Nonlinear Thermal Radiation in Magnetized Casson Fluid Flow: An Artificial Neural Network Analysis
Journal of Computational and Nonlinear Dynamics · 01.10.2026 · 21 (10)
DOI: 10.1115/1.4072121 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Computational and Nonlinear Dynamics, online erschienen am 02.07.2026. Verfasst von Chao Zhang und 5 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 35 Literaturangaben.
Abstract (Originalsprache)
This research explores an artificial intelligence (AI) driven examination of nonlinear thermal radiation effects in steady magnetized Casson fluid flow over a vertically permeable stretching sheet inside a non-Darcy porous medium. The considered physical scenario includes magnetic and electric fields, Joule heating, viscous dissipation, thermal radiation, mass diffusion, and chemical reaction effects. By means of suitable similarity transformations, the original partial differential equations are simplified to a system of nonlinear ordinary differential equations. As the system is strongly nonlinear, a supervised artificial neural network that is trained by the Levenberg–Marquardt algorithm (LBMA) is utilized to get the solution, as LBMA is known for its quick convergence and numerical stability in complicated boundary-layer flow situations. A reference dataset is obtained with the Adams method in mathematica from varying key physical parameters, such as magnetic field strength, Casson parameter, Prandtl number, Schmidt number, Eckert number, thermal radiation parameter, Soret number, electric field parameter, and chemical reaction parameter. To ensure good generalization performance, the dataset is split into training, validation, and testing subsets in the ratio 70:15:15. The LBMA-based neural framework proposed in the study offers a very accurate and computationally efficient method to approximate the nonlinear solution space. It achieves this without explicitly depending on iterative numerical solver operations. The LBMA-based neural framework provides very accurate and robust results, with low mean squared error values being in the range of 10−10 to 10−07. The findings reveal that the velocity of the fluid goes up when the magnetic field intensity is increased, and the temperature also increases with the rise of the values of the Eckert number, the magnetic parameter, and the Prandtl number but it decreases when thermal radiation is present. The concentration profile is negatively affected by chemical reaction, Soret, and Schmidt numbers.
Zitieren
APA
Zhang, C., Shah, Z., Sultan, H., Magdich, A., Zayani, H. M., & Khedher, N. B. (2026). Nonlinear Thermal Radiation in Magnetized Casson Fluid Flow: An Artificial Neural Network Analysis. Journal of Computational and Nonlinear Dynamics, 21(10). https://doi.org/10.1115/1.4072121
Vancouver
Zhang C, Shah Z, Sultan H, Magdich A, Zayani HM, Khedher NB. Nonlinear Thermal Radiation in Magnetized Casson Fluid Flow: An Artificial Neural Network Analysis. Journal of Computational and Nonlinear Dynamics. 2026;21(10). doi:10.1115/1.4072121
BibTeX
@article{Zhang2026,
author = {Zhang, Chao and Shah, Zahoor and Sultan, Hinza and Magdich, Amina and Zayani, Hafedh Mahmoud and Khedher, Nidhal Ben},
title = {Nonlinear Thermal Radiation in Magnetized Casson Fluid Flow: An Artificial Neural Network Analysis},
journal = {Journal of Computational and Nonlinear Dynamics},
year = {2026},
volume = {21},
number = {10},
doi = {10.1115/1.4072121}
}
EUVIMED