State-of-health estimation for lithium-ion batteries based on historical dependency of charging data and ensemble SVR

Accurate estimation of State-of-Health (SOH) is very important for the safe and reliable operation of lithium-ion batteries. Considering that the historical dependency of charging data could reflect the internal electrochemical reaction of the battery, a new SOH estimation method is proposed. Firstly, a data pre-processing method is developed to resample the voltage data of the constant current charging stage with a predefined fixed number of samples. It can suppress the measurement noise and facilitate calculating the difference of voltage curves under different aging levels. Secondly, a new health indicator (HI) is proposed. It includes two types of features, one is accumulated voltage of different intervals and the other is charging capacity, they are used to reflect the nonlinear changes of the charging voltage and changes of the charging time with the battery aging respectively. In addition, considering the cell inconsistency, an Ensemble Support Vector Regression (ESVR) model is put forward to establish the relationship between HI and battery SOH. Finally, two kinds of open-source battery data are tested and the results show that the method developed in the paper could get high-precision SOH estimation results and the HI is robust to the battery type and cell inconsistency.

Automated summary

Accurate estimation of State-of-Health (SOH) is important for lithium-ion batteries. This study proposes a new method to estimate SOH by preprocessing the charging data and introducing a new health indicator. The method is robust to battery type and inconsistency, and achieves high-precision estimation results.