Numerical treatment based on artificial neural network to Soret and Dufour effects on MHD squeezing flow of Jeffrey fluid in horizontal channel with thermal radiation

Abstract

The current investigation formulated an efficient computing technique by incorporating the algorithm of Artificial Neural Network Levenberg Marquardt Method (ANNLMM) to approximate Soret and Dufour effects on Magnetohydrodynamic squeezing flow of Jeffrey fluid (MHDSFJF) in MATLAB environment. Due to its efficiency and flexibility, the applied neural network model can accurately predict the output results. In the ANNLMM, 80% of the data is used for training and 10% is set for both the testing and validation processes. The flow under consideration is mathematically formulated with the help of Navier Stokes Equations. The partial differential equations (PDEs) are converted into ordinary differential equations (ODEs) by similarity variables. The effects of the physical parameters are discussed briefly. When the Hartmann number and Jeffrey fluid parameter increase, the concentration, temperature, and velocity profiles decreases. The temperature profile and heat transfer rate are improved by the effects of joule dissipation, Dufour numbers, and heat generation/absorption. On the other hand, as thermal radiation rises, the temperature profile decreases and the heat transfer rate increases. With an augment in Soret number, the mass transfer rate increases and the concentration profile slows down. Additionally, increasing chemical reactions, the mass transfer rate increases, but in convective chemical reactions, the contradiction is observed.

Keywords

• ANNLMM
• Squeezing flow
• MHD
• Intelligent computing
• Numerical computing
• Regression analysis