Insights into the Estimation of the Enhanced Thermal Conductivity of Phase Change Material-Containing Oxide Nanoparticles using Gaussian Process Regression Method

Thermal conductivity (TC) of a phase change material (PCM) may be enhanced by distributing nanostructured materials (NSMs) termed nano-PCM. It is critical to accurately estimate the TC nano-PCM assess heat transfer during transition processes, namely, solidification and melting. Here, we propose Gaussian process regression (GPR) strategies involving four various kernel functions (KFs) (including exponential (E), squared (SE), rational quadratic (RQ), matern (M)) predict n-octadecane as PCM. The accessible computational techniques indicate accuracy our proposed GPR model compared previously methods. In this research, foremost forecasting strategy has been considered method. This consists KF whose R2 values training testing phases are 1 1, respectively. following, sensitivity analysis (SA) used explore effectiveness variables in terms outputs shows that temperature (T) nanofluid (NF) most efficient input parameter. work describes physical properties NFs parameters should determined optimize their efficiency.