Neural network and thermodynamic optimization of magnetized hybrid nanofluid dissipative radiative convective flow with energy activation

Ferdows, M.; Ahmed, Muktadir; Bhuiyan, M. A.; Anwar Bég, O; Çolak, Andaç Batur; Leonard, H.J

Abstract

This article, motivated by hybrid magnetic coating manufacturing developments, utilizes a neural network-based computational program to study the dynamics of hybrid magnetic nanofluids with entropy generation. A new physico-chemo-mathematical model has been presented to simulate the hybrid magnetic nano-coating flow along a stretching surface to a porous medium with viscous heating. A Rosseland flux model is used for radiation heat transfer, and Darcy's model for the isotropic porous medium. The stretching sheet is porous and wall suction or injection are possible. A robust neural network has been deployed to optimize the physical parameters controlling transport characteristics of hybrid nanofluids. Specifically, 2 hybrid nanoparticle combination are addressed, namely graphite oxide (GO)-molybdenum disulfide (í µí±€í µí±œí µí±† 2) and copper (Cu)-silicon dioxide (í µí±†í µí±–í µí±‚ 2), both with engine oil as the base fluid. The dimensional boundary layer model is transformed via suitable scaling variables from a partial differential system into a dimensionless non-linear coupled ordinary differential system. The transformed boundary value problem is solved numerically with the BVP4C subroutine in the symbolic software MATLAB, which achieves exceptional accuracy. Validation with previous simpler studies is conducted and good correlation is obtained. The neural network optimization analysis which incorporates Bayesian regularization as the training algorithm. The Bejan entropy generation minimization (EGM) analysis shows that with increasing radiation parameter í µí± í µí±‘ , both entropy generation rate and Bejan number are increased. Furthermore, an elevation in Brinkman number í µí°µí µí±Ÿ leads to an upsurge in entropy generation rate and a downtrend in Bejan number. The numerical solution of the boundary value problem reveals that with increment in nanoparticle solid volume fraction í µí¼‘ 2 , magnetic parameter í µí±€, inverse permeability parameter í µí¼–, surface injection parameter (í µí± < 0), Eckert number í µí°¸í µí± and radiation parameter í µí± í µí±‘ and with a decrement in suction parameter (í µí± > 0) and Prandtl number í µí±ƒí µí±Ÿ, there is a strong enhancement in temperature magnitude and thermal boundary layer thickness. With greater nanoparticle solid volume fraction í µí¼‘ 2 , magnetic parameter í µí±€, inverse permeability parameter í µí¼–, suction parameter í µí± and a reduction in thermal buoyancy parameter í µí¼†, strong flow deceleration is induced, and momentum boundary layer thickness is increased. Skin friction coefficient is substantially boosted with lower values of magnetic parameter í µí±€, inverse permeability parameter í µí¼–, suction parameter í µí± and higher values of thermal buoyancy parameter í µí¼†. There is a significant decrement also computed in

Citation

Ferdows, M., Ahmed, M., Bhuiyan, M. A., Anwar Bég, O., Çolak, A. B., & Leonard, H. (in press). Neural network and thermodynamic optimization of magnetized hybrid nanofluid dissipative radiative convective flow with energy activation. Numerical Heat Transfer, Part A Applications, 1-35. https://doi.org/10.1080/10407782.2024.2329312

• Journal Article Type: Article
• Acceptance Date: Mar 6, 2024
• Online Publication Date: Mar 21, 2024
• Deposit Date: Mar 7, 2024
• Publicly Available Date: Mar 22, 2025
• Journal: Numerical Heat Transfer, Part A: Applications
• Print ISSN: 1040-7782
• Publisher: Taylor and Francis
• Peer Reviewed: Peer Reviewed
• Pages: 1-35
• DOI: https://doi.org/10.1080/10407782.2024.2329312
• Keywords: Condensed Matter Physics, Numerical Analysis