Modeling Convective Heat Transfer Augmentation of TiO۲ Nanofluids Using Neural Networks

In this study, a neural network methodology was employed to estimate the forced convective heattransfer coefficient of nanofluids. Various operational parameters, including heat flux, thermal conductivity of fluids, nanoparticle concentration, and flow Reynolds number, were investigated to quantify the convective heat transfer coefficient. These operational parameters were introduced as inputs into an artificial neural network (ANN) to model the convective heat transfer coefficient. The addition of nanoparticles to the base fluid enhanced the forced convective heat transfer coefficient, with more significant effects observed in base fluids with lower thermal conductivity and flows characterized by higher Reynolds numbers and elevated heat fluxes. Good agreement between experimental data and the predicted results of the ANN demonstrates that the ANN can accurately model this process, except for higher heat flux

کلیدواژه ها:

Nanofluids ، Forced convection ، artificial neural networks ، TiO۲ nanoparticles