Evaluating the effect of temperature and concentration on the thermal conductivity of ZnO-TiO2/EG hybrid nanofluid using artificial neural network and curve fitting on experimental data

In this paper, the experimental data on the thermal conductivity of EG based hybrid nanofluid containing zinc oxide and titanium oxide have been used. At the first, three two-variable correlations have been proposed using curve-fitting on experimental data. After that, the best transfer function for training the artificial neural network has been selected. The input variables of neural network were temperature and solid volume fraction, while the output variable was the thermal conductivity enhancement of the nanofluid. Moreover, the correlation outputs, ANN results and experimental data have been compared. The results showed that there is a good agreement between experimental data and neural network results so that the resulting model of the neural network is able to predict the thermal conductivity enhancement of the nanofluid. The findings also indicated that the accuracy of the neural network is much greater than the curve fitting method to predict thermal conductivity enhancement of ZnO-TiO₂/EG hybrid nanofluid.