Optimizing Remaining Useful Life Estimation of Lithium-Ion Batteries: A Particle Swarm Optimization-Based Grey Prediction Model

Abstract

Accurate estimation of the age and condition of lithium-ion batteries (LIBs) is paramount for their safe and economically viable utilization. However, assessing the degradation of these power units proves challenging due to their dependence on various environmental and usage factors. In this study, we propose an efficient Particle Swarm Optimization (PSO)-based Grey Theory prediction model to determine the Remaining Useful Life (RUL) of lithium-ion batteries.

The proposed model utilizes PSO to optimize the coefficients of a grey prediction model, enabling accurate forecasting of the remaining useful life of LIBs. Our results demonstrate that the presented model outperforms conventional grey prediction models in terms of both accuracy and stability. Furthermore, the proposed model offers simpler predictions compared to existing models in the literature.

By introducing this promising technique, our study contributes to the precise forecasting of the RUL of lithium-ion batteries and holds potential for applications in similar domains. This research serves as a significant step towards ensuring effective management and utilization of LIBs, promoting their reliability and safety.