Application of artificial intelligence and using optimal ANN to predict the dynamic viscosity of Hybrid nano-lubricant containing Zinc Oxide in Commercial oil

The objective of present research is to investigate the effect of temperature, the volume fraction of nanoparticles (phi) and shear rate (gamma) to predict the dynamic viscosity (mu nf) of MWCNT-ZnO (50-50)/oil SAE50 nano-lubricant by using an artificial neural network (ANN). The second principal component was used as an indicator of variance and various statistical characteristics of all the data. This is used to identify outliers. Due to the Principal Component Analysis (PCA) minimizing quadratic norms, it has the same least-squares problems, or it becomes Gaussian the sensitivity to outliers. Sensitivity analysis was used to evaluate the importance and role of temperature, gamma, and phi in experimental mu nf variations. The results show that the estimated values of the ANN simulation have a strong correlation with the experimental data and the predicted data extracted from the ANN are similar to the targets close to mu nf of MWCNT-ZnO (50-50)/oil SAE50 nano-lubricant by ANN simulation with 7 neurons model. Finally, ANN was generated and tested with experimental data sets and the results show that there was a good agreement between the actual and predicted ANN values.

Automated summary

This research investigates the effect of temperature, volume fraction of nanoparticles, and shear rate on the dynamic viscosity of a nano-lubricant. An artificial neural network is used to predict the viscosity, and sensitivity analysis is performed to evaluate the importance of different parameters.