Scholarlink

<p>This work uses a supervised machine learning approach to examine the boundary layer flow of a non-Newtonian fluid affected by homogeneous and heterogeneous reactions over a convectively heated surface. Similarity variables transform the governing nonlinear PDEs into ODEs, which are solved using the bvp4c technique followed by the application of a supervised machine learning model. The model successfully captures different velocity, energy, and concentration profiles for every situation, precisely predicting flow and thermal properties. Performance metrics that demonstrate the model's accuracy and predictive power in a variety of scenarios include Mean Squared Error (MSE) and R-squared values. Scenarios 3 and 6 exhibit the maximum accuracy and lowest mean square error (MSE) in Table <InternalRef RefID="Tab1">1</InternalRef>. On the other hand, the material parameter <InlineEquation ID="IEq1"> <InlineMediaObject> <ImageObject Color="BlackWhite" FileRef="41939_2025_734_Article_IEq1.gif" Format="GIF" Height="16" Rendition="HTML" Resolution="72" Type="Linedraw" Width="17" /> </InlineMediaObject> <EquationSource Format="TEX">\({\lambda }_{1}\)</EquationSource> <EquationSource Format="MATHML"><math> <msub> <mi>λ</mi> <mn>1</mn> </msub> </math></EquationSource> </InlineEquation> enhances fluid velocity while decreasing the temperature field, and porosity parameter S enhances momentum boundary layer. Error histograms and three-dimensional contour plots are examples of visual assessments that highlight the model's consistency and capacity to identify data trends. Differences in predictions between machine learning and bvp4c with MATLAB indicate that machine learning (ML) can handle a large variety of complex data. Homogeneous and heterogeneous reactions have several uses in the technical and scientific sectors. A lot of reactors are made to take use of both homogeneous and heterogeneous reactions in order to increase efficiency and selectivity. Heterogeneous reactions are used to regulate air pollution, like in car catalytic converters to lower emissions.</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

Machine learning-based prediction of heat transfer enhancement in carreau fluids with impact of homogeneous and heterogeneous reactions

  • 期刊论文

  • 发表日期：

    2025年1月19日

查看全文
  • Nahid Fatima,
  • Refka Ghodhbani,
  • Nouman Khalid,
  • Muhammad Imran Khan,
  • Talal Taha,
  • Nouman Ijaz,
  • Najma Saleem

摘要

This work uses a supervised machine learning approach to examine the boundary layer flow of a non-Newtonian fluid affected by homogeneous and heterogeneous reactions over a convectively heated surface. Similarity variables transform the governing nonlinear PDEs into ODEs, which are solved using the bvp4c technique followed by the application of a supervised machine learning model. The model successfully captures different velocity, energy, and concentration profiles for every situation, precisely predicting flow and thermal properties. Performance metrics that demonstrate the model's accuracy and predictive power in a variety of scenarios include Mean Squared Error (MSE) and R-squared values. Scenarios 3 and 6 exhibit the maximum accuracy and lowest mean square error (MSE) in Table 1. On the other hand, the material parameter \({\lambda }_{1}\) λ 1 enhances fluid velocity while decreasing the temperature field, and porosity parameter S enhances momentum boundary layer. Error histograms and three-dimensional contour plots are examples of visual assessments that highlight the model's consistency and capacity to identify data trends. Differences in predictions between machine learning and bvp4c with MATLAB indicate that machine learning (ML) can handle a large variety of complex data. Homogeneous and heterogeneous reactions have several uses in the technical and scientific sectors. A lot of reactors are made to take use of both homogeneous and heterogeneous reactions in order to increase efficiency and selectivity. Heterogeneous reactions are used to regulate air pollution, like in car catalytic converters to lower emissions.