State‐of‐health estimation for lithium‐ion batteries based on partial charging segment and stacking model fusion

Abstract

Abstract State‐of‐health (SOH) estimation is essential for evaluating the aging process of lithium‐ion batteries, which can effectively guarantee the steady application of the battery system. Most existing prediction approaches apply a single model or a single feature to achieve SOH estimation based on the entire charging curve. In this paper, a multifeature‐based stacked ensemble learning framework is proposed for SOH prediction using partial charging curves. Firstly, combined with the range of state‐of‐charge (SOC) commonly used in the actual operation of vehicles, the charging segment is effectively intercepted through the mapping correlation between the SOC and the terminal voltage. Then, five relevant features characterizing the battery health status are extracted from multiple data, such as temperature, voltage, and incremental capacity profiles. Finally, a two‐level stacking ensemble framework is developed to fuse several individual estimation methods for higher SOH accuracy. To validate the performance of the proposed method, the Oxford University data set and the NASA data set are deployed for comparison experiments, and the results reveal the superior precision and robustness of the developed model in SOH estimation.