Conformalized Transfer Learning for Li-ion Battery State of Health Forecasting under Manufacturing and Usage Variability

2026-03-25

AI Summary

This work addresses the limited generalization of existing state-of-health (SOH) prediction models for lithium-ion batteries under manufacturing variations and diverse operating conditions. To overcome this challenge, the authors propose a novel SOH prediction framework that integrates transfer learning with uncertainty quantification. Specifically, an LSTM model is first trained on synthetic battery data encompassing both manufacturing and usage variability. Maximum Mean Discrepancy (MMD) is then employed to align the feature distributions between source and target domains. Notably, the method pioneers the combination of conformal prediction with MMD-based domain adaptation to produce statistically valid and well-calibrated prediction intervals. Experimental results demonstrate that the proposed approach significantly enhances generalization across different batteries and operating conditions while improving prediction reliability, thereby bolstering safety and robustness in real-world deployment scenarios.

Technology Category

• Machine Learning: Transfer, Domain Adaptation, Multi-Task Learning
• Intelligent Robots: State Estimation
• Reasoning under Uncertainty: Stochastic Optimization

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Social Networks and Social Media: Influence propagation, information diffusion, and the prediction on networks

Abstract

Accurate forecasting of state-of-health (SOH) is essential for ensuring safe and reliable operation of lithium-ion cells. However, existing models calibrated on laboratory tests at specific conditions often fail to generalize to new cells that differ due to small manufacturing variations or operate under different conditions. To address this challenge, an uncertainty-aware transfer learning framework is proposed, combining a Long Short-Term Memory (LSTM) model with domain adaptation via Maximum Mean Discrepancy (MMD) and uncertainty quantification through Conformal Prediction (CP). The LSTM model is trained on a virtual battery dataset designed to capture real-world variability in electrode manufacturing and operating conditions. MMD aligns latent feature distributions between simulated and target domains to mitigate domain shift, while CP provides calibrated, distribution-free prediction intervals. This framework improves both the generalization and trustworthiness of SOH forecasts across heterogeneous cells.

Problem

• State of Health
• Transfer Learning
• Domain Shift
• Lithium-ion Battery
• Generalization

Innovation

• Transfer Learning
• Conformal Prediction
• Maximum Mean Discrepancy
• LSTM
• State of Health