Lie symmetry neural networking for heat transfer in magnetized williamson fluid (MWF) with heat source (HS) and thermal slip (TS)

In the analysis, design, and optimization of a wide range of engineering applications involving stretching surfaces and fluid flow, the skin friction coefficient (SFC) at a stretching surface with heat transfer is an important parameter that reflects the fluid dynamics, heat transfer characteristics, and surface interactions. Owing such importance, the purpose of present article is offer artificial neural networking remedy for evaluation of SFC for Williamson flow field with thermal slip and heat source effects. The Williamson fluid flow is realized by considering surface stretching with an externally supplied magnetic field. The energy equation is used to address the heat transmission. The constructed differential system for flow field is solved by conjecturing artificial neural networking with Lie symmetry and shooting methods. Artificial Neural Networking (ANN) model is developed to predict the surface quantity namely SFC at thermally magnetized surface. The major findings includes the variation in SFC for pertinent flow parameters and we found that in the presence of heat transfer aspects, the SFC admits declining nature towards Weissenberg number while opposite is the case for magnetic field parameter.