A cross-fluid heat transfer analysis using neural networks over porous rotating disk
Fahim Ullah, Muhammad Bilal Ashraf
Abstract
This research explores the complex interaction of incompressible cross-fluid flow, heat, and mass transfer characteristics on a porous rotating disk. The study employs sophisticated mathematical methods, including similarity transformations, to convert governing partial differential equations into nonlinear ordinary differential equations. These equations are then solved using a sophisticated numerical method, the fourth-class boundary value problem. We employ an Artificial Neural Networks algorithm with backpropagation Levenberg–Marquardt Scheme to analyze the heat transfer mechanism quantitatively. Our results provide accurate values for the Nusselt number, the Sherwood number, and the skin friction coefficient. The examination addresses this complex system's fluid mechanics and transport phenomena with potential applications in engineering and industrial processes.