Numerical and artificial neural network framework for predicating MHD radiative flow and heat transfer of hybrid nanofluid with Cattaneo-Christov theory

Abstract

In this paper, the artificial neural network (ANN) is executed to scrutinize the heat transfer performance of water-based hybrid nanofluid (HNF) flow over a permeable stretching surface under the influence of an inclined magnetic field and thermal radiation. The advanced Cattaneo–Christov heat flux model (CCHFM), is introduced in this study in order to characterize the heat transfer features in a boundary layer (BL) slip flow, with thermal radiation, variable thermal conductivity and nanoparticles diffusion. The equation of energy is renovated taking thermal radiation, variable thermal conductivity, thermal jump and thermal relaxation effects. The flow model is constructed using BL approximation and necessary assumption while the Robin type boundary conditions are obtained by assuming thermal jump and velocity slip. The modified first order differential equations are solved using Bvp4c mechanism. The findings reveals that the coefficient of frictional drag is reduced by the magnetic parameter while contrary behavior is seen for nanoparticle volume fraction. The precision of the ANN model appeared astounding, with an error range of 10 $E^{-8}$ to 10 $E^{-9}$. The regression values that are nearer 1 indicate a good fit between the actual data and the forecasts. The thermal relaxation parameter diminished the temperature and heat dissipation.