A method based on SVMD and improved DELM for fault classification of rolling bearings
In order to address the problems of difficult feature extraction and low accuracy of fault classification in rolling bearing fault diagnosis,a bearing fault diagnosis method based on Successive Variational Mode Decomposition(SVMD),Fractal Dimension(FD),Arithmetic Optimization Algorithm(AOA)and Deep Extreme Learning Machine(DELM)was proposed.A series of intrinsic mode functions(IMFs)were obtained by SVMD of the original vibration signals of bearings.The FD of each component under different states are calculated and normalized as the fault feature vectors.The AOA-DELM model was applied to achieve the fault diagnosis of bearings.The Case Western Reserve University(CWRU)bearing data set was used as the experimental data for validation.The results showed that the proposed method was superior in rolling bearing fault classification diagnosis,and the recognition accuracy can reach 98.80%.
NETL
NSTL
万方数据
