Gear Crack Detection Using Kernel Function Approximation
Failure detection in machine condition monitoring involves a classification mainly on the basis of data from normal operation, which is essentially a problem of one-class classification. Inspired by the successful application of KFA (Kernel Function Approximation) in classification problems, an approach of KFA-based normal condition domain description is proposed for outlier detection. By selecting the feature samples of normal condition, the boundary of normal condition can be determined. The outside of this normal domain is considered as the field of outlier. Experiment results indicated that this method can be effectively and successfully applied to gear crack diagnosis.
KeywordsFeature Vector Fault Diagnosis Kernel Principal Component Analysis Support Vector Data Description Machine Condition Monitoring
Unable to display preview. Download preview PDF.
- 2.Ypma, A.: Learning Methods for Machine Vibration Analysis and Health Monitoring, Ph.D. Dissertation. Delft University of Technology (2001)Google Scholar
- 4.Addison, J., Wermter, S., McGarry, K., Macintyre, J.: Methods for integrating memory into neural networks in condition monitoring. In: Proc. International Conference on Artificial Intelligence and Soft Computing, Alberta, Canada, pp. 380–384 (2002)Google Scholar
- 10.Campbell, C., Bennett, K.P.: A linear programming approach to novelty detection. Advances in NIPS, vol. 14. MIT Press, Cambridge (2001)Google Scholar
- 11.Tax, D., Ypma, A., Duin, R.: Support vector data description applied to machine vibration analysis. In: Boasson, M., Kaandorp, J., Tonino, J., Vosselman, M. (eds.) Proc. 5th Annual Conference of the Advanced School for Computing and Imaging, Heijen, pp. 398–405 (1999)Google Scholar
- 13.Li, W.H., Shi, T.L., Yang, S.Z.: Mechanical Fault Classification Using Nonlinear Discriminant Analysis. Journal of Vibration Engineering 18, 133–138 (2005)Google Scholar
- 15.Baudat, G., Anouar, F.: Kernel-based Methods and Function Approximation. In: Proceedings of International Joint Conference on Neural Networks, Washington D.C, pp. 1244–1249 (2001)Google Scholar
- 16.Zhang, G.: Gear Vibration Signature Analysis and Fault Diagnosis, Master thesis. Xi’an Jiaotong University. Xi’an (1993)Google Scholar
- 17.Ma, J., Zhao, Y., Ahalt, S.: OSU SVM Classifier Matlab Toolbox (version 3.00), Ohio State University, Columbus, USA (2002), http://www.ece.osu.edu/~maj/osusvm/