Heat Transfer

Heat transfer research focuses on accurately predicting and controlling the movement of thermal energy in various systems, aiming to improve efficiency and safety in diverse applications. Current research emphasizes the use of machine learning, particularly deep learning architectures like convolutional neural networks, recurrent neural networks (LSTMs), and physics-informed neural networks, to create surrogate models for complex heat transfer phenomena, often surpassing the accuracy and efficiency of traditional numerical methods. These data-driven approaches are applied across numerous domains, including microchannel heat exchangers, high-energy density physics, and building energy efficiency, offering significant potential for optimizing designs and improving predictions in engineering and scientific contexts. The development of explainable AI methods is also a key focus, enhancing the interpretability and trustworthiness of these powerful predictive models.

Papers