Fault Diagnosis of Rolling Bearings Based on Multi-Scale Entropy and Ensembled Artificial Neural Network

Rolling bearing is widely used in rotating mechanical system, and its operating state has great effects on availability, reliability and the life cycle of whole mechanical system. Therefore, fault diagnosis of rolling bearing is indispensable for the health monitoring in rotating machinery system. In this paper, a method based on multi-scale entropy (MSE) and ensembled artificial neural network (EANN) is proposed for feature extraction and fault recognition in rolling bearings respectively. MSE is mainly in charge for quantizing the complexity of the nonlinear time series in different scales. Then, EANN is employed to identify various faults of rolling bearing after overcoming the two disadvantages like local minimization and slow convergence speed in back propagation neural network (BPNN). The experimental results indicate that the method based on MSE and EANN is feasible and effective to classify different categories of faults and to identify the severity level of fault in the rolling bearings. Therefore, it is available for fault detection and diagnosis in rolling bearings with good performance.