Λεπτομέρειες βιβλιογραφικής εγγραφής
| Τίτλος: |
Artificial neural network-based computational modeling of Jeffrey fluid in sloping channel with Navier-slip boundaries using Levenberg–Marquardt algorithm. |
| Συγγραφείς: |
Mahla, Ravi, Kolla, Kaladhar |
| Πηγή: |
Journal of Thermal Analysis & Calorimetry; Jul2026, Vol. 151 Issue 14, p11893-11907, 15p |
| Θεματικοί όροι: |
Artificial neural networks, Marquardt algorithm, Boundary value problems, Computer simulation, Quasilinearization, Magnetohydrodynamics, Viscoelastic materials, Non-Newtonian flow (Fluid dynamics) |
| Περίληψη: |
The present study investigates the influence of an inclined magnetic field and Hall current on the free convective flow of a Jeffrey fluid within a channel under Navier-slip conditions. The governing nonlinear equations are transformed into a dimensionless form and solved using a hybrid computational framework that combines the spectral quasi-linearization method (SQLM) with a Levenberg-Marquardt-based artificial neural network (BANN-LM). The novelty of the work lies in integrating a high-accuracy numerical solver with a data-driven ANN model to efficiently predict velocity, cross-flow, and temperature profiles under coupled physical effects. The reliability of the developed BANN-LM framework is verified through a validation process that incorporates performance indices including mean squared error, regression analysis, and error histogram evaluation. Graphical illustrations present the key findings, highlighting the influence of thermophysical parameters. The velocity and cross-flow velocity increase with larger values of the inclination angle, Jeffrey parameter, and magnetic strength. Conversely, the temperature rises with a higher Hall current and Jeffrey parameter but decreases as the inclination angle and magnetic parameter intensify. The proposed framework provides a robust and computationally efficient approach for modeling complex Non-Newtonian magnetohydrodynamic flows. [ABSTRACT FROM AUTHOR] |
|
Copyright of Journal of Thermal Analysis & Calorimetry is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) |
| Βάση Δεδομένων: |
Complementary Index |