Abstract
As one pioneer means for energy storage, Li-ion battery packs have a complex and critical issue about degradation monitoring and remaining useful life estimation. It induces challenges on condition characterization of Li-ion battery packs such as internal resistance (IR). The IR is an essential parameter of a Li-ion battery pack, relating to the energy efficiency, power performance, degradation, and physical life of the li-ion battery pack. This study aims to obtain reliable IR through applying an evaluation test that acquires data such as voltage, current, and temperature provided by the battery management system (BMS). Additionally, this paper proposes an approach to predict the degradation of Li-ion battery pack using support vector regression (SVR) with RBF kernel. The modeling approach using the relationship between internal resistance, different SOC levels 20%–100%, and cycle at the beginning of life 1 cycle until cycle 500. The data-driven method is used here to achieve battery life prediction.based on internal resistance behavior in every period using supervised machine learning, SVR. Our experiment result shows that the internal resistance was increasing non-linear, approximately 0.24%, and it happened if the cycle rise until 500 cycles. Besides, using SVR algorithm, the quality of the fitting was evaluated using coefficient determination R2, and the score is 0.96. In the proposed modeling process of the battery pack, the value of MSE is 0.000035.
A Bayesian least-squares support vector machine method for predicting the remaining useful life of a microwave component