Abstract
Accurate state-of-health (SOH) estimation of lithium-ion batteries remains challenging in practical battery management scenarios, where available observations are often limited to partial charging segments. Under such conditions, handcrafted health indicators (HIs) may become sensitive to the selected charging window, while data-driven models may suffer from reduced robustness under varying operating protocols and limited interpretability. To address these issues, this paper proposes a local-adaptive multivariate state estimation technique (MSET) framework for SOH estimation from partial charging data. Handcrafted HIs and neural representations are extracted from charge-related curves and organized as grouped features for local-adaptive MSET-based capacity reconstruction. The framework assigns optimized weights to different feature groups and uses a local-adaptive kernel operator to account for variations in the data distribution. Experiments on a self-built lithium-ion battery aging dataset with four operating protocols examine the method under mixed-protocol SOH estimation, cross-protocol settings, and multiple voltage-window analysis. The proposed framework shows strong estimation accuracy, robustness to protocol shifts, and stable performance across voltage windows. External validation on the XJTU benchmark further confirms its generalization ability.

This publication has 22 references indexed in Scilit: