Multiscale fuzzy entropy and its application in rolling bearing fault diagnosis
Zheng Jin-d · 2014
A new method which is referred as multiscale fuzzy entropy(MFE)is introduced for measuring the complexity of time series.Fuzzy entropy is defined to measure the complexity and irregularity of time series,while multiscale entropy which is based on fuzzy entropy is defined to measure the complexity and irregularity of time series in different scale factors.Compared with sample entropy,fuzzy entropy,fractal dimension or other complexity measure methods of nonlinear dynamics,multiscale fuzzy entropy contains more and deeper information of time series.In this paper,the concepts of fuzzy entropy and multiscale fuzzy entropy are introduced firstly,and then they are used to measure the complexity of the rolling bearing vibration signals.Lastly,a new rolling bearing fault diagnosis approach based on multiscale fuzzy entropy and support vector machine(SVM)is put forward.By analysing experimental data,the results show that the proposed method can differentiate the fault categories of rolling bearings effectively.