A Hierarchical and Flexible Data-Driven Method for Online State-of-Health Estimation of Li-Ion Battery

This paper proposes a flexible data-driven method for online estimating the State of Health (SOH) of Li-ion batteries in both charging and discharging modes. Based on comprehensive battery aging data analytics, a novel health indicator called voltage variance during equal time interval (VVETI) is extracted. The VVETI can be extracted during either charging or discharging mode. For online applications, the indicator is derived from a small segment of charge/discharging curves. Unlike existing methods, the indicator can be extracted in various voltage ranges which is highly flexible for application. Then, a hierarchical ensemble model of extreme learning machine (ELM) is proposed as the machine learning engine for accurate SOH estimation. The proposed method is tested on three open datasets and reports a very high accuracy (average RMSE below 0.5% under appropriate voltage ranges).