Tractor Engine Fault Detection System Based on Vibration and Acoustic Monitoring

Year 2011, Volume: 7 Issue: 1, 1 - 6, 01.02.2011

Dimitrios Moshou Athanasios Natsıs Dimitrios Katerıs İoannis Gravalos Nader Sawalhı İoannis Kalımanıs Spyridon Loutrıdıs Theodoros Gıalamas Panayiotis Xyradakıs Zisis Tsıropoulos

Abstract

A
tractor gearbox test rig has been used to collect signals from different types
of bearing faults. For vibration monitoring accelerometers have been used to
obtain vibtation data. For fuel injectors a Bearing Checker has been used in
order to collect acoustic data. Least squares support vector machines (LS-SVM) are used for detecting faults when exposed to
actual data from the system representing a yet unknown state. Feature extraction
was performed using seven features. The feature vectors are then fed to the
LS-SVM for training. LS-SVM classification gave promising results (more than 95% correct classification). The fusion of
features from both the vertical and the horizontal accelerometer resulted in
more accurate separation of classes regarding fault position. In the case of
the fuel injectors the feasibility of using one-class SVM has been tested in
the detection of signal deviations indicating failure with high detection performance.

Keywords

Vibration, condition monitoring, SVM, bearing

References

• McFadden P. D., J. D. Smith, 1984. Vibration monitoring of rolling element bearings by the high-frequency resonance technique – A review. Tribology International, 17(1): 3–10.
• Paya B. A., I. I. Esat, M. N. M. Badi, 1997. Artificial neural network based fault diagnostics of rotating machinery using wavelet transforms as a preprocessor. Mechanical Systems and Signal Processing, 11(5): 751–765.
• Pelckmans K., J.A.K. Suykens, T. Van Gestel, J. De Brabanter, L. Lukas, B. Hamers, B. De Moor, J. Vandewalle, 2002. LS-SVMlab: a Matlab/C toolbox for Least Squares Support Vector Machines., Internal Report 02-44, ESAT-SISTA, K.U.Leuven (Leuven, Belgium).
• Sawalhi N., 2007. Diagnostics, Prognostics and Fault Simulation for Rolling Element Bearings, PhD Thesis, University of New South Wales, Australia.
• Scholkopf B., J. Platt, J. Shawe-Taylor, A. Smola, and R. Williamson, 2001. Estimating the support of a highdimensional distribution. Neural Computation, 13(7): 1443–1472.
• Suykens J.A.K., J. Vandewalle, 1999. Least Squares Support Vector Machine Classifiers. Neural Processing Letters, 9: 293–300. Vapnik V.N., 1998. Statistical Learning Theory. New York: Wiley Interscience.
• Vapnik V.N., 1999. The Nature of Statistical Learning Theory. New York: Springer-Verlag.
• Xu Z, J. Xuan., T. Shi, B. Wu, Y. Hu, 2009. Application of a modified fuzzy ARTMAP with feature-weight learning for the fault diagnosis of bearing. Expert Systems with Applications, 36: 9961-9968.