Optimal Feature Set for Detection of Inner Race Defect in Rolling Element Bearings
##plugins.themes.bootstrap3.article.main##
##plugins.themes.bootstrap3.article.sidebar##
Abstract
Rolling element bearings are the key components in many rotating machinery. It is necessary to determine the condition of the bearing with reasonable degree of confidence. Many techniques have been developed for bearing fault detection. Each of these techniques have their own strengths and weaknesses. In this paper various features are compared for detecting inner race defects in rolling element bearings. Mutual information between the feature and defect is used as a quantitative measure of quality and the features are ranked appropriately. Often, a combination of different features is used for bearing fault detection. Hence it is important to understand the interaction of features for classification purposes. This paper addresses this issue and determines the optimal feature set for best detection performance.
How to Cite
##plugins.themes.bootstrap3.article.details##
bearings, damage detection, damage modeling
N. Barkov. Condition assesment and life prediction of rolling element bearings. Sound and Vibration, 1995.
(Cade et al., 2005) Iain S. Cade, Patrick S. Keogh, and M. Necip Sahinkaya. Fault identification in ro- tor/ magnetic bearing systems using discrete time wavelet coefficients. IEEE/ ASME Transctions on Mechatronics, 10(6):648–657, December 2005 2005.
(Chan, 1995) Y. T. Chan. Wavelet Basics. Kluwer Academic Publihsers, Boston, 1995.
(Cover and Thomas, 1991) T. M. Cover and J. A. Thomas. Elements of Information Theory. John Wiley and Sons, New York, 1991.
(Djebalaetal.,2008) AbderrazekDjebala,Douredine Ouelaa, and Nace Hamzaoui. Detection of rolling bearing defects using discrete wavelet analysis. Me- chanica, 43:339–348, 2008.
(Duda et al., 2001) Richard O. Duda, Peter E. Hart, and David G. Stork. Pattern Classification. Wiley- Interscience, New York, 2001.
(Feng and Schlindwein, 2009) Yanhui Feng and Fer- nando S. Schlindwein. Normalized wavelet packets quantifiers for condition monitoring. Mechanical Systems and Signal Processing, 23:712–723, 2009.
(Guo et al., 2004) H. Guo, L. B. Jack, and A. K. Nandi. Automatic feature extraction for bearing fault detection using genetic programming. Eighth International Conference on Vibrations in Rotat- ing Machinery - IMechE Conference Transactions, 2:363–372, 2004.
(Harris, 2002) Tedric A. Harris. Rolling Bearing Analysis. Wiley-Interscience, 2002.
(Harsha et al., 2004) S. P. Harsha, K. Sandeep, and R. Prakash. Nonlinear behaviors of rolling element bearings due to surface waviness. Journal of Sound and Vibration, 272:557–580, 2004.
(Ho and Randall, 2000) D. Ho and R. B. Randall. Optimisation of bearing diagnostic techniques using simulated and actual bearing fault signals. Mechan- ical Systems and Signal Processing, 14:763–788, 2000.
(Malhi and Gao, 2004) Arnaz Malhi and Robert X. Gao. PCA-based feature selection scheme for machine defect classification. IEEE Transcations on Instrumentation and Measurement, 53:1517–1525, 2004.
(Mori et al., 1996) K. Mori, N. Kasashmi, T. Yosh- ioka, and Y. Ueno. Prediction of spalling on ball bearings by applying discrete wavelet transform to vibration signals. Wear, 8:195–162, 1996.
(Nataraj and Pietrusko, 2005) C. Nataraj and Robert Gerad Pietrusko. Dynamic response of rigid rotors supported on rolling element bearings with an outer raceway defect. In ASME, editor, Proceedings of IDETC/CIE 2005, Long Beach California, USA, September 2005.
(Ocak et al., 2007) Hasan Ocak, Kenneth A. Loparo, and Fred M. Discenzo. Online tracking of bearing wear using wavelet packet decomposition and probabilistic modeling. Journal of Sound and Vibration, 302:951–961, 2007.
(Pan et al., 2009) Yuna Pan, Jin Chen, and Lei Guo. Robust bearing performance degradation assessment method based on improved wavelet packet - support vector data descriptions. Mechanical Systems and Signal Processing, 23:669–681, 2009.
(Peng et al., 2005) Hanchuan Peng, Fuhui Long, and Chris Ding. Feature selection based on mutual information : Criteria of max-dependency , max- relevance and min-redundancy. IEEE Transactions on Pattern Analysis and Machine Intelligence, 27:1226–1238, 2005.
(Randall and Gao, 1994) R. B. Randall and Y. Gao. Extraction of modal parameters from the response of power cepstrum. Journal of Sound and Vibration, 176:179–193, 1994.
(Randall and Sawalhi, 2009) R.B. Randall and N. Sawalhi. Signal processing tools for tracking the size of a spall in a rolling element bearing. In IUTAM Symposium on Emerging Trends in Rotor Dynamics, 2009.
(Randall, 1987) R. B. Randall. Frequency Analysis. Bruel & Kjaer, Naerum, Denmark, 1987.
(Raymer et al., 2000) Michael L. Raymer, William F. Punch, Erik D. Goodman, Leslie A. Kuhn, and Anil K. Jain. Dimensionality reduction using genetic algorithms. IEEE Transactions on Evolution- ary Computation, 4:164–171, 2000.
(Sawalhi and Randall, 2008) N. Sawalhi and R. B. Randall. Simulating gear and bearing interactions in the presence of faults part1. the combined gear bearing model and simulation of localized bearing faults. Mechanical Systems and Signal Processing, 22:1924–1951, 2008.
(Spectra Quest, 2009) Inc Spectra Quest. Http: www.spectraquest.com, 2009.
(Sugumaran et al., 2007) V. Sugumaran, V. Muralidharan, and K. I. Ramachandran. Feature selection using decision tree and classification through prox- imal support vector machine for fault diagnostics of roller bearing. Mechanical Systems and Signal Processing, 21:930–942, 2007.
(Tandon, 1994) N. Tandon. A comparision of some vibration parameters for condition monitoring of rolling element bearings. Measurement, 12:285– 286, 1994.
(Wu and Liu, 2008) Jian-Da Wu and Chiu-Hong Liu. Investigation of engine fault diagnosis using discrete wavelet transform and neural network. Expert Systems and Applications, 35:1200–1213, 2008.
(Ypma, 2001) A. Ypma. Learning Methods of Machine Vibration Analysis and Health Monitoring. PhD thesis, Delft University, 2001.
This work is licensed under a Creative Commons Attribution 3.0 Unported License.
The Prognostic and Health Management Society advocates open-access to scientific data and uses a Creative Commons license for publishing and distributing any papers. A Creative Commons license does not relinquish the author’s copyright; rather it allows them to share some of their rights with any member of the public under certain conditions whilst enjoying full legal protection. By submitting an article to the International Conference of the Prognostics and Health Management Society, the authors agree to be bound by the associated terms and conditions including the following:
As the author, you retain the copyright to your Work. By submitting your Work, you are granting anybody the right to copy, distribute and transmit your Work and to adapt your Work with proper attribution under the terms of the Creative Commons Attribution 3.0 United States license. You assign rights to the Prognostics and Health Management Society to publish and disseminate your Work through electronic and print media if it is accepted for publication. A license note citing the Creative Commons Attribution 3.0 United States License as shown below needs to be placed in the footnote on the first page of the article.
First Author et al. This is an open-access article distributed under the terms of the Creative Commons Attribution 3.0 United States License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.