Scholarlink

<p>The present study develops a hybrid analytical-computational approach to the thermal transport study of Reiner–Rivlin nanofluid flow with Arrhenius activation energy effects, aligning with UN Sustainable Development Goals 9 (Industry, Innovation, and Infrastructure) and 12 (Responsible Consumption and Production). The governing nonlinear partial differential equations are reduced to a coupled system of ordinary differential equations via Lie group transformations and solved numerically. An artificial neural network (ANN), trained using the Levenberg–Marquardt algorithm, is integrated with a modified Garson sensitivity analysis to quantify the effect of important parameters on the heat transfer. The ANN model exhibits excellent prediction accuracy with an overall correlation coefficient <InlineEquation ID="IEq1"> <EquationSource Format="TEX">\(R=0.99977\)</EquationSource> <EquationSource Format="MATHML"><math> <mrow> <mi>R</mi> <mo>=</mo> <mn>0.99977</mn> </mrow> </math></EquationSource> </InlineEquation>. Results show that the thermal Biot number yields the highest positive impact, increasing the heat transfer rate by 54.61% per unit increment, while the cross-viscous parameter has the least effect. The framework presented offers not only accurate modeling but also interpretable parameter sensitivity information for high-end energy, biomedical, and microfluidic systems.</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

Advanced neural-based sensitivity analysis on nonlinear thermal transport in Reiner–Rivlin nanofluid flow using modified Garson algorithm

  • 期刊论文

  • 发表日期：

    2026年2月24日

查看全文
  • R. Akshara,
  • Sujesh Areekara,
  • A. S. Sabu,
  • Alphonsa Mathew,
  • Anukul Sachan,
  • K. V. Nagaraja,
  • Ioannis E. Sarris

摘要

The present study develops a hybrid analytical-computational approach to the thermal transport study of Reiner–Rivlin nanofluid flow with Arrhenius activation energy effects, aligning with UN Sustainable Development Goals 9 (Industry, Innovation, and Infrastructure) and 12 (Responsible Consumption and Production). The governing nonlinear partial differential equations are reduced to a coupled system of ordinary differential equations via Lie group transformations and solved numerically. An artificial neural network (ANN), trained using the Levenberg–Marquardt algorithm, is integrated with a modified Garson sensitivity analysis to quantify the effect of important parameters on the heat transfer. The ANN model exhibits excellent prediction accuracy with an overall correlation coefficient \(R=0.99977\) R = 0.99977 . Results show that the thermal Biot number yields the highest positive impact, increasing the heat transfer rate by 54.61% per unit increment, while the cross-viscous parameter has the least effect. The framework presented offers not only accurate modeling but also interpretable parameter sensitivity information for high-end energy, biomedical, and microfluidic systems.