A uniform estimation framework for state of health of lithium-ion batteries considering feature extraction and parameters optimization

State of health is one of the most critical parameters to characterize inner status of lithium-ion batteries in electric vehicles. In this study, a uniform estimation framework is proposed to simultaneously achieve the estimation of state of health and optimize the healthy features therein, which are excavated based on the charging voltage curves within a fixed range. The fixed size least squares-support vector machine is employed to estimate the state of health with less computation intensity, and the genetic algorithm is applied to search the optimal charging voltage range and parameters of fixed size least squares-support vector machine. By this manner, the measured raw data during the charging process can be directly fed into the estimation model without any pretreatment. The estimation performance of proposed algorithm is validated in terms of different voltage ranges and sampling time, and also compared with other three traditional machine learning algorithms. The experimental results highlight that the presented estimation framework cannot only restrict the prediction error of state of health within 2%, but also feature high robustness and universality.