Intelligent neuro-computing for entropy generated Darcy-Forchheimer mixed convective fluid flow

In the present article, the Darcy-Forchheimer mixed convective flow model (DFMC-FM) is examined by utilizing the algorithm of Levenberg Marquardt with backpropagated artificial neural networks (ALM-BANN). Partial differential equations representing the proposed DFMC-FM are converted to non-linear ordinary differential equations (ODEs) by similarity transformation. These ODEs are solved by Adam numerical method to interpret the reference dataset of ALM-BANN for various scenarios of DFMC-FM by varying curvature parameter, Forchheimer number, chemical reaction parameter, slip parameter, Schmidt number and activation energy parameter. By testing, validation and training process, the solutions for designed DFMCFM are interpreted. The performance analysis of DFMC-FM is validated through regression analysis, error histogram studies and MSE results. Graphs are given in figures for velocity profile, temperature profile and concentration profile. The velocity and temperature distributions show an increasing behavior with the upsurge in the curvature parameter, whereas the velocity profile decreases with the growth in Forchheimer number and slip parameter. An increase in the chemical reaction parameter and Schmidt number values leads to a decline in concentration profile, but the increase in activation energy parameter increases the concentration profile.(c) 2022 International Association for Mathematics and Computers in Simulation (IMACS). Published by Elsevier B.V. All rights reserved.