Sign in Subscribe
Artificial neural networks

Nanotechnology Research Yields Breakthroughs in Nanofluids and Heat Transfer

Strategic Insights

— 1 min read

Researchers from Government College University and Imam Mohammad Ibn Saud Islamic University have made significant advancements in nanotechnology, particularly in the field of nanofluids and heat transfer. According to a new report, the research has led to the development of a novel approach to enhance conventional thermal and fluid systems. The study focuses on the inclusion of nanoparticles in base fluids, which significantly improves thermal conductivity and enables advanced phase-change technologies.

Key Takeaways:

  • The researchers used the Powell-Eyring nanofluid model to examine heat transmission properties on a stretched Riga plate, considering the effects of magnetic fields, porosity, Darcy-Forchheimer flow, thermal radiation, and activation energy.
  • The study revealed that the velocity of the nanofluid decreases with an increase in the Hartmann number, porosity, and Darcy-Forchheimer parameter values, while its energy curves increase with boosting the values of thermal radiation and the Biot number.
  • A stronger Hartmann number M decelerates the flow, while increasing the Riga forcing parameter Q can locally enhance the near-wall velocity due to wall-parallel Lorentz forcing.
  • The researchers employed an artificial neural network (ANN) architecture to predict velocity, temperature, and concentration profiles, achieving exceptional accuracy with regression coefficients R ≈ 1.0 and the best validation mean squared errors of 8.52x10^-10, 7.91x10^-9, and 1.59x10^-8 for the Powell-Eyring, heat radiation, and thermophoresis models, respectively.
  • The study demonstrated the ability of the ANN to serve as a credible surrogate for quick parametric assessment and refinement in magnetohydrodynamic (MHD) nanofluid heat transfer systems.

Statistics:

  • The Powell-Eyring nanofluid show a significant improvement in thermal conductivity (up to 50%) compared to base fluids.
  • The artificial neural network (ANN) achieved a regression coefficient R ≈ 1.0, indicating a strong correlation between the predicted and actual values.
  • The best validation mean squared errors of 8.52x10^-10, 7.91x10^-9, and 1.59x10^-8 were obtained for the Powell-Eyring, heat radiation, and thermophoresis models, respectively.

Sources:

  • "Artificial Neural Network Modeling of Darcy-forchheimer Nanofluid Flow Over a Porous Riga Plate: Insights Into Brownian Motion, Thermal Radiation, and Activation Energy Effects On Heat Transfer." Symmetry 2025; 17(9): 1582.
  • NewsRx. "New Findings on Nanofluids from Government College University Summarized (Artificial Neural Network Modeling of Darcy-forchheimer Nanofluid Flow Over a Porous Riga Plate: Insights Into Brownian Motion, Thermal Radiation, and Activation Energy ...)." Journal of Engineering. October 20, 2025; p 1962.

Read more