ROLLING BEARING FAULT DIAGNOSIS BASED ON VARIATIONAL MODAL DECOMPOSITION AND LFOA-RVM

Abstract

Aiming at the fault diagnosis problem of rolling bearing, a fault diagnosis method of rolling bearing based on variational modal decomposition（VMD）, improved fruit fly optimize algorithm（LFOA） and relevance vector machine（RVM） was proposed. Firstly, the bearing vibration signals was decomposed into several intrinsic mode components（IMF） and root mean square value and frequency of the center of gravity was calculated as fault feature vectors that could represent the operating conditions of bearings. In order to improve the classification accuracy, the LFOA was used to optimize the parameter of RVM and a LFOA-RVM model was built. And then, the fault feature were extracted for training and testing, so that it might recognize different fault type and different fault degree. The actual signals were analyzed and diagnosed, and compared with some other methods, it proves the validity of the method.

Keywords

• Variational modal decomposition
• Improved fruit fly optimization algorithm
• Relevance vector machine
• Fault diagnosis
• Bearing