Scholarlink

<p>Nanofluids have emerged as advanced heat transfer media with significant applications in industrial, biomedical, and energy systems. This study aims to examine the thermal and mass transport behavior of a bioconvective Oldroyd-B nanofluid over a convectively heated porous surface using artificial neural network (ANN) modeling. The mathematical formulation incorporates nonlinear thermal radiation, activation energy, Cattaneo–Christov heat and mass fluxes (accounting for non-Fourier effects), viscous dissipation, slip boundary conditions, magnetic field effects, and porous medium permeability. The governing equations are solved with the Levenberg–Marquardt backpropagation algorithm (LMBNN) trained on datasets generated by the bvp4c solver, to achieve fast convergence and high accuracy. Results indicate that the ANN-predicted absolute error remains within 10<sup>9</sup>–10⁻<sup>10</sup> and that parameter variations strongly influence velocity, thermal, and concentration boundary layers. The study concludes that ANN-based models provide a reliable and intelligent computational framework for nonlinear transport phenomena, offering practical insights for improving thermal extrusion, renewable energy systems, power plant efficiency, and electronic cooling technologies.</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

Artificial neural network modeling of heat transfer in bioconvective Oldroyd-B nanofluids with nonlinear radiation and activation energy

  • 期刊论文

  • 发表日期：

    2025年11月5日

查看全文
  • Raheela Razzaq,
  • Shazia Habib,
  • Zeeshan Khan,
  • Umer Farooq,
  • Bandar Almohsen

摘要

Nanofluids have emerged as advanced heat transfer media with significant applications in industrial, biomedical, and energy systems. This study aims to examine the thermal and mass transport behavior of a bioconvective Oldroyd-B nanofluid over a convectively heated porous surface using artificial neural network (ANN) modeling. The mathematical formulation incorporates nonlinear thermal radiation, activation energy, Cattaneo–Christov heat and mass fluxes (accounting for non-Fourier effects), viscous dissipation, slip boundary conditions, magnetic field effects, and porous medium permeability. The governing equations are solved with the Levenberg–Marquardt backpropagation algorithm (LMBNN) trained on datasets generated by the bvp4c solver, to achieve fast convergence and high accuracy. Results indicate that the ANN-predicted absolute error remains within 109–10⁻10 and that parameter variations strongly influence velocity, thermal, and concentration boundary layers. The study concludes that ANN-based models provide a reliable and intelligent computational framework for nonlinear transport phenomena, offering practical insights for improving thermal extrusion, renewable energy systems, power plant efficiency, and electronic cooling technologies.