Polynomial degree impact on prediction accuracy in Casson-Williamson fluid with Cattaneo-Christov
A discussion on the 3D incompressible steady laminar boundary layer flow over a porous sheet due to the CattaneoChristov heat flux model and magnetohydrodynamic (MHD) effects are present, and artificial intelligence-based tools are used to predict the boundary layer flow, with a comparative analysis...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-06-01
|
| Series: | Results in Engineering |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2590123025011430 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849324154851950592 |
|---|---|
| author | Ramzan Ali Nouman Khalid Talal Taha Ainura Mitalipova Abdikerim Kurbanaliev |
| author_facet | Ramzan Ali Nouman Khalid Talal Taha Ainura Mitalipova Abdikerim Kurbanaliev |
| author_sort | Ramzan Ali |
| collection | DOAJ |
| description | A discussion on the 3D incompressible steady laminar boundary layer flow over a porous sheet due to the CattaneoChristov heat flux model and magnetohydrodynamic (MHD) effects are present, and artificial intelligence-based tools are used to predict the boundary layer flow, with a comparative analysis of degree 1 (linear model) polynomial approaches and degree 2 (linear model). The results have established that degree 2 polynomials are found to be more accurate than linear regressions in making precise predictions on flow behavior for its complexity. Important parameters under analysis include the fluid properties of Casson and Williamson, thermophoresis, heat flux overflow, and thermal profiles. With an increase in the Casson and Williamson fluid parameters, the velocity profile becomes smaller, showing improved resistance in flow. As thermophoresis parameter values are increased, the concentration profile increases while the boundary layer thickness decreases with improved mass transfer. The comparison among the polynomial models can be analyzed by referring to Table 2. The prediction performance metrics, such as R-squared and modified R-squared values, are displayed in Table 3. The nonlinear polynomial approach's success is demonstrated by the maximum value of 0.9912 for the Casson fluid parameter. The MSE values vary between 10−8 to 10−10 indicating strong reliability and accuracy of the ANN model. The results have significant engineering applications in designing thermal-fluid systems, such as polymer extrusion processes, cooling systems for electronic devices, and enhanced oil recovery techniques, where fluid flow and heat transfer control are critical. |
| format | Article |
| id | doaj-art-7e83068cf03c4682b11d68a8d0f72800 |
| institution | Kabale University |
| issn | 2590-1230 |
| language | English |
| publishDate | 2025-06-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Results in Engineering |
| spelling | doaj-art-7e83068cf03c4682b11d68a8d0f728002025-08-20T03:48:47ZengElsevierResults in Engineering2590-12302025-06-012610506810.1016/j.rineng.2025.105068Polynomial degree impact on prediction accuracy in Casson-Williamson fluid with Cattaneo-ChristovRamzan Ali0Nouman Khalid1Talal Taha2Ainura Mitalipova3Abdikerim Kurbanaliev4Department of Mathematics, University of Doha for Science and Technology (UDST), Qatar; Corresponding author.Department of Mathematics & Statistics, International Islamic University Islamabad Pakistan, PakistanDepartment of Mathematics & Statistics, International Islamic University Islamabad Pakistan, PakistanDepartment of Natural Science and Mathematics, Osh State University, Kyrgyz RepublicDepartment of Natural Science and Mathematics, Osh State University, Kyrgyz RepublicA discussion on the 3D incompressible steady laminar boundary layer flow over a porous sheet due to the CattaneoChristov heat flux model and magnetohydrodynamic (MHD) effects are present, and artificial intelligence-based tools are used to predict the boundary layer flow, with a comparative analysis of degree 1 (linear model) polynomial approaches and degree 2 (linear model). The results have established that degree 2 polynomials are found to be more accurate than linear regressions in making precise predictions on flow behavior for its complexity. Important parameters under analysis include the fluid properties of Casson and Williamson, thermophoresis, heat flux overflow, and thermal profiles. With an increase in the Casson and Williamson fluid parameters, the velocity profile becomes smaller, showing improved resistance in flow. As thermophoresis parameter values are increased, the concentration profile increases while the boundary layer thickness decreases with improved mass transfer. The comparison among the polynomial models can be analyzed by referring to Table 2. The prediction performance metrics, such as R-squared and modified R-squared values, are displayed in Table 3. The nonlinear polynomial approach's success is demonstrated by the maximum value of 0.9912 for the Casson fluid parameter. The MSE values vary between 10−8 to 10−10 indicating strong reliability and accuracy of the ANN model. The results have significant engineering applications in designing thermal-fluid systems, such as polymer extrusion processes, cooling systems for electronic devices, and enhanced oil recovery techniques, where fluid flow and heat transfer control are critical.http://www.sciencedirect.com/science/article/pii/S2590123025011430Casson-Williamson fluidMagnetohydrodynamicCattaneo-ChristovArtificial intelligence |
| spellingShingle | Ramzan Ali Nouman Khalid Talal Taha Ainura Mitalipova Abdikerim Kurbanaliev Polynomial degree impact on prediction accuracy in Casson-Williamson fluid with Cattaneo-Christov Results in Engineering Casson-Williamson fluid Magnetohydrodynamic Cattaneo-Christov Artificial intelligence |
| title | Polynomial degree impact on prediction accuracy in Casson-Williamson fluid with Cattaneo-Christov |
| title_full | Polynomial degree impact on prediction accuracy in Casson-Williamson fluid with Cattaneo-Christov |
| title_fullStr | Polynomial degree impact on prediction accuracy in Casson-Williamson fluid with Cattaneo-Christov |
| title_full_unstemmed | Polynomial degree impact on prediction accuracy in Casson-Williamson fluid with Cattaneo-Christov |
| title_short | Polynomial degree impact on prediction accuracy in Casson-Williamson fluid with Cattaneo-Christov |
| title_sort | polynomial degree impact on prediction accuracy in casson williamson fluid with cattaneo christov |
| topic | Casson-Williamson fluid Magnetohydrodynamic Cattaneo-Christov Artificial intelligence |
| url | http://www.sciencedirect.com/science/article/pii/S2590123025011430 |
| work_keys_str_mv | AT ramzanali polynomialdegreeimpactonpredictionaccuracyincassonwilliamsonfluidwithcattaneochristov AT noumankhalid polynomialdegreeimpactonpredictionaccuracyincassonwilliamsonfluidwithcattaneochristov AT talaltaha polynomialdegreeimpactonpredictionaccuracyincassonwilliamsonfluidwithcattaneochristov AT ainuramitalipova polynomialdegreeimpactonpredictionaccuracyincassonwilliamsonfluidwithcattaneochristov AT abdikerimkurbanaliev polynomialdegreeimpactonpredictionaccuracyincassonwilliamsonfluidwithcattaneochristov |