Unified physics-informed subspace identification and transformer learning for lithium-ion battery state-of-health estimation

Abstract

The growing use of lithium-ion batteries in electric transportation and grid-scale storage systems has intensified the need for accurate and highly generalizable state-of-health (SOH) estimation. Conventional approaches often suffer from reduced accuracy under dynamically uncertain state-of-charge (SOC) operating ranges and heterogeneous aging stresses. This study presents a unified SOH estimation framework that integrates physics-informed modeling, subspace identification, and Transformer-based learning. A reduced-order model is derived from simplified electrochemical dynamics, providing an interpretable and computationally efficient representation of battery behavior. Subspace identification across a wide SOC and SOH range yields degradation-sensitive features, which the Transformer uses to capture long-range aging dynamics via multi-head self-attention. Experiments on LiFePO₄ cells under joint-cell training show consistently accurate SOH estimation, with a maximum error of 1.39 %, demonstrating the framework’s effectiveness in decoupling SOC and SOH effects. In cross-cell validation, where training and validation are performed on different cells, the model maintains a maximum error of 2.06 %, confirming strong generalization to unseen aging trajectories. Comparative experiments on LiFePO₄ and public LiCoO₂ datasets confirm the framework’s cross-chemistry applicability. By extracting low-dimensional, physically interpretable features via subspace identification, the framework significantly reduces training cost while maintaining high SOH estimation accuracy, outperforming conventional data-driven models lacking physical guidance.