Scholarlink

<p>The prediction of heat transport properties in electrically conducting fluid has significant importance because of their several applications in energy systems, thermal management, biomedical engineering, and various material processing. In particular, magnetohydrodynamic (MHD) micropolar bioconvective nanofluids have considerable interest owing to their microstructural effects. Motivated by the current demand and enhanced thermal performance, the present study introduces a neural network for predicting the motile microorganism associated to heat transportation in a micropolar nanofluid flow under slip conditions. The proposed model incorporates the thermo-physical properties including Joule dissipation, internal heat source, and a binary chemical reaction with the motile microorganism profiles. The governing coupled system of equations is handled numerically, and further, structural behavior of certain factors is elaborated. A machine learning approach using artificial neural network (ANN) is proposed in predicting motile number utilizing scaled conjugate gradient (SCG) technique. This shows an efficient and robust technique in handling the nonlinear regression model. The results demonstrate an excellent agreement between machine learning prediction and numerical solution presenting the computational efficiency of SCG-based NN. It shows a promising tool for real-time prediction and optimization of heat transport in MHD micropolar bioconvective nanofluid system.</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 prediction on motile microorganism behavior during heat transfer in MHD micropolar bioconvective nanofluids

  • 期刊论文

  • 发表日期：

    2026年5月18日

查看全文
  • P. P. Nayak,
  • S. R. Mishra,
  • Priya Mathur,
  • Subhajit Panda

摘要

The prediction of heat transport properties in electrically conducting fluid has significant importance because of their several applications in energy systems, thermal management, biomedical engineering, and various material processing. In particular, magnetohydrodynamic (MHD) micropolar bioconvective nanofluids have considerable interest owing to their microstructural effects. Motivated by the current demand and enhanced thermal performance, the present study introduces a neural network for predicting the motile microorganism associated to heat transportation in a micropolar nanofluid flow under slip conditions. The proposed model incorporates the thermo-physical properties including Joule dissipation, internal heat source, and a binary chemical reaction with the motile microorganism profiles. The governing coupled system of equations is handled numerically, and further, structural behavior of certain factors is elaborated. A machine learning approach using artificial neural network (ANN) is proposed in predicting motile number utilizing scaled conjugate gradient (SCG) technique. This shows an efficient and robust technique in handling the nonlinear regression model. The results demonstrate an excellent agreement between machine learning prediction and numerical solution presenting the computational efficiency of SCG-based NN. It shows a promising tool for real-time prediction and optimization of heat transport in MHD micropolar bioconvective nanofluid system.