Health monitoring of a gear box has been attempted by the support vector machine (SVM) learning technique with the help of time-frequency (wavelet) vibration data. Multi-fault classification capability of the SVM is suitably demonstrated that is based on the selection of SVM parameters. Different optimization methods (i.e., the grid-search method (GSM), the genetic algorithm (GA) and the artificial bee colony algorithm (ABCA)) have been performed for optimizing the SVM parameters. Four fault conditions have been considered including the no defect case. Time domain vibration signals were obtained from the gearbox casing operated in a suitable speed range. The continuous wavelet transform (CWT) and wavelet packet transform (WPT) are extracted from time domain signals. A set of statistical features are extracted from the wavelet transform. The classification ability is noted and compared against predictions when purely time domain data is used, and it shows an excellent prediction performance.
Skip Nav Destination
ASME 2013 Gas Turbine India Conference
December 5–6, 2013
Bangalore, Karnataka, India
Conference Sponsors:
- International Gas Turbine Institute
ISBN:
978-0-7918-5616-1
PROCEEDINGS PAPER
Health Monitoring of Gear Elements Based on Time-Frequency Vibration by Support Vector Machine Algorithms
D. J. Bordoloi,
D. J. Bordoloi
Indian Institute of Technology Guwahati, Guwahati, India
Search for other works by this author on:
Rajiv Tiwari
Rajiv Tiwari
Indian Institute of Technology Guwahati, Guwahati, India
Search for other works by this author on:
D. J. Bordoloi
Indian Institute of Technology Guwahati, Guwahati, India
Rajiv Tiwari
Indian Institute of Technology Guwahati, Guwahati, India
Paper No:
GTINDIA2013-3772, V001T05A019; 11 pages
Published Online:
February 28, 2014
Citation
Bordoloi, DJ, & Tiwari, R. "Health Monitoring of Gear Elements Based on Time-Frequency Vibration by Support Vector Machine Algorithms." Proceedings of the ASME 2013 Gas Turbine India Conference. ASME 2013 Gas Turbine India Conference. Bangalore, Karnataka, India. December 5–6, 2013. V001T05A019. ASME. https://doi.org/10.1115/GTINDIA2013-3772
Download citation file:
16
Views
Related Proceedings Papers
Related Articles
Damage Identification of a Gear Transmission Using Vibration Signatures
J. Mech. Des (June,2003)
Extraction of Periodic Components for Gearbox Diagnosis Combining Wavelet Filtering and Cyclostationary Analysis
J. Vib. Acoust (July,2004)
Identification of Nonlinear Systems Through Time-frequency Filtering Technique
J. Vib. Acoust (April,2003)
Related Chapters
Rotation Invariant Texture Classification Based on Support Vector Machine and Wavelet Transform
International Conference on Computer Technology and Development, 3rd (ICCTD 2011)
Detecting Tampered Image Based on Contrast Enhancement of Y Channel
International Conference on Future Computer and Communication, 3rd (ICFCC 2011)
The Analysis of Engine Vibration Signals Based on Wavelet Packet
International Conference on Mechanical and Electrical Technology, 3rd, (ICMET-China 2011), Volumes 1–3