A Data-Driven Method With Mode Decomposition Mechanism for Remaining Useful Life Prediction of Lithium-Ion Batteries

Lithium-ion batteries offer excellent advantages of high efficiency, small size, and low cost, but their instability and inconformity remain challenging. Sudden failure of batteries may cause serious accidents, endangering the safety of people's lives and properties. Advanced remaining useful life prediction methods for batteries can effectively avoid those accidents. In this article, we proposed a novel hybrid method with the purpose of enhancing battery remaining useful life prediction precision and robustness. Based on improved complete ensemble empirical mode decomposition with adaptive noise algorithm, utilizing a special-designed interpolation reconstruction mechanism, the battery capacity degradation series was decomposed into a trend subseries and several fluctuation subseries. Weighted least square support vector machine and long short-term memory network are then established to perform prediction for the trend subseries and the fluctuation ones, respectively. A complementary series of experiments is designed to verify the effectiveness of the proposed method. The simulation results represent that the proposed method achieves higher prediction accuracy and robustness over other comparison models. The proposed approach provides a promising and effective alternate for lithium-ion batteries remaining useful life prediction without relying on the cell dynamic process, which is meaningful for cases with limited measurement parameters or limited computational power.