View in EDS

Artificial neural network simulation with numerical computation for targeted modulation of blood cells in hemodynamically stenosed anisotropic artery.

Saved in:
Bibliographic Details
Title: Artificial neural network simulation with numerical computation for targeted modulation of blood cells in hemodynamically stenosed anisotropic artery.
Authors: Batool, Maria1 (AUTHOR) mariamwu21@outlook.com, Rubbab, Qammar1 (AUTHOR), Akbar, Noreen Sher1,2 (AUTHOR) nakbar@pmu.edu.sa, Farooq, Muhammad Asif3 (AUTHOR), Muhammad, Taseer4 (AUTHOR)
Source: International Communications in Heat & Mass Transfer. Apr2026, Vol. 173, pN.PAG-N.PAG. 1p.
Subjects: Artificial neural networks, Magnetohydrodynamics, Computer simulation, Biomedical engineering, Mass transfer, Nanofluids, Heat transfer, Non-Newtonian fluids
Abstract: This study investigates steady magnetohydrodynamic (MHD) flow and transport characteristics of a tetra-hybrid nanofluid through a stenosed artery modeled as a Cross non-Newtonian fluid. The problem is motivated by biomedical applications such as magnetic drug targeting, hyperthermia therapy, and controlled blood flow regulation. An extended Tiwari–Das nanofluid model incorporating titanium dioxide, gold, silver, and aluminium oxide nanoparticles is employed to enhance heat and mass transfer. The governing momentum, energy, and concentration equations account for nonlinear thermal radiation, Joule heating, viscous dissipation, non-uniform heat generation/absorption, chemical reaction, and Soret effects. Using similarity transformations, the resulting dimensionless system is solved numerically via MATLAB's bvp4c solver. To improve computational efficiency, Artificial Neural Networks (ANNs) and Physics-Informed Neural Networks (PINNs) are developed as surrogate models. Results indicate that increasing the Weissenberg number reduces wall shear stress, while magnetic effects suppress velocity by approximately 28%. Temperature rises by about 22% due to combined thermal effects, whereas concentration increases near the wall with higher Soret number and decreases with stronger chemical reactions. Enhanced nanoparticle volume fraction significantly improves Nusselt and Sherwood numbers. Excellent agreement between numerical and machine-learning results is observed, with ANN showing superior accuracy and faster convergence. The study demonstrates that integrating MHD control with AI-driven modeling offers an efficient framework for optimizing thermal and mass transport in non-Newtonian biomedical flows. [ABSTRACT FROM AUTHOR]
Copyright of International Communications in Heat & Mass Transfer is the property of Pergamon Press - An Imprint of Elsevier Science 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.)
Database: Engineering Source
Description
Abstract:This study investigates steady magnetohydrodynamic (MHD) flow and transport characteristics of a tetra-hybrid nanofluid through a stenosed artery modeled as a Cross non-Newtonian fluid. The problem is motivated by biomedical applications such as magnetic drug targeting, hyperthermia therapy, and controlled blood flow regulation. An extended Tiwari–Das nanofluid model incorporating titanium dioxide, gold, silver, and aluminium oxide nanoparticles is employed to enhance heat and mass transfer. The governing momentum, energy, and concentration equations account for nonlinear thermal radiation, Joule heating, viscous dissipation, non-uniform heat generation/absorption, chemical reaction, and Soret effects. Using similarity transformations, the resulting dimensionless system is solved numerically via MATLAB's bvp4c solver. To improve computational efficiency, Artificial Neural Networks (ANNs) and Physics-Informed Neural Networks (PINNs) are developed as surrogate models. Results indicate that increasing the Weissenberg number reduces wall shear stress, while magnetic effects suppress velocity by approximately 28%. Temperature rises by about 22% due to combined thermal effects, whereas concentration increases near the wall with higher Soret number and decreases with stronger chemical reactions. Enhanced nanoparticle volume fraction significantly improves Nusselt and Sherwood numbers. Excellent agreement between numerical and machine-learning results is observed, with ANN showing superior accuracy and faster convergence. The study demonstrates that integrating MHD control with AI-driven modeling offers an efficient framework for optimizing thermal and mass transport in non-Newtonian biomedical flows. [ABSTRACT FROM AUTHOR]
ISSN:07351933
DOI:10.1016/j.icheatmasstransfer.2026.110721