Heat transfer enhancement of magnetized GO–Al₂O₃/ethylene glycol hybrid nanofluid flow over a stretching cylinder in a porous medium using ReLU-based artificial neural network
Year: 2026
Type: article
Abstract: The present study aims to investigate the flow and heat transfer characteristics of magnetohydrodynamic (MHD) GO-Al₂O₃/ethylene glycol hybrid nanofluid (HNF) flow over a stretching cylinder embedded in a porous medium with viscous dissipation and thermal radiation. The governing nonlinear partial differential equations are transformed into a system of ordinary differential equations using suitable similarity transformations and solved by the Homotopy Analysis Method (HAM). To analyze and predict the flow and thermal characteristics of the model, a semi-analytical and artificial neural network (ANN) based framework is employed in this study. The effects of the obtained physical parameters, including the magnetic parameter, curvature parameter, porous-medium parameter, thermal radiation parameter, and Eckert number, on the flow and heat transfer characteristics are investigated. The obtained results show that the magnetic parameter reduces the velocity profile, whereas the curvature parameter enhances the skin friction coefficient. The HNF shows up to 6.8% higher local Nusselt number than the corresponding GO/ethylene glycol nanofluid and 28.3% enhancement compared with the ethylene glycol base fluid. Furthermore, to predict the skin friction coefficient and local Nusselt number, a feed-forward ANN is developed using the governing physical parameters as input variables. The ANN performance is assessed using training and validation loss, regression analysis, residual distributions, and prediction error metrics against the HAM reference solutions.
Source: Discover Nano
Authors: Salma Aljawi(Conceptualization, Formal analysis, Methodology, Writing – review & editing), Amal F. Alharbi(Investigation, Resources, Validation, Writing – review & editing), Fida Mohammad(Conceptualization, Project administration, Supervision, Writing – review & editing), Muhammad Usman(Data curation, Formal analysis, Methodology, Software, Visualization, Writing – original draft)
Language: English
Subfield: Fluid Flow and Transfer Processes
Field: Chemical Engineering
Domain: Physical Sciences
Open Access status: gold
Estimated APC paid: $2,090
Award: G6177408267
OpenAlex ID: W7234821433
