World Model for Battery Degradation Prediction Under Non-Stationary Aging

TL;DR

This paper introduces a world model approach for lithium-ion battery degradation prediction, encoding cycle data into a latent space and forecasting future health trajectories, with electrochemical knowledge enhancing accuracy at critical degradation points.

Contribution

It formulates battery degradation as a world model problem, integrating electrochemical constraints to improve long-term SOH trajectory predictions.

Findings

Iterative rollout reduces forecast error by half.

SPM constraint enhances prediction at degradation knee.

Method outperforms direct regression in trajectory accuracy.

Abstract

Degradation prognosis for lithium-ion cells requires forecasting the state-of-health (SOH) trajectory over future cycles. Existing data-driven approaches can produce trajectory outputs through direct regression, but lack a mechanism to propagate degradation dynamics forward in time. This paper formulates battery degradation prognosis as a world model problem, encoding raw voltage, current, and temperature time-series from each cycle into a latent state and propagating it forward via a learned dynamics transition to produce a future trajectory spanning 80 cycles. To investigate whether electrochemical knowledge improves the learned dynamics, a Single Particle Model (SPM) constraint is incorporated into the training loss. Three configurations are evaluated on the Severson LiFePO4 (LFP) dataset of 138 cells. Iterative rollout halves the trajectory forecast error compared to direct regression from the same encoder. The SPM constraint improves prediction at the degradation knee where the resistance to SOH relationship is most applicable, without changing aggregate accuracy.