Intelligent computing for the dynamics of entropy optimized nanofluidic system under impacts of MHD along thick surface

Abstract

This article examines entropy production (EP) of magneto-hydrodynamics viscous fluid flow model (MHD-VFFM) subject to a variable thickness surface with heat sink/source effect by utilizing the intelligent computing paradigm via artificial Levenberg–Marquardt back propagated neural networks (ALM-BPNNs). The governing partial differential equations (PDEs) of MHD-VFFM are transformed into ODEs by applying suitable similarity transformations. The reference dataset is obtained from Adam numerical solver by the variation of Hartmann number (Ha), thickness parameter [Formula: see text], power index ([Formula: see text], thermophoresis parameter (Nt), Brinkman number (Br), Lewis number (Le) and Brownian diffusion parameter (Nb) for all scenarios of proposed ALM-BPNN. The reference data samples arbitrary selected for training/testing/validation are used to find and analyze the approximated solutions of proposed ALM-BPNNs as well as comparison with reference results. The excellent performance of ALM-BPNN is consistently endorsed by Mean Squared Error (MSE) convergence curves, regression index and error histogram analysis. Intelligent computing based investigation suggests that the rise in values of Ha declines the velocity of the fluid motion but converse trend is seen for growing values of [Formula: see text]. The rising values of Ha, Nt and Br improve the heat transfer but converse trend is seen for growing values of [Formula: see text]. The inclining values of Nt incline the mass transfer but it shows reverse behavior for escalating values of Le. The inclining values of Br incline the EP.