ARTIFICIAL NEURAL NETWORK–BASED MODELING OF MHD BLOOD–CU–AL₂O₃ HYBRID NANOFLUID FLOW OVER A STRETCHING SHEET FOR BIOMEDICAL APPLICATIONS

Abstract

Machine learning techniques employ new techniques to solve complicated issues and optimize methods for understanding through large data sets. In fluid dynamics, there is currently a continuous and rising interest for the use of nano particles in a variety of medical fields. Artificial neural networks (ANNs) help medical devices work more efficiently by minimizing heat transfer through circulation control of hybrid nanofluids. ANN was also used to look into the inspiration for magnetohydrodynamic hybrid nanofluid flow through a stretching sheet in the presence of thermal radiation and porous medium. In this model used blood mixed with Cu-Al2O3 nanoparticles. The PDE is transformed into an ODE by using the appropriate self-similarity variables. The dimensionless equations are solved using the MATLAB software in the Bvp4c scheme. Furthermore, in the results section, noticed that the velocity outlines decreased, and, on the other hand, there was an increasing tendency on the energy outlines to increase the magnetic field parameter. Graphs and tables explain how operational factors affect fluid flow efficiency. Hybrid nanofluids have a higher heat transfer rate compared to nanofluids. Consequently, the latest study's originality, its impact on technology and mathematical information, and its potential to inspire young scientists and also these kinds of models to play an important role in biomedical systems. In addition, magnetic field interactions with tiny fluids may be tuned utilizing ANNs to create desired magnetic implications, hence improving the efficiency of MHD compressors and biomedical industry.