A scalable neural bundle map for multiphysics prediction in lithium-ion battery across varying configurations

TL;DR

This paper introduces a Neural Bundle Map framework that accurately predicts multiphysics evolution in lithium-ion batteries across various configurations, enabling efficient design and real-time monitoring with high fidelity and reduced computational costs.

Contribution

The paper presents a novel Neural Bundle Map approach that decouples geometric complexity from physical laws, allowing scalable, accurate multiphysics predictions across diverse battery geometries and configurations.

Findings

Achieves less than 1% normalized mean absolute error across configurations

Reduces computational costs by two orders of magnitude compared to traditional solvers

Identifies an optimal battery design with 38% increased energy density

Abstract

Efficient and accurate prediction of Multiphysics evolution across diverse cell geometries is fundamental to the design, management and safety of lithium-ion batteries. However, existing computational frameworks struggle to capture the coupled electrochemical, thermal, and mechanical dynamics across diverse cell geometries and varying operating conditions. Here, we present a Neural Bundle Map (NBM), a mathematically rigorous framework that reformulates multiphysics evolution as a bundle map over a geometric base manifold. This approach enables the complete decoupling of geometric complexity from underlying physical laws, ensuring strong operator continuity across varying domains. Our framework achieves high-fidelity spatiotemporal predictions with a normalized mean absolute error of less than 1% across varying configurations, while maintaining stability during long-horizon forecasting far beyond the training window and reducing computational costs by two orders of magnitude compared with conventional solvers. Leveraging this capability, we rapidly explored a vast configurational space to identify an optimal battery design that yields a 38% increase in energy density while adhering to thermal safety constraints. Furthermore, the NBM demonstrates remarkable scalability to multi-cell systems through few-shot transfer learning, providing a foundational paradigm for the intelligent design and real-time monitoring of complex energy storage infrastructures.