<p>This work investigates the magnetohydrodynamic flow of a dissipative Ree-Eyring fluid over a permeable stretching surface, subjected to an inclined magnetic field relative to the direction of fluid motion. Thermal transport is analyzed using the Cattaneo-Christov heat flux model, which accounts for thermal relaxation effects absent in the classical Fourier formulation. The flow regime further incorporates the influence of a Darcy-Forchheimer porous medium, introducing both linear and quadratic drag contributions to the momentum equation. The main equations have initially evaluated numerically through bvp4c approach in dimensionless form. The dataset generated through the bvp4c numerical scheme is subsequently employed to implement the artificial neural network (ANN) methodology. It has revealed as outcomes of this work that optimal convergence achieved through ANN approach at epochs 134, 205, and 275 across the three scenarios. Error histograms and fitness evaluation confirm solution stability, progressive improvement, and close alignment between predicted and expected values. With growth in Weissenberg number <InlineEquation ID="IEq1"> <EquationSource Format="TEX">\(\left( {We} \right)\)</EquationSource> </InlineEquation>, magnetic parameter <InlineEquation ID="IEq2"> <EquationSource Format="TEX">\(\left( M \right)\)</EquationSource> </InlineEquation>, Darcy Forchheimer factor <InlineEquation ID="IEq3"> <EquationSource Format="TEX">\(\left( {Fr} \right)\)</EquationSource> </InlineEquation> and porosity parameter <InlineEquation ID="IEq4"> <EquationSource Format="TEX">\(\left( K \right)\)</EquationSource> </InlineEquation> there is decline in velocity <InlineEquation ID="IEq5"> <EquationSource Format="TEX">\(\left\{ {f^{\prime}\left( \eta \right)} \right\}\)</EquationSource> </InlineEquation>. Thermal distribution <InlineEquation ID="IEq6"> <EquationSource Format="TEX">\(\left\{ {\theta \left( \eta \right)} \right\}\)</EquationSource> </InlineEquation> augmented with growth in radiation parameter <InlineEquation ID="IEq7"> <EquationSource Format="TEX">\(\left( {Rd} \right)\)</EquationSource> </InlineEquation>, Brownian motion parameter <InlineEquation ID="IEq8"> <EquationSource Format="TEX">\(\left( {Nb} \right)\)</EquationSource> </InlineEquation>, thermo-phoresis parameter <InlineEquation ID="IEq9"> <EquationSource Format="TEX">\(\left( {Nt} \right)\)</EquationSource> </InlineEquation>, heat source/sink factor <InlineEquation ID="IEq10"> <EquationSource Format="TEX">\(\left( Q \right)\)</EquationSource> </InlineEquation> while declined with higher Prandtl number <InlineEquation ID="IEq11"> <EquationSource Format="TEX">\(\left( {\Pr } \right)\)</EquationSource> </InlineEquation> and thermal relaxation time parameter <InlineEquation ID="IEq12"> <EquationSource Format="TEX">\(\left( \delta \right)\)</EquationSource> </InlineEquation>.</p>

错误:搜索内容不能为空,请输入英文关键词
错误:关键词超出字数限制,请精简
高级检索

Neural network-driven analysis of magnetized dissipative Ree-Eyring fluid flow with Cattaneo-Christov heat flux on a permeable surface

  • Ebrahem A. Algehyne,
  • Safa Elshaikh Saad Ahmed,
  • Muntasir Suhail,
  • Fahad Maqbul Alamrani,
  • Anwar Saeed,
  • Gabriella Bognár

摘要

This work investigates the magnetohydrodynamic flow of a dissipative Ree-Eyring fluid over a permeable stretching surface, subjected to an inclined magnetic field relative to the direction of fluid motion. Thermal transport is analyzed using the Cattaneo-Christov heat flux model, which accounts for thermal relaxation effects absent in the classical Fourier formulation. The flow regime further incorporates the influence of a Darcy-Forchheimer porous medium, introducing both linear and quadratic drag contributions to the momentum equation. The main equations have initially evaluated numerically through bvp4c approach in dimensionless form. The dataset generated through the bvp4c numerical scheme is subsequently employed to implement the artificial neural network (ANN) methodology. It has revealed as outcomes of this work that optimal convergence achieved through ANN approach at epochs 134, 205, and 275 across the three scenarios. Error histograms and fitness evaluation confirm solution stability, progressive improvement, and close alignment between predicted and expected values. With growth in Weissenberg number \(\left( {We} \right)\) , magnetic parameter \(\left( M \right)\) , Darcy Forchheimer factor \(\left( {Fr} \right)\) and porosity parameter \(\left( K \right)\) there is decline in velocity \(\left\{ {f^{\prime}\left( \eta \right)} \right\}\) . Thermal distribution \(\left\{ {\theta \left( \eta \right)} \right\}\) augmented with growth in radiation parameter \(\left( {Rd} \right)\) , Brownian motion parameter \(\left( {Nb} \right)\) , thermo-phoresis parameter \(\left( {Nt} \right)\) , heat source/sink factor \(\left( Q \right)\) while declined with higher Prandtl number \(\left( {\Pr } \right)\) and thermal relaxation time parameter \(\left( \delta \right)\) .