Machine Learning-Supported Heat Transfer Prediction Using Differential Equation-Based Models
M Srivani,
K M V Ramana,
G Radhika,
G Sriraja Vijaya Krishna
Accurate prediction of heat transfer is essential for the design and optimization of thermal systems
operating under complex and nonlinear conditions. Traditional differential equation–based heat
transfer models provide strong physical interpretability but often require high computational effort
and simplifying assumptions. This study presents a machine learning–supported framework for heat
transfer prediction that integrates physics-based differential equation models with data-driven learning
techniques. Numerical solutions of governing heat transfer equations are used to generate reliable
thermal datasets, which are then employed to train machine learning models capable of capturing
nonlinear thermal behavior. A hybrid approach combining machine learning predictions with physics based
constraints is developed and evaluated. Comparative results demonstrate that the hybrid model
achieves high prediction accuracy while significantly reducing computational time when compared to
conventional numerical methods. The proposed framework offers a reliable and efficient solution for
advanced heat transfer prediction in engineering applications.
