Intelligent predictive neural network analysis of stefan blowing impacts on chemical reactive flow of Boger nanofluid with thermophoresis and brownian motion

Abstract

This study scrutinizes the effect of thermal radiation and Stefan blowing on the chemical reactive flow of Boger nanofluid across a stretched sheet with Darcy Forchheimer medium and heat generation using an intelligent computational framework based on Artifice neural network-Bayesian regularization. Furthermore, Brownian motion and thermophoresis properties have been examined. The suggested model of how Stefan blowing affects the chemical reactive flow of a Boger nanofluid with thermophoresis effects and Brownian motion has useful applications in a number of industrial and engineering operations. In chemical reactors, nano-coating technologies, and polymer processing, this model is essential for improving heat and mass transport processes. While the Boger nanofluid model accurately depicts non-Newtonian behaviour pertinent to biofluids and complex lubricants, Stefan blowing consideration offers insights on evaporation or suction effects. For the purpose of maximizing nanoparticle dispersion in cooling systems, fuel cells, and medicinal devices like targeted drug delivery systems where exact control over particle motion and chemical reactivity is crucial, Brownian motion and thermophoresis are also critical. The velocity profile improves as the Stefan blowing parameter values rise, but the thermal and concentration profiles decrease.