Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

World Model for Battery Degradation Prediction Under Non-Stationary Aging

Kai Chin Lim, Khay Wai See

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.

World Model for Battery Degradation Prediction Under Non-Stationary Aging

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.
Paper Structure (34 sections, 12 equations, 3 figures, 5 tables)

This paper contains 34 sections, 12 equations, 3 figures, 5 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Data-Driven SOH Estimation
  4. Physics-Informed Machine Learning for Batteries
  5. Continual Learning
  6. World Models
  7. Methodology
  8. Problem Formulation
  9. World Model Architecture
  10. Training Objective
  11. Physics Constraint
  12. Elastic Weight Consolidation
  13. Model Variants and Controls
  14. Experimental Setup
  15. Dataset
  16. ...and 19 more sections

Figures (3)

  • Figure 1: World model architecture. Raw V/I/T time-series per cycle are encoded by a shared 1-D CNN, then processed by PatchTST to produce latent state $\mathbf{z}(k)$. The dynamics module rolls out future latent states and a shared head decodes SOH at each step. The physics constraint operates during training only.
  • Figure 2: Per-cell SOH trajectory performance. Top row: three representative cells showing rollout advantage on cell 127, PIWM+EWC failure mode on cell 57, and short lifecycle limitation on cell 45. Forecast wicks in purple show 80 cycles ahead predictions from PIWM, 20 wicks per cell. Bottom: MAE heatmap for all five methods across all 14 test cells, sorted by degradation depth.
  • Figure 3: PCA of latent vectors $\mathbf{z}(k)$, coloured by SOH value. The rollout objective produces a unified SOH-ordered curve (b, c), while the encoder without rollout retains per-cell structure (a) and batch-staged training distorts the manifold (d).