Remaining useful life prediction of lithium-ion batteries using CEEMDAN and WOA-SVR model

The remaining useful life (RUL) prediction of Lithium-ion batteries (LIBs) is a crucial element battery health management. accurate RUL enables the maintenance and replacement with potential safety hazards, which ensures safe stable operation. This paper develops new method for LIBs, combined complete ensemble empirical mode decomposition adaptive noise (CEEDMAN), whale optimization algorithm (WOA), support vector regression (SVR). Firstly, CEEMDAN employed to perform reduction in capacity data accuracy improvement. Then, an SVR model optimized by WOA proposed predict RUL. Finally, public datasets are selected validate performance CEEMDAN-WOA-SVR method. better than WOA-SVR In addition, comparison made between existing methods (artificial bee colony algorithm-SVR method, decomposition-gray wolf optimization-SVR method). results show that superior two methods.