Since variational mode decomposition (VMD) was proposed, it has been widely used in condition monitoring and fault diagnosis of mechanical equipment. However, the parameters K and α in the VMD algorithm need to be set before decomposition, which causes VMD to be unable to decompose adaptively and obtain the best result for signal decomposition. Therefore, this paper optimizes the VMD algorithm. On this basis, this paper also proposes a method of multi-domain feature extraction of signals and combines an extreme learning machine (ELM) to realize comprehensive and accurate fault diagnosis. First, VMD is optimized according to the improved grey wolf optimizer; second, the feature vectors of the time, frequency, and time-frequency domains are calculated, which are synthesized after dimensionality reduction; ultimately, the synthesized vectors are input into the ELM for training and classification. The experimental results show that the proposed method can decompose the signal adaptively, which produces the best decomposition parameters and results. Moreover, this method can extract the fault features of the signal more completely to realize accurate fault identification.

Symplectic geometric mode decomposition (SGMD) is a newly proposed signal processing method. Because of its superiority, it has gained more and more attention in the field of fault diagnosis. However, the similar component reorganization problem involved in this method has not been clearly stated. Aiming at this problem, this paper proposes the SGMD-CS method based on the SGMD method and the cosine similarity (CS) and has been compared and verified on the simulation signal and the actual rolling bearing signal. In addition, in order to realize the intelligent diagnosis of the wind turbine bearing fault, the symplectic geometric entropy (SymEn) is extracted as the fault feature and input it into the AdaBoost classification model. In summary, this paper proposes a new wind turbine fault feature extraction method based on the SGMD-CS and AdaBoost framework, and the validity of the method is verified by the rolling bearing vibration data of the Electrical Engineering Laboratory of Case Western Reserve University.

No abstract

No abstract