A Hybrid Approach of Buongiorno's Law and Darcy–Forchheimer Theory Using Artificial Neural Networks: Modeling Convective Transport in Al2O3-EO Mono-Nanofluid Around a Riga Wedge in Porous Medium

Abstract

The inspiration for this study originates from a recognized research gap within the broader collection of studies on nanofluids, with a specific focus on their interactions with different surfaces and boundary conditions (BCs). The primary purpose of this research is to use an artificial neural network to examine the combination of Alumina-Engine oil-based nanofluid flow subject to electro-magnetohydrodynamic effects, within a porous medium, and over a stretching surface with an impermeable structure under convective BCs. The flow model incorporates Thermophoresis and Brownian motion directly from Buongiorno's model. Accounting for the porous medium's effect, the model integrates the Forchheimer number (depicting local inertia) and the porosity factor developed in response to the presence of the porous medium. The conversion of governing equations into non-linear ordinary differential systems is achieved by implementing transformations. A highly non-linear ordinary differential system's final system is solved using a numerical scheme (Runge–Kutta fourth-order). Findings indicate that the porosity factor positively impacts the skin friction and the momentum boundary layer. The influence suggests an increment in the frictional force and a decline in the velocity profile. The volume fraction, Prandtl number, and magnetic number significantly impact the flow profiles. The skin friction data is tabulated with some physical justifications.