Applying Artificial Neural Networks (ANNs) for prediction of the thermal characteristics of engine oil –based nanofluids containing tungsten oxide -MWCNTs
Farid Soltani, Mehdi Hajian, Davood Toghraie, Abbasali Gheisari, Nima Sina, As’ad Alizadeh
Abstract
This paper aims to determine the thermal conductivity (knf) of oxide of tungsten (WO3)-MWCNTs/hybrid engine oil, through an Artificial Neural Network (ANN). Nanofluid were prepared by the suspension of nanoparticles in engine oil. The experiments were conducted at a volume fraction of nanoparticles ϕ = 0.05 to ϕ = 0.6%, as well as a temperature range of T = 20°C–60 °C. The ANN was then used to estimate the knf, and the optimum neuron number was 7. Results showed that the absolute error values of the ANN method in many points are zero. Also, the ANN had smaller error values compared to the correlation method. ANN showed acceptable performance and correlation coefficient. Also, a correlation method was used to predict knf.