Open AccessFault diagnosis of rolling bearing based on improved EMD algorithm
Author(s) -
Shuo Meng,
Jianshe Kang,
Kuo Chi,
Xupeng Die
Publication year - 2020
Publication title -
iop conference series. materials science and engineering
Language(s) - English
Resource type - Journals
eISSN - 1757-899X
pISSN - 1757-8981
DOI - 10.1088/1757-899x/892/1/012069
Subject(s) - hilbert–huang transform , kurtosis , fault (geology) , algorithm , bearing (navigation) , computer science , entropy (arrow of time) , waveform , pattern recognition (psychology) , artificial intelligence , mathematics , statistics , telecommunications , radar , physics , quantum mechanics , seismology , filter (signal processing) , computer vision , geology
The EMD (Empirical mode decomposition) is a good method to diagnose faults of equipment, but the endpoint effect and false IMF (Intrinsic Mode Function) of EMD seriously affects the effect of fault diagnosis. So this paper used an adaptive waveform matching extension algorithm to restrain the endpoint effect. To select effective IMF, moreover, this paper put forward another method which is based on information entropy and kurtosis value. Finally, the paper used the two methods combined with HHT to diagnose the bearing fault, the experimental results show that the above problems have been effectively solved and the fault diagnosis effect has been significantly improved.