This study was on the optimization of the viscosity of MWCNT-MgO (35–65%)/5W50 nanofluid and comparison of experimental results with the designed artificial neural network (ANN). The experimental examination was performed at solid volume fraction (SVF) s of 0.05, 0.1, 0.25, 0.5, 0.75, 1% and the temperature of 5–55 °C. A mathematical relationship was proposed to predict its viscosity using the RSM method in Design-Expert software. The viscosity of this nanofluid was also optimized concerning temperature, SVF, and shear rate (SR). A point with a specification of T = 54.45 (°C), SVF = 0.06%, and SR = 11,899.24 (1/s) had an optimum viscosity of 39.0754 mPa s. Specification parameters of the ANN model were reported in this study as well. The results of the proposed mathematical correlation could not accurately predict, as well as the ANN and the predictions provided by ANN were more accurate.

这项研究的目的是优化MWCNT-MgO（35–65％）/ 5W50纳米流体的粘度，并与设计的人工神经网络（ANN）进行实验结果比较。实验检查是在固体体积分数（SVF）为0.05、0.1、0.25、0.5、0.75、1％和5-55°C的温度下进行的。提出了一种数学关系式，以使用Design-Expert软件中的RSM方法来预测其粘度。还针对温度，SVF和剪切速率（SR）对这种纳米流体的粘度进行了优化。规格为T的点 = 54.45（°C），SVF = 0.06％和SR = 11,899.24（1 / s）的最佳粘度为39.0754 mPa s。这项研究还报告了ANN模型的规范参数。所提出的数学相关性的结果无法准确预测，并且人工神经网络和人工神经网络提供的预测更加准确。