A novel bearing faults detection method using generalized gaussian distribution refined composite multiscale dispersion entropy

Rolling element bearings are a critical component of rotating machines, and the presence of defects in the bearings may eventually lead to machine failure. Hence, early identification of such defects and severity assessment may avoid malfunctioning and breakdown of machines. Vibration signal features are often used to build fault diagnosis and fault classification systems. In this article, a novel refined composite multiscale dispersion entropy (RCMDE)-based feature is proposed using a nonlinear mapping approach using the generalized Gaussian distribution (GGD)-cumulative distribution function (cdf) with the different shape parameter β. This work combines the GGD dispersion entropy (DE) algorithm within the RCMDE framework with a feature selection algorithm, which is then used as input to a multiclass support vector machine (MCSVM) model for categorizing rolling element bearings' fault conditions. The proposed method is validated using Case Western Reserve University (CWRU), Jiangnan University (JNU), and Southeast University (SEU) datasets. The experimental analysis shows that the GGD-RCMDE features are better in terms of classification accuracy, precision, recall, and F1-score when compared with the existing approaches.