Degradation Detection and RUL Prediction of Rolling Bearings Based on Gini Index and Particle Filter

Condition-based monitoring (CBM) plays a fundamental role in bearing prognostics health management. To effectively reveal the degradation severity of the bearings, the choice of health indicators based on sensor measurements determines the promptness of fault detection and predictive maintenance. The Gini index (GI) is a widely used inequality measure for income distributions in economics while recent research has also successfully applied it in the CBM field. This study applies the Gini index of the vibration envelope signal (GIES) for bearing degradation detection and life prediction. Based on the changes of vibration impulsiveness, bearing degradation can be detected using the empirical three sigma rule. After the detection of bearing degradation, the remaining useful life (RUL) is predicted using the particle filter (PF) based on only a few GIES observations. The performance the RUL prediction method is demonstrated through the measured vibration data from an experimental rig available on the Internet.