Estimating the Physical Properties of Nanofluids Using a Connectionist Intelligent Model Known as Gaussian Process Regression Approach

This work aims to develop a robust machine learning model for the prediction of relative viscosity nanoparticles (NPs) including Al2O3, TiO2, SiO2, CuO, SiC, and Ag based on most important input parameters affecting them covering size, concentration, thickness interfacial layer, intensive properties NPs. In order comprehensive artificial intelligence in this study, sixty-nine data samples were collected. To end, Gaussian process regression approach with four basic function kernels (Matern, squared exponential, rational quadratic) was exploited. It found that Matern outperformed other models R2 = 0.987, MARE (%) 6.048, RMSE 0.0577, STD 0.0574. precise yet simple can be good alternative complex thermodynamic, mathematical-analytical past.