Scholarlink

<p>An artificial neural network (ANN) was developed to predict the effect of nanoparticle aggregation on the transfer of heat that occurs due to the presence of&#xa0;nonlinear thermal radiation that interacts with Marangoni convection of TiO<sub>2</sub>-Ethylene Glycol (EG) nanofluid. Variable surface temperature and nonlinear thermal radiation are utilized to investigate the heat transfer phenomenon. After applying similarity transformations, the resulting governing partial differential equations become nonlinear ordinary differential equations that may be numerically solved with MATLAB software, followed by bvp4c and then an artificial neural network. Two different ANN models have been developed to predict the Nusselt number of linear and nonlinear thermal radiation. The Levenberg–Marquardt method with back propagation is used to forecast desired output. There is good agreement between the ANN values and the reported numerical values. Plotted graphs and tables show how the effective factors affect temperature, velocity, and Nusselt number profiles. From the numerical analysis, it was concluded that nanoparticle aggregation effect generates a higher temperature profile and reduces velocity profile compared to models without nanoparticle aggregation. Further, the Nusselt number is rising as a direct result of the increasing number of radiological effects, both linear and nonlinear. It is noted that according to the error histograms, the ANN model’s training phase has very little error. Furthermore, mean square error values calculated for local Nusselt number for linear and nonlinear parameters were obtained as&#xa0;2.67827 × 10<sup>–9</sup> and 5.17183 × 10<sup>–9</sup>, respectively. Both artificial neural network models can predict with high accuracy, according to the findings of the calculated performance parameters.</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

Optimization of heat transport in nanofluid with nanoparticle aggregation and Marangoni convection effects: artificial neural network approach

  • 期刊论文

  • 发表日期：

    2025年1月8日

查看全文
  • J. Pavithra,
  • N. V. Raju,
  • S. N. Sridhara,
  • T. Prasanna Kumar

摘要

An artificial neural network (ANN) was developed to predict the effect of nanoparticle aggregation on the transfer of heat that occurs due to the presence of nonlinear thermal radiation that interacts with Marangoni convection of TiO2-Ethylene Glycol (EG) nanofluid. Variable surface temperature and nonlinear thermal radiation are utilized to investigate the heat transfer phenomenon. After applying similarity transformations, the resulting governing partial differential equations become nonlinear ordinary differential equations that may be numerically solved with MATLAB software, followed by bvp4c and then an artificial neural network. Two different ANN models have been developed to predict the Nusselt number of linear and nonlinear thermal radiation. The Levenberg–Marquardt method with back propagation is used to forecast desired output. There is good agreement between the ANN values and the reported numerical values. Plotted graphs and tables show how the effective factors affect temperature, velocity, and Nusselt number profiles. From the numerical analysis, it was concluded that nanoparticle aggregation effect generates a higher temperature profile and reduces velocity profile compared to models without nanoparticle aggregation. Further, the Nusselt number is rising as a direct result of the increasing number of radiological effects, both linear and nonlinear. It is noted that according to the error histograms, the ANN model’s training phase has very little error. Furthermore, mean square error values calculated for local Nusselt number for linear and nonlinear parameters were obtained as 2.67827 × 10–9 and 5.17183 × 10–9, respectively. Both artificial neural network models can predict with high accuracy, according to the findings of the calculated performance parameters.