AI-driven analysis of Darcy-Forchheimer EMHD boundary layer flow in thermal hybrid nanofluids

Abstract

This study thoroughly examined the complex electro-magnetohydrodynamic (EMHD) boundary layer flow of ternary hybrid nanofluids (THNP), specifically, Ti 6Al4V-ZnO-Fe2O3, over stretching-shrinking and permeable surfaces, and recognized the important impact of the nonlinear Darcy-Forchheimer law and thermal radiation. The THNP, comprised of three distinct nanoparticles including: titanium alloy Ti6Al4V (6% aluminum, 4% vanadium, balance titanium), zinc oxide ZnO, and iron oxide Fe2O3 suspended in a base fluid, is used to enhance both thermal and flow properties. The model comprehensively addressed inertial effects in porous media through the Darcy-Forchheimer drag, as well as the electromagnetic forces and thermal radiation. The governing partial differential equations were transformed into nonlinear ordinary differential equations via similarity transformations, which were solved through an intelligent numerical approach using artificial neural networks (ANN). A thorough analysis was conducted on the effect of important parameters such as the Darcy-Forchheimer permeability, nanoparticle volume fractions, stretching/shrinking rates, surface permeability, and radiation intensity on the velocity and temperature profiles. The results are shown graphically and discussed, providing insight related to the fluid dynamics and heat-transfer phenomena in such advanced systems.