آمار
| تعداد نشریات | 45 |
| تعداد شمارهها | 1,434 |
| تعداد مقالات | 17,659 |
| تعداد مشاهده مقاله | 57,571,973 |
| تعداد دریافت فایل اصل مقاله | 19,291,013 |
Numerical and Artificial Neural Network Model for Williamson Fluid Flow over a Stretching Sheet under Inclined Magnetic Field and Radiation | ||
| Computational Methods for Differential Equations | ||
| مقالات آماده انتشار، پذیرفته شده، انتشار آنلاین از تاریخ 24 شهریور 1404 اصل مقاله (2.32 M) | ||
| نوع مقاله: Research Paper | ||
| شناسه دیجیتال (DOI): 10.22034/cmde.2025.62082.2710 | ||
| نویسندگان | ||
| P Priyadharshini* ؛ V. Karpagam | ||
| Department of Mathematics, PSG College of Arts and Science, Coimbatore-641014, Tamil Nadu, India. | ||
| چکیده | ||
| Potential developments of Williamson fluid flow across porous media included plasma mechanics, blood transport, bio-thermal engineering, medication delivery, and tissue temperature perception. The benefits of these results are evident in the biomedical fields of tissue engineering and tissue replacement, where porous scaffolds improve blood flow across biological tissues and address organ shortages. In the fluid flow model, velocity Uw(x) = ax is influenced by an inclined magnetic field and radiation effect at an angle of α over the stretching surface, with the temperature, concentration, and velocity slips present. Relevant partial differential equations were transformed into ordinary differential equations by the conversion of similarity. The MATLAB module implements the BVP4C solver computationally to determine these ODEs. The current discoveries constitute a remarkable extension of previous results. As the magnetic parameter rises, the Lorentz force acting on the fluid flow reduces the velocity distribution. The temperature profile minimized as the Prandtl number improved because of a reduction in the thickness of the thermal boundary layer. In addition, the proposed innovative work for a machine learning-based multiple linear regression improves the accuracy to 95%. In the end, employing an artificial neural network technique yields highly dependable validation and 99% correct forecasts for such scenarios by locating accurate data for amounts of interest. The exact quality of the prediction and verification of the present result is ultimately verified and confirmed by a graph and tabular data for comparison with the prior outcomes. | ||
| کلیدواژهها | ||
| Artificial Neural Network؛ Inclined Magnetic Field؛ Multiple Linear Regression؛ Radiation | ||
|
آمار تعداد مشاهده مقاله: 134 تعداد دریافت فایل اصل مقاله: 109 |
||