%0 Journal Article
%A CHEN Kang
%A LIU Tong-yi
%A WANG Ying-bo
%A XU Tong-le
%A ZHENG Dian-kun
%T Research of the Rolling Bearing Fault Signal Feature Extraction Method Based on the LMD-ICA Noise Reduction
%D 2017
%R 10.13190/j.jbupt.2017.01.020
%J Journal of Beijing University of Posts and Telecommunications
%P 111-116
%V 40
%N 1
%X Aiming at the problem of existing the end effect, easily producing false component. The local mean decomposition (LMD) was used in analysis of non-stationary and nonlinear signals containing noise and the underdetermined problem of the single channel independent component analysis (ICA) blind source separation, the feature extraction algorithm of the vibration signals based on the noise reduction LMD-ICA was proposed. By applying the algorithm, the fault of rolling bearing is diagnosed, firstly, the original signals are decomposed by LMD, the <em>n</em> instantaneous frequency product function (PF) components with physical significance are obtained and the end effect is limited. Then the obtained PF components which are arranged into one sequence combination per constant third-order PF components are analyzed by independent component. And <em>n</em>-2 refactoring components can be obtained by ICA. At last, the fault signals of which the noises are reduced are decomposed by LMD or calculated by power spectrum again to extract the fault. According to the experiment, the multi-types fault signals of rolling bearing can be effectively recognized by the method proposed above.
%U https://journal.bupt.edu.cn/EN/10.13190/j.jbupt.2017.01.020