A novel integrated model to improve the dynamic viscosity of MWCNT-Al2O3 (40:60)/Oil 5W50 hybrid nano-lubricant using artificial neural networks (ANNs)

In this study, a unique incorporated version is presented to enhance the dynamic viscosity of MWCNT- Al 2 O 3 (40:60)/Oil 5W50 hybrid nanofluid the usage of the 3 maximum vast and vital powerful parameters corresponding to temperatures, solid volume fractions and shear rates. An empirical relationship between energy consumption and these characteristics is presented. Thus, ANNs are used to develop a high-level data analysis model to predict the dynamic viscosity of MWCNT-Al 2 O 3 (40:60)/Oil 5W50 hybrid nanofluid. A sensitivity analysis is employed to assess the importance of various parameters of MWCNT- Al 2 O 3 (40:60)/Oil 5W50 hybrid nanofluid dynamic viscosity and the position of temperature, solid volume fraction and shear rate in simulation. It is found that the highest hybrid nanofluid dynamic viscosity values are observed at temperatures below 5 °C. In addition, the hybrid nanofluid dynamic viscosity is reduced by shear rate changes from 0 rpm to 800 rpm. Statistical analysis shows that the model performance is nearly equal, ranging between 0.98, 0.978, and 0.925, and that the errors are less than 2.6% for the training, testing, and validation phases, respectively. Overall, it could be determined that the ANN simulation can generate the connection between the measured dynamic viscosity and anticipated dynamic viscosity of hybrid nanofluid. • A novel integrated model is proposed to improve dynamic viscosity of HNF. • ANN is employed to develop an advanced data analytic model. • SA is used to assess the importance of different parameters of HNF dynamic viscosity. • the highest HNF dynamic viscosity values are observed at temperatures below 5 °C. • ANN can generate the relationship between the measured viscosity and predicted viscosity.