5 / 2021-07-15 12:45:59

Fault feature enhancement and diagnosis of rolling bearing based on complex network

Rolling bearings,Fault Diagnosis,Complex network,symplectic geometric mode decomposition

As the key part of wind turbine and other rotating machinery, rolling bearing is of great significance in the safe and stable operation of the equipment. Aiming at the problems of traditional rolling bearing fault diagnosis methods, such as strong expert dependence and insufficient representation information, a rolling bearing fault feature enhancement and diagnosis method based on complex network is proposed. Firstly, symplectic geometric mode decomposition (SGMD) is used to preprocess the signal, which is good at processing complex nonstationary signals. Then, the global and local features of the complex network are extracted from the topological characteristics of the complex network, and the multi-level diagnosis basis of the bearing signal is established. Finally, the diagnosis of different bearing signal is realized by combining the SVM typical classifier. The experimental results show that the proposed fault feature enhancement and diagnosis method of rolling bearing based on complex network can guarantee the signal eigen information, and can get high diagnosis accuracy and robustness for different experiments, which provides a new idea for rolling bearing fault diagnosis.