Gear Fault Classification Using Kernel Discriminant Analysis


Article Preview

This paper presents a study of KDA(kernel discriminant analysis) in gearbox failure feature extraction and classification. Experimental gearbox vibration signals measured from normal, gear small spall, gear severe spall and gear wear operating conditions are analyzed using either KPCA(kernel principal component analysis) or KDA as the feature extraction and fault classification methods. Experiment results indicate the effectiveness and thesuperiority of KDA for gear fault classification over KPCA.



Key Engineering Materials (Volumes 321-323)

Edited by:

Seung-Seok Lee, Joon Hyun Lee, Ik Keun Park, Sung-Jin Song, Man Yong Choi






W. H. Li et al., "Gear Fault Classification Using Kernel Discriminant Analysis", Key Engineering Materials, Vols. 321-323, pp. 1556-1559, 2006

Online since:

October 2006




[1] Weihua Li, Guanglan Liao�Tielin Shi, Shuzi Yang. Feature extraction and Classification of gear faults using principal component analysis. Journal of Quality in Maintenance Engineering. Vol9. No. 2 (2003): pp.132-143.

DOI: 10.1108/13552510310482389

[2] B. Schölkopf, A. Smola, K. R. Müller. Nonlinear Component Analysis as a Kernel Eigenvalue Problem. Neural Computation. Vol10 (1998): pp.1299-1319.

DOI: 10.1162/089976698300017467

[3] G. Baudat, F. Anouar. Generalized Discriminant Analysis Using a Kernel Approach. Neural Computation. Vol12. No10(2000): pp.2385-2404.

DOI: 10.1162/089976600300014980

[4] Leduc. V, Kanny. G, Moneret-Vautrin. DA, et al. Diagnostic de l'allergie aux graines de Sésame: choix de la matière première et optimisation du procédé de fabrication. Revue Francaise d'Allergologie et d'Immunologie Clinique., Vol41. No1 (2001).

DOI: 10.1016/s0335-7457(01)80077-0

In order to see related information, you need to Login.