Gear Fault Classification Using Kernel Discriminant Analysis
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.
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