Research on the Fault Feature Extraction of Rolling Bearings Based on SGMD-CS and the AdaBoost Framework

Abstract

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.

Keywords

• rolling bearings
• symplectic geometric mode decomposition
• cosine similarity
• symplectic geometric entropy
• AdaBoost