CFD and ANN analyses for the evaluation of the heat transfer characteristics of a rectangular microchannel heat sink with various cylindrical pin-fins

Abstract

Electrical equipment extensively uses Microchannels (MCs) for cooling. Due to their complexity, it is challenging to evaluate the features of the fluid flow and heat transfer processes in MC pin-fin heat sinks. Numerical approaches have been frequently employed in MC design to enhance efficiency. Machine learning methods have recently enabled the assessment of flow and heat transfer research in these devices. In this study, numerical calculations have been made to obtain outlet fluid temperature, the average Nusselt number, and pressure drop, using the computational fluid dynamics (CFD) software, ANSYS Fluent. Previous experimental work validates the numerical model by examining the average Nusselt number and the apparent friction factor. Three distinct ratios of fin spacing to fin diameter (l/d = 2, 4, and 6) and five different values of Reynolds number (Re = 50, 75, 100, 125, and 150) are considered. A constant ratio of fin height to channel height (h/H = 0.25) is maintained, and the inlet fluid temperature is set to 291.15, 294.15, 297.15, and 300.15 K. Numerical calculations have been conducted for cases of uniform and non-uniform heating, where bottom wall temperatures of 323.15 K and 317.15 K were considered, respectively, for a fixed fin surface temperature of 323.15 K. Using the results of the numerical simulations, a multi-layer perceptron (MLP)-structured artificial neural network (ANN) is trained. The Levenberg-Marquardt (LM) training method is employed in the hidden layer, using 17 neurons for the training procedure. The results of the numerical simulations show that the average Nusselt number increases linearly with the Reynolds number, except for the non-uniform heating case of Re = 50. The average Nusselt number and pressure drop are inversely proportional to fin spacing for all cases. There is also a linear increase in pressure drop with the Reynolds number, since the flow regime considered in this study is laminar. The ANN model predicts the outlet fluid temperature, the average Nusselt number, and the pressure drop, with variation rates of -0.0027%, -0.075%, and − 0.0004%, respectively.