Scholarlink

<p>Nanofluids, first introduced by Choi and Eastman in 1995 have demonstrated the revolutionizing in every application from renewable energy to space explorations. The present review assesses the revolutionary status of heat transfer technologies driven by the implementation of nanofluids, artificial intelligence (AI) and complex modeling methods. Nanofluids deliver superior performance in terms of thermal conductivity compared to conventional heat transfer fluids such as, water, oil, ethylene glycol. This review highlights the hybrid nanofluids such as A<InlineEquation ID="IEq1"> <InlineMediaObject> <ImageObject Color="BlackWhite" FileRef="41939_2025_891_Article_IEq1.gif" Format="GIF" Height="16" Rendition="HTML" Resolution="72" Type="Linedraw" Width="31" /> </InlineMediaObject> <EquationSource Format="TEX">\({\text{l}}_{2}{\text{O}}_{3}\)</EquationSource> <EquationSource Format="MATHML"><math> <mrow> <msub> <mtext>l</mtext> <mn>2</mn> </msub> <msub> <mtext>O</mtext> <mn>3</mn> </msub> </mrow> </math></EquationSource> </InlineEquation>-MWCNT which can theoretically enhance thermal conductivity up to 79.06%. However, complexity of these materials often challenges conventional numerical methods, necessitating the advance techniques like lattice Boltzmann method (LBM) and multiscale modeling. AI-driven methodologies such as artificial neural networks (ANNs), Convolutional neural networks (CNNs) and recurrent neural networks (RNNs) reveal themselves as valuable experimental predictors in the estimations of nanoparticle’s thermophysical stability. Despite these advancements significant logistical challenges remain including scalability, stability and cost efficiency. This review underscores the importance of bridging experimental findings with theoretical models to enhance the role of nanofluids in heat recovery and development programs.</p> Graphical abstract <p></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

AI-powered optimization and numerical techniques for nanofluid heat transfer systems-a review

  • 期刊论文

  • 发表日期：

    2025年5月26日

查看全文
  • Mohsin Raza,
  • Muazzam Faiz,
  • Waqar U. I. Hassan,
  • Muzamil Abbas,
  • Jawad Raza,
  • Zahid Kumail,
  • Tahsin Nawaz,
  • Sania Shabir,
  • Ali Jan,
  • Feng-Chen Li

摘要

Nanofluids, first introduced by Choi and Eastman in 1995 have demonstrated the revolutionizing in every application from renewable energy to space explorations. The present review assesses the revolutionary status of heat transfer technologies driven by the implementation of nanofluids, artificial intelligence (AI) and complex modeling methods. Nanofluids deliver superior performance in terms of thermal conductivity compared to conventional heat transfer fluids such as, water, oil, ethylene glycol. This review highlights the hybrid nanofluids such as A \({\text{l}}_{2}{\text{O}}_{3}\) l 2 O 3 -MWCNT which can theoretically enhance thermal conductivity up to 79.06%. However, complexity of these materials often challenges conventional numerical methods, necessitating the advance techniques like lattice Boltzmann method (LBM) and multiscale modeling. AI-driven methodologies such as artificial neural networks (ANNs), Convolutional neural networks (CNNs) and recurrent neural networks (RNNs) reveal themselves as valuable experimental predictors in the estimations of nanoparticle’s thermophysical stability. Despite these advancements significant logistical challenges remain including scalability, stability and cost efficiency. This review underscores the importance of bridging experimental findings with theoretical models to enhance the role of nanofluids in heat recovery and development programs.

Graphical abstract