Modeling of Darcy–Forchheimer bioconvective Powell Eyring nanofluid with artificial neural network

Abstract

Nano-engineering has recently grown to include the usages of nanoparticles in combination with base fluids to improve the thermal properties of pure fluids. Today’s industry focuses primarily on thermal machine efficiency, and nanomaterials are the key to achieving this goal. The slip and Darcy–Forchheimer phenomena are studied for bioconvective implementations in a Powell–Eyring nanofluid model confined by a stretching surface via artificial neural network in current study. During the research, the activation energy, convective boundary condition and thermal radiation phenomena are considered as novel impacts. The governing expressions are formulated according to fundamental rules. Numerical simulations using a Runge–Kutta fourth order technique via shooting procedure are used to obtain the solution and then applies artificial neural network. A data set has been created for various flow scenarios, and developed an artificial neural network model to predict skin friction coefficient, local Sherwood number, local motile density of microorganisms and local Nusselt number values . The results of the study showed that the developed artificial neural network models can make predictions with very low error, not exceeding 0.53% on average.