Remaining Useful Life Prediction of Lithium-ion Batteries Based on Particle Filter with Generalized Exponential Distribution

A remaining useful life (RUL) prediction method is proposed, which uses a particle filter (PF) with the generalized exponential distribution (GE). There are three parameters in the adopted GE and the maximum likelihood estimation is used to estimate the parameters of GE. Due to the parameters in GE, more prior information in historical data can be absorbed and taken into PF for RUL prediction. The battery data from NASA Prognostics Center of Excellence Data Set Repository (PCoE) are used to compare the performance of the proposed method and that of using PF with the exponential function. The experiment results show that the performance of the proposed method is better.