Prediction of rheological behavior of SiO2-MWCNTs/10W40 hybrid nanolubricant by designing neural network

Abstract

This paper assesses the viscosity of 10W40 engine oil containing hybrid nanomaterial at different temperatures using artificial neural network (ANN). The volumetric combination of hybrid nanomaterial is 90% silica (SiO2) and 10% multi-walled carbon nanotubes (MWCNTs). Solid volume fraction, temperatures and shear rate were considered as input variables for ANN, and relative viscosity was output parameter. In order to predict viscosity data of SiO2-MWCNTs (90:10%)/10W40, a comparison between the experimental viscosity and that obtained from previous theoretical models was made. This comparison showed that none of the previous theoretical models were able to estimate the viscosity data. Therefore, a neural network was designed to predict the relative viscosity of hybrid nanolubricant. Artificial neural network function was utilized for viscosity data approximation with excellent precision as R2 value was 0.9948.