Cattaneo-christov heat flux model of 3D hall current involving biconvection nanofluidic flow with Darcy-Forchheimer law effect: Backpropagation neural networks approach

Abstract

Recently, the applications of artificial intelligence through soft computing and machine learning algorithms have become the focal point of researcher's consideration on account of their convenience for accurate modelling, ease in simulation and effective assessment. This article endorses soft computing based backpropagated neural networks (BNNs) with Levenberg Marquardt technique (LMT), i.e., BNN-LMT, over a novel mathematical model based on biconvection, second grade combine convection nanofluid (BSCCN) flow associated with Cattaneo-Christove (CC) heat flux model for thermal transportation and viscous dissipation, Darct-Forhheimer (DF) law for permeable medium and Hall (H) current for high intensity electric conductive on flow motion model, i.e., BSCCN-CCDFH flow model. Self-similar transformations are used to reduce the multivariable function model to mathematical system of a single variable. The assessment of thermal buoyancy parameter, Hall parameter, porosity parameter, thermophoresis factor, Lewis number and Peclet number over the flow rate dynamics, energy, nanofluid concentration and microorganism concentration profiles is made through dataset based on Adam numerical solver for different physical quantity based scenarios. The results of exhaustive numerical simulation studies show that the proposed technique BNN-LMT is an efficient, reliable, accurate and rapid convergent stochastic numerical solver exploited viably for the BSCCN-CCDFH flow model having number of physical variations.