Roller bearing safety region estimation and state identification based on LMD–PCA–LSSVM

Abstract

The basic idea of safety region is introduced into roller bearing condition monitoring. Local mean decomposition (LMD), principal component analysis (PCA) and least square support vector machine (LSSVM) are used comprehensively for the estimation of the safety region and the identification of normal state and faulty state for the roller bearing operational status. First, the vibration acceleration data was segmented according to a certain time interval and then Product Functions (PFs) of each piece of the data were obtained by LMD. Based on this, statistics control limits T2 and SPE were extracted by PCA as roller bearings’ state characteristics. Finally, LSSVM was used for the estimation of the safety region of the roller bearing operation state, and multi-class LSSVM was used for the identification of the four normal, ball fault, inner race fault and outer race fault states. The results show that both the safety region estimation and state identification are accurate, and confirm the validity of the LMD–PCA–LSSVM method.