Gradient descent machine learning regression for MHD flow: Metallurgy process

Abstract

Machine learning techniques have received a lot of interest in the exploration to minimize the computational cost of computational fluid dynamics simulation. The present article investigates application of heat and mass transfer in magnetohydrodynamic flow over a stretching sheet in metallurgy process by employing the learning methodology based on gradient descent. It is anticipated that the consequences of the current work will show the benefits of future research to enhance the development in the domains of science and engineering. A tabular and graphical evaluation greatly demonstrates the similarity between current and previous outcomes in the prescribed fluid flow model.