Rheological behavior characteristics of ZrO2-MWCNT/10w40 hybrid nano-lubricant affected by temperature, concentration, and shear rate: An experimental study and a neural network simulating

In this study, the ZrO2-MWCNT (70%–30%)/10w40 hybrid Nano-lubricant was experimentally evaluated in terms of rheological changes. ZrO2 (40 nm) and MWCNTs nanoparticles with an inner diameter of 3–5 nm were used to prepare the Nano-lubricant. Particles were weighted for solid volume fractions of 0.05%, 0.1%, 0.25%, 0.5%, 0.75%, and 1% and the nano-lubricant was prepared. Then, the viscosity of Nano-lubricants was measured at different shear rates between 5 and 55 °C. The results showed that the pure oil was non-Newtonian and the nano-lubricant was pseudoplastic. Calculation and checking the power law and consistency coefficients showed that the increase in temperature intensifies the non-Newtonian behavior. Based on the results, at temperature of 55 °C and a volume fraction of 1% condition, maximum of dynamic viscosity enhancement (DVE) was reported. Based on experimental data, a new correlation was proposed at different temperatures and the solid volume fraction, and the sensitivity of nano-lubricant was measured. An Artificial Neural Network (ANN) with two hidden layers and six neurons was designed to predict the viscosity. R2, MSE, and AARD values were obtained as much as 0.9905, 7.0631e-05, and 0.0051 ANN, respectively. Comparison of experimental data with new correlations and ANN showed that the performance of neural network was better in predicting the viscosity data.