Abstract:
Currently, many industries aim to improve the heat transfer system to reduce cost and carbon emission. For improving heat exchanger apparatus, the conventional working fluid such as water can be replaced by hybrid nanofluid. The hybrid nanofluid is a suspension of two or more nanoparticles into conventional base fluids to improve its properties. Generally, different combinations of nanoparticle and base fluid can variably effect the thermal properties and dynamic properties. In this study, the artificial neural network was thus employed to develop the prediction model for predicting thermal conductivity, specific heat capacity, viscosity, and density using feedforward and cascade forward propagation networks with Levenbreg-Marquardt learning algorithm. The best artificial neural network (ANN) model topology was selected to predict thermal conductivity, specific heat capacity, viscosity, and density of hybrid nanofluid with R value >0.90 for training, validating and testing, respectively. Then, the thermal properties of hybrid nanofluid value from ANN model was applied as heat transfer agent in heat exchanger of isopropyl alcohol process. The hybrid nanofluid with CuO and MgO in water exhibited the best heat removing medium in heat exchanger application to obtain highest concentration of isopropyl alcohol.