T05A027; 10 pages
  • ASME 2017 Gas Turbine India Conference
  • Volume 2: Structures and Dynamics; Renewable Energy (Solar, Wind); Inlets and Exhausts; Emerging Technologies (Hybrid Electric Propulsion, UAV, ...); GT Operation and Maintenance; Materials and Manufacturing (Including Coatings, Composites, CMCs, Additive Manufacturing); Analytics and Digital Solutions for Gas Turbines/Rotating Machinery
  • Bangalore, India, December 7–8, 2017
  • Conference Sponsors: International Gas Turbine Institute
  • ISBN: 978-0-7918-5851-6
  • Copyright © 2017 by ASME


This paper presents a comparative analysis of the time, frequency and time-frequency domain based features of the vibration and current signals for identifying various faults in induction motors (IMs) using support vector machine (SVM). Four mechanical faults (bearing fault, unbalanced rotor, bowed rotor and misaligned rotor), and three electrical faults (broken rotor bars, stator winding fault with two severity levels and phase unbalance with two severity levels) are considered in the present study. The proposed fault diagnosis consists of three steps. In the first step, the vibration in three orthogonal directions and the current in three phases are acquired from the healthy and faulty motors using a machine fault simulator (MFS). In second step, useful statistical features are extracted from the time, frequency and time-frequency domain (continuous wavelet transform (CWT)) of the signal. For the effective fault diagnosis, SVM parameters are optimally selected based on the grid-search method along with 5-fold cross-validation, and the effective fault features are selected based on the wrapper model. Finally, the fault diagnosis of IM is performed using optimal SVM parameters and effective features as input to the SVM. The classification performance of all methodologies developed in three domains is compared for various operating conditions of IMs. The test results showed that the developed methodology could isolate ten IM fault conditions successfully based on features from all three domains at all IM operating conditions; however, time-frequency features give the best results.

Copyright © 2017 by ASME



Interactive Graphics


Country-Specific Mortality and Growth Failure in Infancy and Yound Children and Association With Material Stature

Use interactive graphics and maps to view and sort country-specific infant and early dhildhood mortality and growth failure data and their association with maternal

Citing articles are presented as examples only. In non-demo SCM6 implementation, integration with CrossRef’s "Cited By" API will populate this tab (http://www.crossref.org/citedby.html).

Some tools below are only available to our subscribers or users with an online account.

Related Content

Customize your page view by dragging and repositioning the boxes below.

Related eBook Content
Topic Collections

Sorry! You do not have access to this content. For assistance or to subscribe, please contact us:

  • TELEPHONE: 1-800-843-2763 (Toll-free in the USA)
  • EMAIL: asmedigitalcollection@asme.org
Sign In