A Fault diagnosis method for Rolling Bearing based on Empirical Mode Decomposition and Principal Component Analysis
Xu Zhuofei1 LIU Kai1 Zhang Haiyan2 Wang Dan1 Zhang Minglong2 Wu Xinyang2
1 School of Mechanical and Precision Instrument Engineering, Xi`an University of Technology, Xi`an 710048;2 School of Printing and Packaging Engineering, Xi`an University of Technology, Xi`an 710048
Abstract:A new fault diagnosis method for rolling and bearing based on empirical mode decomposition and multivariate statistics is proposed. The Hilbert-Huang transform and principal component analysis are used in this method. The vibration signal is decomposed into the basic mode components with EMD and the instantaneous frequency of each component is obtained with a Hilbert-Huang transform. Then calculate the statistical characteristics of the instantaneous frequency and the time domain signal. Analyses the statistical characteristics with PCA in order to reduce the number of dimensions of the feature vector and get the principal component characteristics. Finally, complete the classification of three failure modes in rolling bearing and analyze the relationship between the statistical characteristics and failure modes.
徐卓飞 刘凯 张海燕 王丹 张明龙 吴欣阳. 基于经验模式分解和主元分析的滚动轴承故障诊断方法研究[J]. , 2014, 33(23): 133-139.
Xu Zhuofei LIU Kai Zhang Haiyan Wang Dan Zhang Minglong Wu Xinyang. A Fault diagnosis method for Rolling Bearing based on Empirical Mode Decomposition and Principal Component Analysis. , 2014, 33(23): 133-139.