Abstract
The paper presents a new approach to the classification of rolling element bearing faults by implementing statistical pattern recognition. Diagnostics of rolling element bearing faults actually represents the problem of pattern classification and recognition, where the key step is feature extraction from the vibration signal. Characterization of each recorded vibration signal is performed by a combination of signal's time-varying statistical parameters and characteristic rolling element bearing fault frequency components obtained through the envelope analysis method. In this way, an 18-dimensional vector of the vibration signal feature is obtained. Dimension reduction of the 18-dimensional feature vectors was performed afterward into two-dimensional vectors representing the training set for the design of parameter classifiers. The classification was performed in two classes, into defective and functional rolling element bearings. Main trait of parameter classifiers is simplicity in their design process, as opposed to classifiers based on neural networks, which employ complex training algorithms.
Similar content being viewed by others
References
Pan F, Qin SR, Bo L (2006) Development of diagnosis system for rolling bearings faults based on virtual instrument technology. J Phys Conf Ser 48:467–473. doi:10.1088/1742-6596/48/1/089
J Courrech, M Gaudet (1985) Envelope analysis—the key to rolling element bearing diagnosis. Brüel & Kjær, Denmark
H Konstantin-Hansen (2003) Envelope analysis for diagnostics of local faults in rolling element bearings. Brüel & Kjær, Denmark
McCormick AC, Loskiewicz-Buczak A, Uhrig RE (1998) Application of periodic time-varying autoregressive models to the detection of bearing faults. Proc IME J Mater Des Appl 212(part C):417–428
Baillie DC, Mathew J (1994) Nonlinear model-based fault diagnosis of bearings. Proc. of Int. Conf. on Condition, Monitoring, University of Wales, 241–252
Samanta B, Al-Balushi KR (2003) Artificial neural network based fault diagnostics of rolling element bearings using time-domain features. Mech Syst Signal Process 17(2):317–328. doi:10.1006/mssp. 2001.1462
Lindh T (2003) On the condition monitoring of induction machines. Thesis for the degree of Doctor of Science, Lappeenranta University of Technology
Sun W, Chen J, Li J (2007) Decision tree and PCA-based fault diagnosis of rotating machinery. Mech Syst Signal Process 21:1300–1317. doi:10.1016/j.ymssp. 2006.06.010
Fukunaga K (1990) Introduction to statistical pattern recognition. Academic, Boston
Theodoridis S, Koutroumbas K (2003) Pattern recognition. Academic, San Diego
Yang J, Zhang Y, Zhu Y (2006) Intelligent fault diagnosis of rolling element bearing based on svms and fractal dimension. Mec Syst Signal Process 21:2012–2024
SKF Reliability Systems (2004) Early warning fault detection in rolling element bearing using microlog enveloping. Application Note. http://www.skf.com/files/056590.pdf
Ericsson S, Grip N, Johansson E, Persson L-E, Sjöberg R, Strömberg J-O (2005) Towards automatic detection of local bearing defects in rotating machines. Mech Syst Signal Process 19(3):509–535. doi:10.1016/j.ymssp. 2003.12.004
B Geropp (1997) Envelope analysis—a signal analysis technique for early detection and isolation of machine faults. ACIDA GmbH, Kaiserstr. 100, D-52134 Herzogenrath, Germany
Ho D, Randall RB (2000) Optimisation of bearing diagnostic techniques using simulated and actual bearing fault signals. Mech Syst Signal Process 14(5):763–788. doi:10.1006/mssp. 2000.1304
Author information
Authors and Affiliations
Corresponding author
Additional information
†Ilija V. Latinovic – deceased
Rights and permissions
About this article
Cite this article
Stepanic, P., Latinovic, I.V. & Djurovic, Z. A new approach to detection of defects in rolling element bearings based on statistical pattern recognition. Int J Adv Manuf Technol 45, 91–100 (2009). https://doi.org/10.1007/s00170-009-1953-7
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00170-009-1953-7