ANN Modeling of the Viscosity and Effective Thermal Conductivity of Non-Newtonian Nanofluids

Abstract

Abstract The aim of the study is to predict the apparent viscosity and effective thermal conductivity of non-Newtonian nanofluids using the artificial neural network (ANN) approach. Different nanofluids were prepared by dispersing iron oxide, γ-alumina, and copper oxide nanoparticles separately in an aqueous solution of carboxymethyl cellulose (CMC) (base fluid). Three different base fluids containing 0.5, 0.75, and 1.0 weight percent CMC were used. Nanofluids of different nanoparticles were prepared from the base fluid. The effect of the base fluid concentration, nanofluid concentration, temperature of nanofluid, and shear rate on the apparent viscosity were investigated. The effect of the concentration of the base fluid, nanofluid concentration, temperature, diameter of nanoparticles, and nature (thermal conductivity) of the material of nanopowder on effective thermal conductivity were investigated. Feed forward ANN has been used to predict the apparent viscosity and effective thermal conductivity of nanofluid. The network was trained, tested, and validated using a total of 3,600 experimental data points for shear viscosity and 225 experimental data points for effective thermal conductivity. ANN predictions are in good agreement with experimental results.