Effects of the curved winglet vortex generator inserts (CWVGs) on the forced convection heat transfer, friction factor, and performance evaluation criteria (PEC) interior flow were experimentally examined in this work. The CWVGs manufactured in CNC from aluminum 6061 material were used as the expanded finned surface with different attack angles (α) of 0°, 30°, and 60°. In the study, air was used as the fluid. The experiments were realized in the Reynolds number ranging from 6000 to 20000. The results showed that the CWVG insert in a rectangular channel ensured significantly higher Nusselt number than that of the channel without the insert through friction factor that was also increased. The Nusselt number and friction factor increased with the increase in the attack angle (α) of CWVG insert. The heat transfer enhancement by the CWVGs with attack angle of 0°, 30°, and 60° ensured higher than that of the plain tube in the range of 217.39–291.30%, 260.86–465.21%, and 278.26–476.08%, respectively. The friction factors in the inner rectangular channel produced by the CWVGs with attack angle of 0°, 30° and 60°, were about 8.93–10.33, 10.66–14.16, and 14.96–19.13 times above the plain tube, respectively. The performance evaluation criteria (PEC) for CWVGs with attack angle of 0°, 30°, and 60° were in the range of 1.22–1.78, 1.28–1.86, and 1.32–1.89, respectively. ABSTRACT

This work aims to estimate the experimental heat transfer coefficients of a circular channel using artificial neural network. The experiments are carried out at a forced turbulent flow regime of 10,000 < Re <50,000. The obtained experimental Nusselt numbers are compared using the ANN (Artificial Neural Network). In the developed ANN structure are showed mean square error (MSE), average relative deviation (ARD %), and correlation coefficient (R²) in modeling of overall experimental datasets of Nusselt number. As a result, it is observed that the heat transfer correlation predicted by ANN are sufficiently consistent with the experimental results.