Remaining useful life prediction of lithium-ion battery using a novel particle filter framework with grey neural network

Abstract

Remaining Useful Life (RUL) prediction of lithium-ion batteries is critically vital to ensure the safety and reliability of EVs. Because of the complex aging mechanism, accurate prediction of RUL with traditional methods always requires a large number of data, it is hard for traditional methods to guarantee the prediction accuracy when useful data are insufficient. In this paper, a grey neural network (GNN) model fused grey model (GM) and BPNN is proposed to estimate the capacity online with the inputs of new health indicators. Additionally, the sliding-window grey model (SGM) is employed to track the degradation trend of the battery, and the trend equation is set as the state transition equation of Particle Filter algorithm (PF). Meanwhile, the estimation values by GNN model are used as observation values of the PF to construct the GNN fused sliding-window grey model based on PF framework (GNN-SGMPF) for prediction of battery RUL. Moreover, the performance of GNN-SGMPF was verified by two types of batteries under various loading profiles (NEDC/UDDS/JP1015) and temperatures (10 °C/25 °C/40 °C). The results indicate the proposed GNN algorithm can effectively estimate degradation capacity with the MAE is less than 2.2%, and the GNN-SGMPF had a remarkable ability of transfer application, practicability, and universality.