.png){kind=icon}
.png){kind=icon}
Return
Novel artificial neural network approach for hybrid nanofluid flow over nonlinear permeable stretching sheets with Thomson and Troian boundary conditions
.png){kind=icon}
PRE
AI
S
Z
E
A
S
DOI：10.1016/j.ijheatfluidflow.2024.109721.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
The study investigates the flow of a hybrid nanofluid over a non-linear, permeable stretched sheet under Thomson and Troian boundary conditions, while also considering the Darcy-Forchheimer relationship. We employ the Cattaneo-Christov heat flux model and novel artificial neural networks for the first time. This paper describes a new way to use artificial neural networks to add carbon nanotubes to hybrid nanofluids with Thomson and Troian boundary conditions. This creates induced MHD. The MSE ranges from 10-08 to 10-09. The AE range for all the cases lies around 10-03 to 10- 07 . The value of mu is around 10-08, while gradient ranges from 10-07to 10-08. This shows the high accuracy and precision of the proposed scheme. This research highlights the variation of different parameters with velocity, temperature and concentration. As the solid volume fraction rises, fluid velocity diminishes and temperature rises. Nanofluids exhibit enhancement with elevated inertial coefficient and Eckert number values. Increased inertial coefficient and Eckert number values correspond to rising temperatures. Concentration diminishes with rising solid volume percentage; yet, elevated activation energy results in enhanced concentration dispersion. It proves superior thermal conductivity and heat transmission capabilities, with future studies investigating the additional factors. Potential areas for further investigation include the study of other nanoparticles and different hybrid nanofluids and the investigation of real engineering challenges associated to heat and mass transfer in porous media. A graphic comparison between simple and hybrid nanofluids is presented. It is shown that the solid volume fraction improves the temperature distribution while decreasing the velocity profile. Furthermore, hybrid nanofluids perform better in heat transfer and have higher thermal conductivity than simple nanofluids.
Keywords:
Artificial Neural Network
Cattaneo-Christov heat flux model
Hybrid nanofluid
Thomson and Troian boundary conditions
Journal
I
IF:
5.1
Papers:
3.3K
Citations:
5.7K
Organization
Cited Papers