Present a new multi objective optimization statistical Pareto frontier method composed of artificial neural network and multi objective genetic algorithm to improve the pipe flow hydrodynamic and thermal properties such as pressure drop and heat transfer coefficient for non-Newtonian binary fluids

摘要

This work aims to present a new statistical optimization approach of artificial neural network modified by multi objective genetic algorithm to improve the pipe flow hydrodynamic and thermal properties such as pressure drop and heat transfer coefficient for a non-Newtonian nanofluid composed of Fe3O4 nanoparticles dispersed in liquid paraffin. Hence the mixture pressure lose & convection coefficient are evaluated and then optimized so that to maximize the convection heat transfer and minimize the pressure drop. The results showed that the proposed model of multi objective optimization of GA Pareto optimal front, quantified the trade-offs to handle 2 fitness functions of the considered non-Newtonian pipe flow. (C) 2019 Elsevier B.V. All rights reserved.