OICC Press Journal of Solid Mechanics 2008-7683 18 1 2026 03 31 ANN simulation and thermo-flow optimization of a Non-Polar Hybrid CuO nanofluid 10.57647/jsm.2026.1801.04 EN Mohammad Ali Fazilati Efficiency and Smartization of Energy Systems Research Center, Kho.C., Islamic Azad University, Khomeinishahr, Iran Ali Mokhtarian Mojtaba Rahimi https://orcid.org/0000-0002-2567-0508 Mohammad Hashemian https://orcid.org/0000-0003-3891-4126 Journal Article 2026 03 31 Nanoparticles (NPs) can improve the thermo-physical properties of the fluids and increase the effectiveness of heat transfer systems. In this way, finding the optimal properties of nanofluids (NFs) is very important. The present work aims to model and dynamic viscosity (DV) and thermal conductivity (TC) of CuO / 1-4 dioxane + Diethyl amine (DEA) as the non-polar NF with binary base fluids. The input parameters include the temperature and the solid volume fraction (SVF) of NPs. Based on available experimental data, the weight ratio of the NPs is 0.01 % to 0.06 % with temperatures ranging from 25oC to 45oC. The NF is modeled by the design and training of two separate two-layer feedforward artificial neural networks (ANNs) for the prediction of DV and TC at desired inputs of temperature and SVF. The average/maximum relative errors for test datasets are 0.3387/0.5078 and 0.3230/0.6871 for DV and TC prediction networks, respectively. Based on the designed model, a multi-objective optimization problem is defined to specify the maximum TC and minimum DV simultaneously and solved using the MOPSO method. Finally, the optimal values of the objective functions and the corresponding input parameters are plotted along with the Pareto optimal points.