State of health estimation of lithium-ion battery based on improved ant lion optimization and support vector regression

The state of health (SOH) estimation plays an important role in keeping the safe and stable operation of lithium-ion battery management system (BMS). To solve the problem of low estimation accuracy of traditional estimation methods, this paper proposes a SOH estimation method based on improved ant lion optimization algorithm and support vector regression (IALO-SVR). Firstly, the data of battery charge and discharge are analyzed geometrically, and four health features highly correlated with SOH decline are selected as the input of SVR model. Pearson correlation coefficient is used to quantitatively analyze the correlation between features and SOH. On the other hand, the IALO algorithm is used to optimize the kernel parameters of SVR, and the SOH estimation model is obtained after training with battery training set. To verify this method, batteries in different working conditions are verified on NASA battery data set, and compared with ALO-SVR and SVR. The experimental results show that this method can achieve accurate estimation of SOH, with high estimation accuracy and robustness, and the estimation error is stable within 2%.