Applying Artificial Neural Networks (Anns) For Prediction Of The Thermal Characteristics Of Water/Ethylene Glycol-Based Mono, Binary And Ternary Nanofluids Containing Mwcnts, Titania, And Zinc Oxide

An Artificial Neural Network (ANN) was applied to model the thermal conductivity (k(nf)) inwater/ethylene glycol (80:20) based hybrid nanofluid containing MWCNTs-titania-Zinc oxide. The nanofluids were synthesized by a two-step method. The ternary hybrid nanofluids had a volume fraction of nanoparticles phi = 0.1% to 0.4%, as well as mono and binary hybrid nanofluids. The experiments were performed at temperatures T = 25 degrees C-50 degrees C. Then an ANN has been used to predict the knf. According to the results, the optimum neuron number was 26. The designed network has acceptable performance and the maximum absolute error was less than 0.018 in 102 data points. (C) 2021 Elsevier B.V. All rights reserved.