Machine learning analysis of blood hybrid nanofluid flow inside a stenosis artery with heat generation and thermophoresis

Abstract

The machine learning analysis of blood-based hybrid nanofluid flow inside a stenosed artery with heat generation and thermophoretic particle deposition has major uses in biomedical engineering and healthcare. It can be used to advance hyperthermia treatments, optimize targeted drug delivery, and increase the design of cardiovascular implants and stents. Additionally, understanding nanoparticle deposition and thermal behavior aids in predicting blood flow characteristics, preventing arterial blockage, and designing efficient thermal management strategies for medical treatments and diagnostics. This work examines the effects of heat source on hybridnanofluid using the artificial neural networks. The numerical model of a system of PDEs may be converted into a set of ODEs using similarity variables. The ordinary differential equations are then solved using the built-in bvp4c solver in the MATLAB mathematical computing programming. Increasing the nanoparticle volume fraction from 0.01 to 0.04 improves heat transfer rate by 9.41% for nanofluid and 14.00% for hybrid nanofluid.