Physics-Informed Machine Learning for Pouch Cell Temperature Estimation

Accurate temperature estimation of pouch cells with indirect liquid cooling is essential for optimizing battery thermal management systems for transportation electrification, yet it is challenging due to the computational expense of finite element simulations and the limitations of data-driven models. This paper presents a physics-informed machine learning framework for efficient and reliable estimation of steady-state temperature profiles by integrating governing heat transfer equations directly into the neural network loss function. The framework is evaluated on datasets of varying cooling channel geometries. Results demonstrate faster convergence and markedly higher accuracy than purely data-driven models, with a 49.1% reduction in mean squared error, particularly in regions away from cooling channels.