Numerical heat transfer analysis & predicting thermal performance of fins for a novel heat exchanger using machine learning

Abstract

In the present case study, the thermal performance of fins for a novel axial finned-tube heat exchanger is investigated and predicted using machine learning regression technique. The effects of variation in the fin spacing, fin thickness, material, and the convective heat transfer coefficient on the overall efficiency and total effectiveness have been analyzed and commented upon. The k-Nearest Neighbor (k-NN), a machine learning algorithm, is used for regression analysis to predict the thermal performance outputs and the results showed high prediction accuracies. The k-NN algorithm is robust and precise which can be used by thermal system design engineers for predicting output variables. The temperature profiles of various geometries have been depicted and compared in the results. It was concluded that the efficiency is increasing with fin thickness & decreasing with fin spacing and the maximum efficiency ηmax=0.99975 is achieved at δ∗=0.1&t∗=0.0133 having h=5W/m2.K for copper material. The effectiveness is increasing with fin spacing & fin thickness and the maximum effectiveness εmax=122.766 is for δ∗=8&t∗=0.4 having h=5W/m2.K.