Fault diagnosis of rolling bearing based on two-dimensional composite multi-scale ensemble gramian dispersion entropy

One-dimensional ensemble dispersion entropy (EDE 1D ) is an effective nonlinear dynamic analysis method for complexity measurement of time series. However, it is only restricted to assessing the complexity of one-dimensional time series (TS 1D ) with the extracted complexity features only at a single scale. Aiming at these problems, a new nonlinear dynamic analysis method termed two-dimensional composite multi-scale ensemble gramian dispersion entropy (CMEGDE 2D ) is proposed in this paper. First, the TS 1D is transformed into a two-dimensional image (I 2D ) by using gramian angular fields (GAF) with more internal data structures and geometric features, which preserve the global characteristics and time dependence of vibration signals. Second, the I 2D is analyzed at multiple scales through the composite coarse-graining method, which overcomes the limitation of a single scale and provides greater stability compared to traditional coarse-graining methods. Subsequently, a new fault diagnosis method of rolling bearing is proposed based on the proposed CMEGDE 2D for fault feature extraction and the chicken swarm algorithm optimized support vector machine (CSO-SVM) for fault pattern identification. The simulation signals and two data sets of rolling bearings are utilized to verify the effectiveness of the proposed fault diagnosis method. The results demonstrate that the proposed method has stronger discrimination ability, higher fault diagnosis accuracy and better stability than the other compared methods.