Heat Convection Enhancement of Unilateral-Heated Square Channels by Inclined Ribs Optimization with Machine Learning

Abstract

Optimizing structure parameters is pivotal in enhancing the convective heat. This study leverages machine learning methods to establish a relationship between input parameters and targets, providing a novel approach to structure parameter optimization in convective heat transfer of a unilateral-heated square channel with inclined ribs. Initially, dimensional analysis is employed to identify structure parameters that influence friction coefficient, Nusselt number, and comprehensive heat transfer characteristic (PEC). A substantial dataset is procured through batch modeling and CFD simulations. The Gaussian process regression is applied to train the data due to its continuity and smoothness. The influence of the rib structure parameters on the flow and heat transfer characteristics is analyzed by CFD simulations and the training results. Finally, the structure parameters corresponding to the optimal Nu and PEC are obtained via the well-trained machine learning model. The optimization results are validated through CFD simulations, yielding the best structure parameters that demonstrate a 7% and 3% increase in Nu and PEC, respectively, which is better than the best results from the numerical data used for training the machine learning model. The heat transfer mechanism and heat transfer effects of the unilateral-heated square channels with inclined ribs are analyzed. This study underscores the potential of machine learning in optimizing convective heat transfer channels, benefiting future research and applications in this field.