Numerical tackling for MHD Darcy-Forchheimer flow of water-based CNTs in a rotating frame with homogeneous-heterogeneous reactions: An artificial neural network approach

Abstract

Numerous scientific fields rely heavily on rotating flows, such as jet engine design, geophysical flows, turbine engineering, vacuum cleaner design, and many others. Prior research on rotational flow has largely disregarded the impact of viscous dissipation and homogeneous-heterogeneous responses. The present study investigates the Darcy-Forchheimer flow of carbon nanotubes (CNTs) in a rotating frame caused by a biaxial stretched plate with heat consumption and radiation. Furthermore, the mass transport mechanism is treated in terms of homogeneous-heterogeneous chemical reactions. The equations governing the flow are reduced into ordinary differential equations by using appropriate transforms. An advanced computational technique, bvp4c, has been used to provide precise numerical solutions.The computation of the resulting systems is also performed using an artificial neural network (ANN) and also the machine learning study shows a high correlation between the numerical and ANN findings, with a mean squared error (MSE) of 0.000053 for SWCNT and 0.000268 for MWCNT. A comprehensive investigation of several parameters yields both graphical and numerical outcomes. It has been discovered that larger values of the Forchheimer number and porosity parameter result in the decay of fluid velocities. The x − direction skin friction coefficient reduced 50% and the y − direction skin friction coefficient improved 46% when the magnetic field enhanced 200%. The 200% porosity parameter leads to reducing the local Nusselt number by 22% for both CNTs.