Universal Battery Degradation Forecasting Driven by Foundation Model Across Diverse Chemistries and Conditions

2025-12-30

arXiv.org

AI Summary

Battery capacity degradation is strongly influenced by electrochemical systems and operating conditions, making it difficult for a single model to generalize across diverse scenarios. This work proposes a unified prediction framework that integrates 20 publicly available aging datasets—encompassing 1,704 cells and nearly 4 million charge–discharge cycles—and, for the first time, combines time-series foundation models (TSFMs) with physics-guided contrastive learning. To enable parameter-efficient adaptation, low-rank adaptation (LoRA) is incorporated for fine-tuning. The resulting approach achieves accuracy on par with or superior to specialized models across both seen and unseen chemistries and operating conditions, substantially enhancing cross-domain generalization. These results demonstrate the framework’s scalability and transfer potential for real-world battery management systems.

Technology Category

• Machine Learning: Deep Neural Architectures and Foundation Models
• Cognitive Modeling & Cognitive Systems: Adaptive Behavior
• Natural Language Processing: Learning & Optimization for NLP

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Accurate forecasting of battery capacity fade is essential for the safety, reliability, and long-term efficiency of energy storage systems. However, the strong heterogeneity across cell chemistries, form factors, and operating conditions makes it difficult to build a single model that generalizes beyond its training domain. This work proposes a unified capacity forecasting framework that maintains robust performance across diverse chemistries and usage scenarios. We curate 20 public aging datasets into a large-scale corpus covering 1,704 cells and 3,961,195 charge-discharge cycle segments, spanning temperatures from $-5\,^{\circ}\mathrm{C}$ to $45\,^{\circ}\mathrm{C}$, multiple C-rates, and application-oriented profiles such as fast charging and partial cycling. On this corpus, we adopt a Time-Series Foundation Model (TSFM) backbone and apply parameter-efficient Low-Rank Adaptation (LoRA) together with physics-guided contrastive representation learning to capture shared degradation patterns. Experiments on both seen and deliberately held-out unseen datasets show that a single unified model achieves competitive or superior accuracy compared with strong per-dataset baselines, while retaining stable performance on chemistries, capacity scales, and operating conditions excluded from training. These results demonstrate the potential of TSFM-based architectures as a scalable and transferable solution for capacity degradation forecasting in real battery management systems.

Problem

• battery degradation forecasting
• cross-chemistry generalization
• operating condition heterogeneity
• capacity fade prediction
• universal battery model

Innovation

• Time-Series Foundation Model
• Low-Rank Adaptation
• Physics-Guided Contrastive Learning
• Battery Degradation Forecasting
• Cross-Chemistry Generalization