Bearing Fault Diagnosis Based on VMD Fuzzy Entropy and Improved Deep Belief Networks

Background The bearing is an important component of mechanical transmission, and its condition is closely related to the safe operation of the equipment. However, the nonlinear vibration signal of the bearing leads to low accuracy of fault diagnosis because it is difficult to extract bearing characteristics. Method To solve this problem, a bearing fault diagnosis method based on variational mode decomposition (VMD) fuzzy entropy (FE) and improved deep belief networks (DBN) is proposed. Since the information on bearing characteristics is overlaid by strong noise, VMD is used to process the vibration signal and calculate the FE of the modal components. Then, an improved butterfly optimization algorithm (BOA) with a mixed strategy is proposed, and the improved BOA is applied to optimize the hyper-parameters of the DBN to obtain the optimized DBN model. Finally, the optimized DBN is used as a pattern recognition algorithm for fault diagnosis. Results The two experimental results show that this method can effectively diagnose bearing faults. The diagnosis rates are 98.33 % and 100 %, respectively, which provide theoretical support for bearing fault diagnosis.