Bearing Fault Diagnosis Using Vibration Signals by Variational Mode Decomposition and Naïve Bayes Classifier

Muralidharan A, Sugumaran V, Soman KP

Abstract


A bearing is a machine element that constrains relative motion and reduces friction between moving parts in the desired motion. A faulty bearing is a serious threat to the functionality of a machine, be it big or small. Thus, it is essential to diagnose the faults in the bearings at an earlier stage so as to reduce the losses that might be incurred in money and time. Inability to meet the required demand of products in the specific time due to improper functioning of the bearing is another reason of concern. Hence, there is a necessity for continuous monitoring of the bearing. The vibrations and the sounds produced by the bearings from good and simulated faulty conditions can be effectively used to detect the faults in these bearings. The use of Variational Mode Decomposition (VMD) in the study allows decomposition of the signal into various modes by identifying a compact frequency support around its central frequency, such that adding all the modes reconstructs the original signal. VMD finds intrinsic mode functions on central frequencies using alternating direction multiplier method (ADMM). Worthwhile statistical features can be extracted from VMD processed signals. J48 decision tree algorithm was used to identify the useful features and the selected features were used for classification using the Naïve Bayes Classifier. The performance analysis of Naïve Bayes Classifier is elaborately discussed.

Full Text:

PDF

References


Changsen W. Analysis of rolling element bearings. London: Mechanical Engineering Pub. Limited; 1991.

Benbouzid M, Kliman GB. What stator current processing-based technique to use for induction motor rotor faults diagnosis? IEEE Trans. on Energy Conversion. 2003; 18(2): 238–44p.

Li B, Chow MY, Tipsuwan Y, et al. Neural-network-based motor rolling bearing fault diagnosis. IEEE Trans. on Industrial Electronics. 2000; 47(5): 1060–69p.

Nandi S, Toliyat HA. Condition monitoring and fault diagnosis of electrical machine, Proceedings of IEEE IAS Annual Meeting Conference. 1999; 197–204p.

Mathew J, Alfredson RJ. The Condition Monitoring of Rolling Element Bearings using Vibration Analysis. Journal of Vibration, Acoustics, Stress and Reliability in Design.1984; 106:447–53p.

Kim PY. A Review of Rolling Element Bearing Monitoring (III): Preliminary Test Results on Eddy Current Transducer Technique. Proceedings of Third International Conference on Vibrations in Rotating Machinery. The Institution of Mechanical Engineers, York, England; 1984; 119–25p.

Yu JJ, Bently DE, Goldman P, et al. Rolling Element Bearing Defect Detection and Diagnostics Using Displacement Transducers. ASME; Paper 2001-GT-28.

Detection of Rolling Element Bearing Defects in Time Base. Bently Rotor Dynamics Research Corporation. 2000.

Zvokelj M, Zupan S, Prebil I. Multivariate and multiscale monitoring of large-size low-speed bearings using Ensemble Empirical Mode Decomposition method combined with Principal Component Analysis. Mechanical Systems and Signal Processing. 2010; 24: 1049–67p.

Li CJ, Ma J. Wavelet decomposition of vibrations for detection of bearing localized defects. NDT&E International. 1997; 30 (3): 143–9p.

Kumar H, Kumar TAR, Sugumaran V, et al. Fault Diagnosis of Bearings through Vibration Signal Using Bayes Classifiers. International Journal of Computer Aided Engineering and Technology. 2012.

Amarnath HM, Sugumaran V. Exploiting Sound Signals for Fault

Diagnosis of Bearings Using Decision Tree, Measurements. 2013; 46(3): 1250–56p.

Sugumaran V, Muralidharan V, Ramachandran KI. Feature selection using Decision Tree and classification through Proximal Support Vector Machine for fault diagnostics of roller bearing. Mechanical Systems and Signal Processing. 2007; 21(2): 930–42p.

Loutridis SJ. Damage detection in gear systems using Empirical mode decomposition Engineering Structures. 2004; 26(12): 1833–41p.

Yu D, Cheng J, Yang Y. Application of EMD method and Hilbert spectrum to the fault diagnosis of roller bearings. Mechanical systems and signal processing. 2005; 19(2): 259–70p.

Gao Q, Duan C, Fan H, et al. Rotating machine fault diagnosis using Empirical mode decomposition. Mechanical systems and signal processing.2008; 22(5): 1072–81p.

Lei YG, Zuo MJ, He ZJ, et al. A multidimensional hybrid intelligent method for gear fault diagnosis. Expert systems with applications. 2010; 37:1419–30p.

Rilling G, Flandrinand P, Goncalves P. on Emperical Mode Decomposition and its Algorithms. IEEE-EURASIP Workshop on Nonlinear Signal and Image Processing NSIP-03; 2003. Grado (I)

Huang N, Shen Z, Long SR, et al. The empirical mode decomposition and Hilbert spectrum for non-linear non-stationary time series analysis. Proceedings of Royal Society of London;




DOI: https://doi.org/10.37628/ijra.v1i1.1

Refbacks

  • There are currently no refbacks.