Online State-of-Health Estimation for Second-Use Lithium-Ion Batteries Based on Weighted Least Squares Support Vector Machine

Online state-of-health (SOH) estimation is critical for second-use retired lithium-ion batteries. However, the SOH of retired batteries is highly nonlinear, and the existing degradation trend data are limited. Consequently, achieving accurate and effective SOH estimation remains a challenge. To address the above problem, an online SOH estimation based on a weighted least squares support vector machine (WLS-SVM) is proposed in this paper. In this work, the health features (HFs) are first extracted from the partial charging curves of retired batteries, and the Pearson correlation coefficient is applied to select the important HFs that are strongly correlated to the SOH. These selected HFs are used as the estimation model inputs for characterizing the aging procedure of the retired battery effectively. Then, to enhance the accuracy and robustness of SOH estimation, the standard support vector machine (SVM) is improved by a weighting function and linear equations. Last, the online SOH estimation is conducted by using the test data sets of second-use batteries with different battery materials and under different conditions. The results show that compared with the most popular methods, such as the back-propagation neural network (BPNN)-based method, the Gaussian process regression (GPR)-based method, and the standard SVM-based method, the performance of the WLS-SVM-based method is superior. The root mean square error (RMSE) for the SOH estimation with the WLS-SVM-based method for all the test cells is less than 1.85% at different aging paths and levels, whereas the RMSEs of the BPNN-based method, GPR-based method, and standard SVM-based method are within 3.6%, 5.7%, and 7.6%, respectively. The proposed WLS-SVM-based method can thus provide highly robust and accurate online SOH estimation.