Gearboz Failure Detection using An Modified Kernel Principal Component Analysis
Monitoring and diagnostic systems have played an important role in modern industry. Many intelligent or signal processing methods have been successfully applied in the manufacturing process. This paper presents a study of feature samples selection and kernel principal component analysis (FSKPCA) in gearbox condition monitoring. The key issues studied in this paper are nonlinear feature extraction, optimal feature samples selection, and diagnostic performance assessment. Firstly, the integral operator Gaussian kernel function is used to realize the nonlinear map from the raw input space of gearbox vibration features to a high dimensional space, where appropriate feature samples are selected to construct the feature subspace. Then PCA is used to classify two kinds of gearbox running conditions: normal and tooth crack. The quantity of selected samples is much less than that of whole sample sets, which has quickly expedited the computation process. Experiment results indicate the effectiveness of FS-KPCA for gearbox condition monitoring and fault diagnosis.
Failure detection Feature samples selection Kernel function Principal component analysis
Weihua Li Yabing Xu
School of Mechanical and Automotive Engineering, Guangdong Key Laboratory of Automotive Engineering, South China University of Technology, Guangzhou,510640, CHINA
国际会议
2008 Sino-European Workshop on Intelligent Robots and Systems(SEIROS08)(第一届中欧智能系统及机器人国际学术研讨会)
重庆
英文
1-7
2008-12-11（万方平台首次上网日期，不代表论文的发表时间）