Operator-Theoretic and physics-guided Sequence Modeling of Lithium-Ion Battery Voltage Dynamics

TL;DR

This paper compares operator-theoretic and physics-guided transformer models for lithium-ion battery voltage dynamics, highlighting their respective advantages in interpretability, robustness, and flexibility based on experimental results.

Contribution

It introduces a physics-guided transformer model and compares it with an operator-theoretic DMDc approach for battery voltage prediction.

Findings

DMDc achieves lower prediction error and greater robustness to degradation.

Both models effectively capture transient pulse dynamics.

Transformer model offers greater architectural flexibility.

Abstract

Lithium-ion batteries exhibit nonlinear voltage dynamics across varying operating conditions and aging states, making accurate modeling essential for estimation, control, and health monitoring. This work compares two data-driven frameworks for modeling voltage responses from hybrid pulse power characterization (HPPC) measurements: an operator-theoretic model based on Dynamic Mode Decomposition with control (DMDc), and a physics-guided transformer-based sequence model. In the DMDc framework, delay-embedded snapshots of terminal voltage and current are used to identify system matrices directly from measurement data, yielding an interpretable state-space model for recursive prediction. In parallel, a modified PatchTST architecture is developed in which terminal voltage is decomposed into an analytically computed open-circuit-voltage (OCV) component and a learned dynamic residual, with a future-current fusion pathway tailored to the prescribed HPPC current profile. Experimental results on a 30 Ah lithium-ion cell show that, although both models capture the sharp transient pulse dynamics, DMDc achieves lower prediction error and greater robustness to cell degradation under the present limited data regime, while the transformer captures qualitatively similar dynamics with greater architectural flexibility. These results highlight the advantages of operator-theoretic models in interpretability, computational efficiency, and robustness, while indicating the promise of physics-guided transformer models when larger and more diverse datasets are available.