go-v.orgdoi

Machine learning approach of Casson hybrid nanofluid flow over a heated stretching surface

Gunisetty Ramasekhar, Shalan Alkarni, Nehad Ali Shah · AIMS Mathematics · 2024

  • DOI 10.3934/math.2024912
  • Publisher American Institute of Mathematical Sciences
  • Type article
  • Issued 2024

Not cached yet. This record was fetched live for this request and is stored after the lookup. Reopening the page should serve the cached copy.

AIMS Mathematics · American Institute of Mathematical Sciences · article · 2024

Abstract

The present investigation focused on the influence of magnetohydrodynamic Gold-Fe3O4 hybrid nanofluid flow over a stretching surface in the presence of a porous medium and linear thermal radiation. This article demonstrates a novel method for implementing an intelligent computational solution by using a multilayer perception (MLP) feed-forward back-propagation artificial neural network (ANN) controlled by the Levenberg-Marquard algorithm. We trained, tested, and validated the ANN model using the obtained data. In this model, we used blood as the base fluid along with Gold-Fe3O4 nanoparticles.

By using the suitable self-similarity variables, the partial differential equations (PDEs) are transformed into ordinary differential equations (ODEs). After that, the dimensionless equations were solved by using the MATLAB solver in the Fehlberg method, such as those involving velocity, energy, skin friction coefficient, heat transfer rates and other variables. The goals of the ANN model included data selection, network construction, network training, and performance assessment using the mean square error indicator. The influence of key factors on fluid transport properties is presented via tables and graphs.

The velocity profile decreased for higher values of the magnetic field parameter and we noticed an increasing tendency in the temperature profile. This type of theoretical investigation is a necessary aspect of the biomedical field and many engineering sectors.

Open the resolved locator · 10.3934/math.2024912

Metadata licence: OpenAlex metadata (CC0)

Registry
OpenAlex DOI index + API
Fetched
2026-11-19 21:10 UTC
Cache state
not cached yet (bulk-index+openalex)
Locator
http://www.aimspress.com/article/doi/10.3934/math.2024912
Metadata licence
OpenAlex metadata (CC0)
Scope
Metadata as returned by the resolver; abstracts are never generated here.