Application of Neural Network for estimation of heat transfer treatment of Al2O3-H2O nanofluid through a channel
Heat transfer studying in channels is crucial for transport of the fluids in the oil and gas industry. In this study, numerical approach is applied to analyze the thermal behavior of alumina nanofluid in a duct. Brownian motion impact has been included for predicting nanofluid properties. Neural Network was employed to estimate the heat transfer rate. Numerical data has been obtained via Runge-Kutta method. Our outputs display that GMDH achieved an operative method for an efficient recognition of trends in data. Impact of expansion ratio, nanoparticle concentration, power law index and Reynolds number on Nu was also studied. Our findings reveal that heat transfer intensifies by rise of nanoparticle concentration while it has a reducing trend with rise of expansion ratio.