Measurement of intelligent computing via Levenberg Marquardt algorithm (LMA) for accurate prediction of fluid forces in a transient non-Newtonian thermal flow
Predicting precise results for the quantities of interest in time-dependent Computational Fluid Dynamics (CFD) simulations requires a significant investment of computational resources and time. To get around these issues, CFD simulations have been joined with Artificial Neural Networks (ANN). An opt...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2024-12-01
|
| Series: | Results in Physics |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2211379724007174 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850123582459346944 |
|---|---|
| author | Atif Asghar Rashid Mahmood Afraz Hussain Majeed Ahmed S. Hendy Mohamed R. Ali |
| author_facet | Atif Asghar Rashid Mahmood Afraz Hussain Majeed Ahmed S. Hendy Mohamed R. Ali |
| author_sort | Atif Asghar |
| collection | DOAJ |
| description | Predicting precise results for the quantities of interest in time-dependent Computational Fluid Dynamics (CFD) simulations requires a significant investment of computational resources and time. To get around these issues, CFD simulations have been joined with Artificial Neural Networks (ANN). An optimally configured artificial neural network (ANN) is given the training and validation data sets produced by computational fluid dynamics (CFD). The flow around a cylinder, which is a well-known benchmark problem for incompressible flows, has been taken into consideration by the hybrid-CFD system. The mathematical model is based on the non-stationary Navier-Stokes and energy equations with viscosity. The basic architecture of the ANN model consists of 10 hidden layers, three output levels, and five input layers. Fast second-order LMA, a top-tier approach, was used to train the network. Both the Mean Square Error (MSE) and the coefficient of determination (R) provide statistical evidence that the ANN projected values for the drag and lift coefficients and average Nusselt number obtained from the finite element analysis are accurate. This analysis suggests that ANNs have the potential to significantly cut down on the amount of time and energy needed to run time-dependent simulations. |
| format | Article |
| id | doaj-art-e96cb37ccc3845a4b5cc79d8a7b4a001 |
| institution | OA Journals |
| issn | 2211-3797 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Results in Physics |
| spelling | doaj-art-e96cb37ccc3845a4b5cc79d8a7b4a0012025-08-20T02:34:34ZengElsevierResults in Physics2211-37972024-12-016710803210.1016/j.rinp.2024.108032Measurement of intelligent computing via Levenberg Marquardt algorithm (LMA) for accurate prediction of fluid forces in a transient non-Newtonian thermal flowAtif Asghar0Rashid Mahmood1Afraz Hussain Majeed2Ahmed S. Hendy3Mohamed R. Ali4Department of Mathematics, Air University, PAF Complex E-9, Islamabad 44000, PakistanDepartment of Mathematics, Air University, PAF Complex E-9, Islamabad 44000, PakistanSchool of Energy and Power Engineering, Jiangsu University, Zhenjiang 212013, China; Corresponding authors.Department of Computational Mathematics and Computer Science, Institute of Natural Sciences and Mathematics, Ural Federal University, 19 Mira St., Yekaterinburg 620002, Russia; Department of Mechanics and Mathematics, Western Caspian University, Baku 1001, AzerbaijanFaculty of Engineering and Technology, Future University in Egypt, New Cairo 11835, Egypt; Corresponding authors.Predicting precise results for the quantities of interest in time-dependent Computational Fluid Dynamics (CFD) simulations requires a significant investment of computational resources and time. To get around these issues, CFD simulations have been joined with Artificial Neural Networks (ANN). An optimally configured artificial neural network (ANN) is given the training and validation data sets produced by computational fluid dynamics (CFD). The flow around a cylinder, which is a well-known benchmark problem for incompressible flows, has been taken into consideration by the hybrid-CFD system. The mathematical model is based on the non-stationary Navier-Stokes and energy equations with viscosity. The basic architecture of the ANN model consists of 10 hidden layers, three output levels, and five input layers. Fast second-order LMA, a top-tier approach, was used to train the network. Both the Mean Square Error (MSE) and the coefficient of determination (R) provide statistical evidence that the ANN projected values for the drag and lift coefficients and average Nusselt number obtained from the finite element analysis are accurate. This analysis suggests that ANNs have the potential to significantly cut down on the amount of time and energy needed to run time-dependent simulations.http://www.sciencedirect.com/science/article/pii/S2211379724007174Artificial intelligenceNeural networkThermal flowFEMFluid forces |
| spellingShingle | Atif Asghar Rashid Mahmood Afraz Hussain Majeed Ahmed S. Hendy Mohamed R. Ali Measurement of intelligent computing via Levenberg Marquardt algorithm (LMA) for accurate prediction of fluid forces in a transient non-Newtonian thermal flow Results in Physics Artificial intelligence Neural network Thermal flow FEM Fluid forces |
| title | Measurement of intelligent computing via Levenberg Marquardt algorithm (LMA) for accurate prediction of fluid forces in a transient non-Newtonian thermal flow |
| title_full | Measurement of intelligent computing via Levenberg Marquardt algorithm (LMA) for accurate prediction of fluid forces in a transient non-Newtonian thermal flow |
| title_fullStr | Measurement of intelligent computing via Levenberg Marquardt algorithm (LMA) for accurate prediction of fluid forces in a transient non-Newtonian thermal flow |
| title_full_unstemmed | Measurement of intelligent computing via Levenberg Marquardt algorithm (LMA) for accurate prediction of fluid forces in a transient non-Newtonian thermal flow |
| title_short | Measurement of intelligent computing via Levenberg Marquardt algorithm (LMA) for accurate prediction of fluid forces in a transient non-Newtonian thermal flow |
| title_sort | measurement of intelligent computing via levenberg marquardt algorithm lma for accurate prediction of fluid forces in a transient non newtonian thermal flow |
| topic | Artificial intelligence Neural network Thermal flow FEM Fluid forces |
| url | http://www.sciencedirect.com/science/article/pii/S2211379724007174 |
| work_keys_str_mv | AT atifasghar measurementofintelligentcomputingvialevenbergmarquardtalgorithmlmaforaccuratepredictionoffluidforcesinatransientnonnewtonianthermalflow AT rashidmahmood measurementofintelligentcomputingvialevenbergmarquardtalgorithmlmaforaccuratepredictionoffluidforcesinatransientnonnewtonianthermalflow AT afrazhussainmajeed measurementofintelligentcomputingvialevenbergmarquardtalgorithmlmaforaccuratepredictionoffluidforcesinatransientnonnewtonianthermalflow AT ahmedshendy measurementofintelligentcomputingvialevenbergmarquardtalgorithmlmaforaccuratepredictionoffluidforcesinatransientnonnewtonianthermalflow AT mohamedrali measurementofintelligentcomputingvialevenbergmarquardtalgorithmlmaforaccuratepredictionoffluidforcesinatransientnonnewtonianthermalflow |