[2604.01229] Interpretable Battery Aging without Extra Tests via Neural-Assisted Physics-based Modelling

Electrical Engineering and Systems Science > Signal Processing arXiv:2604.01229 (eess) [Submitted on 21 Mar 2026] Title:Interpretable Battery Aging without Extra Tests via Neural-Assisted Physics-based Modelling Authors:Yuan Qiu, Wei Li, Wei Zhang, Yi Zhou, Fang Liu, Jianbiao Wang, Zhi Wei Seh View a PDF of the paper titled Interpretable Battery Aging without Extra Tests via Neural-Assisted Physics-based Modelling, by Yuan Qiu and 6 other authors View PDF HTML (experimental) Abstract:State of health (SoH) is widely used for battery management, but it is a single scalar and offers limited interpretability. Two batteries with similar SoH can exhibit very different degradation behaviors and the lack of interpretability hinders optimal battery operation. In this paper, we propose IBAM for interpretable battery aging modelling with a neural-assisted physics-based framework. IBAM outputs a 2-D aging fingerprint without extra diagnostic tests and uses only routine logs from the battery management system. The fingerprint offers great interpretability by capturing a battery's curve-wide polarization voltage loss and the tail loss near the end-of-discharge. IBAM first creates a physics-based battery model based on a fractional-order equivalent circuit model, and then extracts per-cycle fingerprints from the model using a two-stage least-squares method. IBAM further anchors fingerprints on the SoH axis with physics-guided regression, where the per-cycle SoH is estimated via a bidirec...