Physics-Informed Neural Networks (PINN) for Advanced Thermal Management in Electronics and Battery System: A Review of Recent Developments and Future Prospects

The growing complexities, power densities, and cooling demands of modern electronic systems and batteries—such as three-dimensional integrated circuit chip packaging, printed circuit board assemblies, and electronics enclosures—have pushed the urgency for efficient and dynamic thermal management strategies. Conventional numerical approaches generally require high computational costs for unseen scenarios, and have limited scalability for comprehensive thermal analysis, especially when incorporating temperature-dependent properties and dynamic operating conditions. Physics-Informed Neural Networks (PINN) emerge as a powerful alternative approach, which incorporates physical principles, such as mass and energy conservation equations into deep learning models. This approach delivers rapid and adaptable resolutions to the partial differential equations that govern heat transfer and fluid dynamics. This review examines the basic principle of PINN and its role in thermal management for electronics and batteries, from small unit scale to system scale. We highlight their advancements, including performance over traditional computational fluid dynamics methods. Furthermore, we explore the potential of PINNs in facilitating generating design space and predicting unseen trials, while addressing challenges such as training convergence difficulties in fine-grain or large-scale applications. Additionally, we propose future research pathways, focusing on the synergy of PINN with advanced hardware and hybrid techniques to drive designs in thermal management for next-generation electronics and battery systems.