Heat and Mass Transfer Analysis of Al2O3-Water and Cu-Water Nanofluids Over a Stretching Surface with Thermo-diffusion and Diffusion-Thermo Effects Using Artificial Neural Network

Abstract

The present paper deals with the artificial neural network (ANN) modeling of heat and mass transfer on magnetohydrodynamic (MHD) convective flow of Al2O3-water and Cu-water nanofluids past a stretching sheet through porous media with thermo-diffusion and diffusion-thermo effects. The set of suitable similarity transformations are employed to alter the nonlinear partial differential equations into ordinary differential equations. The solutions of the resulting nonlinear differential equations are solved numerically with the help of Runge–Kutta Fehlberg fourth–fifth order method accompanied by shooting technique, and then, the ANN is applied to them. The multilayer feedforward neural network with backpropagation training algorithm is used for predicting the desired outputs. The influence of various physical parameters on velocity, temperature and concentration profiles is explored and discussed in detail. The friction factors, heat and mass transfer rates are predicted using ANN. The numerical results and the results of the ANN are in good agreement with errors less than 5%. According to the findings of this paper, the ANN approach is reliable and more effective for simulating heat and mass transfer in MHD nanofluid flow over a stretched sheet.