Abstract:The paper proposes the fault diagnosis method for rolling bearing based on compensation distance evaluation technique (CDET)-wavelet kernel principal component analysis (WKPCA). Firstly, use the CDET for dimension reduction. Then the WKPCA is applied to dimension reduced fault feature vectors and better classification result is got. Compared with the classification result based on WPCA directly without dimension reduction using CDET firstly, the classification result of proposed method has the advantages of higher compactness and higher computational efficiency. Besides, the WKPCA has evident advantage over RBF kernel principal component analysis (RKPCA) through verification.
王宏超;陈 进;董广明. 基于补偿距离评估-小波核PCA的滚动轴承故障诊断[J]. , 2013, 32(18): 87-90.
WANG Hong-chao;CHEN Jin;DONG Guang-ming. Fault diagnosis of rolling bearing based on compensation distance evaluation technique-wavelet kernel principal component analysis. , 2013, 32(18): 87-90.