Open Access Open Access  Restricted Access Subscription or Fee Access

A Comprehensive Study of Fault Diagnostics of Roller Bearings Using Continuous Wavelet Transform

V Sugumaran, Aditya Vasudev Rao, K. I. Ramachandran

Abstract


One of the prominent causes of breakdown of rotating machinery, bearing failure, proves to be costly to the industry. Unexpected machine stoppage disrupts production schedule and maintenance strategies. Therefore, condition monitoring has become a very important research field in recent years. It can be used to avoid unexpected failures of critical systems. Bearing fault diagnostics using vibration signals has proven to be very effective. This paper deals with the fault detection and classification of roller bearings using Continuous Wavelet Transform. This paper is the result of an exhaustive study of different families wavelets and the determination of the best wavelet for the purpose. A decision tree is constructed using the C4.5 algorithm to determine the best wavelet based on classification accuracy. Once the wavelet was selected, those features were used in two classifiers viz. Support Vector Machines (SVM) and Proximal Support Vector Machines (PSVM) to determine classification accuracy. The test results showed that 'rbio1.5' gives maximum classification accuracy among wavelets and PSVM gave 100% classification accuracy for all of the bearing faults thus proving to be most suitable for practical applications

Full Text:

PDF

References


Prabhakar S., Mohanty A.R., Sekhar A.S. Application of discrete wavelet transform for detection of ball bearing race faults. Tribology International. 2002; 35: 793–800p.

Lou X., Loparo K.A. Bearing fault diagnosis based on wavelet transform and fuzzy inference. Mechanical Systems and Signal Processing. 2004; 18:1077–95p.

Sugumaran V., Muralidharan V., Ramachandran K.I. Feature selection using decision tree and classification through proximal support vector machine for fault diagnostics of roller bearing. Mechanical Systems and Signal Processing. 2001; 21: 930–42p.

Abbasion S., Rafsanjani A., Farshidianfar A., et al. Rolling element bearings multi-fault classification based on the wavelet denoising and support vector machine. Mechanical Systems and Signal Processing. 2007; 21: 2933–45p.

Yu G., Li C., Kamarthi S. Machine fault diagnosis using a cluster-based wavelet feature extraction and probabilistic neural networks. International Journal of Advance Manufacturing Technology. 2009; 42: 145–51p.

Li Y. Study on Incipient Fault Diagnosis for Rolling Bearings Based on Wavelet and Neural Networks. 4th International Conference on Natural Computation. 2008 Oct 18–20; Jinan. IEEE; 2008. 262–5p.

Wang D., Miao Q., Fan X., et al. Rolling element bearing fault detection using an improved combination of Hilbert and Wavelet transforms. Journal of Mechanical Science and Technology. 2009; 23: 3292-3301p.

Su W., Wang F. , Zhu H., Zhixin et al. Rolling element bearing faults diagnosis based on optimal Morlet wavelet filter and autocorrelation enhancement. Mechanical Systems and Signal Processing. 2010; 24: 1458–72p.

Chebil J., Noel G., Mesbah M., et al. Wavelet Decomposition for the Detection and Diagnosis of Faults in Rolling Element Bearings. Jordan Journal of Mechanical and Industrial Engineering. 2009; 3( 4): 260–7p.

Kankar P.K., Sharma S.C., Harsha S.P. Fault diagnosis of ball bearings using continuous wavelet transform. Applied Soft Computing. 2011;11: 2300–12p.

Saravanan N., Ramachandran K.I. Incipient gear box fault diagnosis using discrete wavelet transform (DWT) for feature extraction and classification using artificial neural network (ANN). Expert Systems with Applications. 2010; 37: 4168–81p.

Konar P., Chattopadhyay P. Bearing fault detection of induction motor using wavelet and Support Vector Machines (SVM). Applied Soft Computing. 2011;11: 4203–11p.

Li H., Fu L., Zheng H. Bearing fault diagnosis based on amplitude and phase map of Hermitian wavelet transform. Journal of Mechanical Science and Technology. 2011; 25: 2731–40p.

Feng K., Jiang Z., He W., et al. Rolling element bearing fault detection based on optimal antisymmetric real Laplace wavelet. Measurement. 2011; 44: 1582–91p.

Kanneg D., Wang W. A Wavelet Spectrum Technique for Machinery Fault Diagnosis. Journal of Signal and Information Processing 2011; 2: 322–9p.

Bendjama H., Bouhouche S., Boucherit M.S. Application of Wavelet Transform for Fault Diagnosis in Rotating Machinery. International Journal of Machine Learning and Computing. 2012; 2(1): 82–7p.

Chen K., Li X., Wang F., et al. Bearing Fault Diagnosis Using Wavelet Analysis. International Conference on Quality, Reliability, Risk, Maintenance, and Safety Engineering. (ICQR2MSE). 2012 June 15–18; Chengdu. 2012. 699–702p.

Li P., Kong F., He Q., et al. Multiscale slope feature extraction for rotating machinery fault diagnosis using wavelet analysis. Measurement. 2013; 46: 497–505p.

Shen C., Wang D., Kong F, et al. Fault diagnosis of rotating machinery based on the statistical parameters of wavelet packet paving and a generic support vector regressive classifier. Measurement. 2013; 46: 1551–64p.

Muralidharan V., Sugumaran V. A comparative study of Naïve Bayes classifier and Bayes net classifier for fault diagnosis of monoblock centrifugal pump using wavelet analysis. Applied Soft Computing. 2012; 12: 2023–9p.

Muralidharan V., Sugumaran V. Feature extraction using wavelets and classification through decision tree algorithm for fault diagnosis of mono-block centrifugal pump. Measurement. 2013; 46: 353–9p.

Kumar H.S., Dr. Srinivasa P.P., Sriram N.S., et al. ANN based evaluation of performance of wavelet transform for condition monitoring of rolling element bearing. International Conference On Design And Manufacturing, IConDM 2013. Procedia Engineering. 2013; 64: 805–14p.

Meng L., Xiang J., Wang Y., et al. A hybrid fault diagnosis method using morphological filter–translation invariant wavelet and improved ensemble empirical mode decomposition. Mechanical Systems and Signal Processing. 2015; 50–51: 101–15p.


Refbacks

  • There are currently no refbacks.