Roller Bearing Fault Diagnosis Combined CEEMD-VMD and Parameter Optimization SVM
In order to solve the difficulty in extracting fault features of roller bearings under complex working environment,a noise reduction method was proposed based on the combination of complementary ensemble empirical mode decomposition(CEEMD)and variational modal decomposition(VMD).Firstly,the collected signals are decomposed by CEEMD,and the components are screened and reconstructed according to the correlation coefficient and kurtosis to generate new signals.Then,VMD was used to decompose the new signal,and the intrinsic mode functions(IMF)were optimized based on the composite index of the combination of envelope entropy and envelope spectrum kurtosis.Finally,the corresponding features were extracted and input into salp swarm optimized support vector machine(SSO-SVM)model to complete the fault diagnosis.The experimental results show that the diagnosis accuracy of normal bearing,bearing inner ring fault and bearing outer ring fault is up to 97.78%.Compared with the single noise reduction method,this method can effectively improve the signal noise ratio of fault signal,and the noise reduction effect is obvious.
国家科技期刊平台
NSTL
万方数据
