Neural network analysis for unsteady flow of viscoelastic nanofluid with slip effects

Abstract

Nanomaterials elegantly amplify the thermal applications in different engineering processes and industrial fluids. In the era of nanotechnology, various sources have been specified to improve the thermal phenomenon and heat transfer performances. Recently, development in machine learning has suggested artificial neural network (ANN) algorithms to optimise the results and achieve peak performance. This work aims to present a novel ANN analysis for the slip flow of a viscoelastic nanofluid problem by assessing heat and mass transfer. The unsteady flow of the viscoelastic nanofluid over an oscillatory stretched surface has been considered. The radiative impact is utilised. The higher-order slip relations are imposed on the flow problem. The whole problem is modelled in partial differential equations. The computational fluid dynamics (CFD) simulations are performed using an implicit finite difference scheme. It is claimed that the current research problem is the first initiative for the ANN framework regarding the periodically oscillatory stretching surface flow. The physical impact of the problem is presented via a graphical approach.