Bearing fault diagnosis based on adaptive mutiscale fuzzy entropy and support vector machine

This paper proposes a new rolling bearing fault diagnosis method based on adaptive multiscale fuzzy entropy (AMFE) and support vector machine (SVM). Unlike existing multiscale Fuzzy entropy (MFE) algorithms, the scales of AMFE method are adaptively determined by using the robust Hermite-local mean decomposition (HLMD) method. AMFE method can be achieved by calculating the Fuzzy Entropy (FuzzyEn) of residual sums of the product functions (PFs) through consecutive removal of high-frequency components. Subsequently, the obtained fault features are fed into the multi-fault classifier SVM to automatically fulfill the fault patterns recognition. The experimental results show that the proposed method outperforms the traditional MFE method for the nonlinear and non-stationary signal analysis, which can be applied to recognize the different categories of rolling bearings.