» Download Article

Authors
Kilundu, Bovic; Letot, Christophe; Dehombreux, Pierre; Chiementin, Xavier

Digital Object Identifier (DOI)
10.3182/20081205-2-CL-4009.00038

Page Numbers:
211-215

Index Terms
damage detection,bearing damage,envelope detection,decision trees,preventive maintenance

Abstract
This paper presents a procedure for early detection of rolling bearing damages on the basis of vibration measurements. First, an envelope analysis is performed on bandpass filtered signals. For each frequency range, a feature indicator is defined as sum of spectral lines. These features are passed through a principal component model to generate a single variable which allows to track change in the bearing health. Thresholds and rules for early detection are learned thanks to decision trees. Experimental results demonstrate that this procedure enables early detection of bearing defects.

References

[1] Chen, Y. (1993). Impending failure detection for a discrete
    process. Mechanical Systems and Signal Processing,
    7(2), 121-132.
[2] Chen, Z. (2000). Computational intelligence for decision
    support. CRC Press LLC, New York.
[3] Courrech, J. and Eshleman, R. (2002). Harri's Shock and
    Vibration Handbook, chapter Condition monitoring of
    machinery, 16.1-16.25. McGRAW-HILL.
[4] Dron, J.P., Bolaers, F., and Rasolofondraibe, L. (2003).
    Optimisation de la détection de defauts de roulements
    par débruitage des signaux par soustraction spectrale.
    Mécanique et Industries, 4(3), 213-219.
[5] Gebraeel, N., Lawley, M., Liu, C.R., and Parmeshwaran
    (2004). Residual life predictions from vibration-based
    degradation signals: A neural network approach. IEEE
    Transactions on Industrial Electronics, 51, 694-700.
[6] Hand, D., Manilla, H., and Smyth, P. (2001). Principles
    of Data Mining. MIT Press.
[7] Harris, T. and Kotzalas, M. (2007). Advanced concepts of
    bearing technology. CRC Press, Taylor & Francis Group.
[8] Iserman, R. (2006). Fault-Diagnosis System. An introduction
    from fault detection to fault tolerance. Springer.
[9] Li, Y., Zhang, C., Kurfess, T., Danyluk, S., and Liang,
    S. (1999). Adaptative prognostics for rolling element
    bearing condition. Mechanical Systems and Signal Processing,
    13(1), 103-113.
[10] MacGregor, J., Kourti, T., and Nomikos, P. (1996). Analysis,
     monitoring and fault diagnosis of industrial processes
     using multivariate statistical projection methodes.
     In Proceedings of IFAC Congress, volume M, 145-
     150. San Francisco.
[11] Mohamed-Faouzi, H. (2003). Détection et Localisation de
     Défauts par Analyse en Composantes Principales. Ph.D.
     thesis, Institut National Polytechnique de Lorraine.
[12] Qiu, J., Zhang, C., Seth, B., and Liang, S. (2002). Damage
     mechanics approach for bearing lifetime prognostics.
     Mechanical Systems and Signal Processing, 16(5), 817-
     829.
[13] Quinlan, R. (1993). C4.5: Programs for Machine Learning.
     Morgan Kaufmann Publishers, San Mateo, CA.
[14] Sugumaran, V. and Ramachandran, K. (2007). Automatic
     rule learning using decision tree for fuzzy classifier in
     fault diagnosis of roller bearing. Mechanical Systems
     and Signal Processing, 21(5), 2237-2247.
[15] Tandon, N. and Choudhury, A. (1999). A review of vibration
     and acoustic measurement methods for the detection
     of defects in rolling element bearings. Tribology
     International, 32(8), 469-480.