Optimization, modeling and accurate prediction of thermal conductivity and dynamic viscosity of stabilized ethylene glycol and water mixture Al 2 O 3 nanofluids by NSGA-II using ANN

AuthorsMohammad Hemmat Esfe, Peyman Razi, Mohammad Hadi Hajmohammad, Seyed Hadi Rostamian, Wail Sami Sarsam, Ali Akbar Abbasian Arani, Mahidzal Dahari
JournalINT COMMUN HEAT MASS
Presented byUniversity of Kashan
Page number154–160
Volume number82
Paper TypeFull Paper
Published At2016
Journal GradeISI
Journal TypeElectronic
Journal CountryIran, Islamic Republic Of

Abstract

In this study, multi-objective optimization of nanofluid aluminum oxide in a mixture of water and ethylene glycol (40:60) is studied. In order to reduce viscosity and increase thermalconductivityofnanofluids, NSGA-II algorithm is used to alter the temperature and volume fraction of nanoparticles. Neural network modeling of experimental data is used to obtain the values of viscosity and thermal conductivity on temperature and volume fraction of nanoparticles. In order to evaluate the optimization objective functions, neural network optimization is connected to NSGA-II algorithm and at any time assessment of the fitness function, the neural network model is called. Finally, Pareto Front and the corresponding optimum points are provided and introduced. Optimal results showed that the optimum viscosity and thermal conductivity occurs at maximum temperature.