Flow and heat transfer optimization of a fin-tube heat exchanger with vortex generators using Response Surface Methodology and Artificial Neural Network

Using vortex generators (VGs) in fin-tube heat exchangers (FTHEs) is one of the main options to increase their performance. Although numerical models can replace the expensive experimental studies, suggesting an optimum design configuration using numerical models involves trial and error procedures and can be very computationally demanding. To alleviate this situation in the present research, the utilization of Response Surface Methodology (RSM) and Artificial Neural Network (ANN) in the optimum design of FTHEs with VGs was proposed. To train the models, three explanatory variables were chosen: the length (L), arc angle (alpha), and attack angle (beta) of the VGs. The target variables were the Nusselt number and the friction factor. The results showed that both ANN and RSM performed reliably, although the ANN outperformed the RSM in predicting the Nusselt number and the friction factor. Considering the Nusselt number value prediction, the ANN and RSM had an R-squared value of 0.990 and 0.954, respectively. Regarding the friction factor, the same performance criteria showed a value of 0.998 for the ANN and 0.972 for the RSM. In the end, based on whether the heat exchange performance or pressure drop reduction is the main objective of design or a balanced approach to both are the target, three optimum design configurations were suggested.