Extracting the shock features in the fault signals of reciprocating compressor valves and identifing the non-linear and non-stationary characteristics involved have been the hot and difficult issues in this research field.In order to effectively extract the characteristic information in the reciprocating compressor signal,a feature extraction method based on improved variational mode decomposition(VMD)and fuzzy entropy(FE)is proposed in this paper.Firstly,the beluga whale optimization(BWO)algorithm is used to optimize the variational mode decomposition algorithm,and the core parameters(number of modes Kand penalty parameters α)are adaptively optimized,on the basis,the reciprocating compressor air valve vibration signal is decomposed into K intrinsic mode functions(IMFs).Then the IMFs are reconstructed into a new signal,and the feature vector set is formed through fuzzy entropy analysis.Finally,the air valve working condition mode recognition is completed by the constructed extreme learning machine(ELM)classification model.Numerical and experimental simulation results show that the proposed method has good effectiveness,applicability and accuracy.
NETL
NSTL
万方数据
