Darcy-Forchheimer hybrid nanofluid flow over the rotating Riga disk in the presence of chemical reaction: Artificial neural network approach

Abstract

The aim of present study is to examine the augmentation of thermal energy transfer in hybrid nanofluid flow caused by a rotating Riga disk in the presence of thermal radiation and chemical reaction. The silver and aluminium oxide nanoparticles are used to examine the thermal effect of water base fluid. The Darcy-Forchheimer model is considered to endorse the inertial and porous media effects and makes the model more realistic from the physical scenario. Levenberg-Marquardt backpropagation algorithm is considered to analyze the hybrid nanofluid’s properties. Using scaling group transformations, the governing partial differential equations are transformed into a system of ordinary differential equations. Resulting ordinary differential equations are solved numerically by applying a suitable shooting technique by MATLAB. The results obtained for the governing differential equations have been incorporated into a dataset on which the neural network has been trained. The effects of physical parameters have been analyzed for velocity, temperature, and concentration profiles. The determination, designing, convergence, verification, and stability of the Levenberg-Marquardt backpropagation neural network algorithm are validated on the assessment of achieved accuracy through performance, fit, regression, and error histogram plots for the discussed hybrid nanofluid. It is observed that fluid velocity reduces for enhanced Darcy-Forchheimer number, magnetic parameters and boosted for enhanced modified Hartmann number. Temperature profile increases by increasing the Brownian motion and thermophoresis parameters.