https://doi.org/10.1140/epjs/s11734-025-01800-y
Regular Article
Machine learning and numerical approach of heat transfer properties of two different kinds of hybrid nanofluids flow in a U-shaped cavity
1
School of Technology, The Apollo University, 517127, Chittoor, A.P., India
2
Department of Mathematics, SAS, Vellore Institute of Technology, Chennai Campus, 600127, Vellore, T.N., India
3
Department of Mathematics and Statistics, The University of the West Indies, St Augustine Circular Road, St. Augustine, Trinidad and Tobago
4
Department of Mathematics, Koneru Lakshmaiah Education Foundation, Bowrampet, 500043, Hyderabad, Telangana, India
5
Department of Mathematical Sciences, Ulsan National Institute of Science and Technology, Ulsan, South Korea
Received:
3
December
2024
Accepted:
8
July
2025
Published online:
23
July
2025
This work investigates the heat transfer characteristics of natural convection in a water-based hybrid nanofluid flow inside a U-shaped cavity, with the objective of enhancing thermal efficiency in solar dish collectors. The artificial compressibility finite-difference method (AC-FDM) is employed for numerical analysis, ensuring the precise calculation of flow and heat fields. Hybrid nanoparticles Cu–Fe₃O₄ and MoS₂–Fe₃O₄ are utilized to evaluate their impact on thermal efficiency, employing machine learning methodologies to determine optimal configurations and investigate parameter variations. Essential factors, including the Rayleigh number, Darcy number, thermal radiation parameter, heat source/sink parameter, and Hartmann number, are analyzed, indicating that elevated Rayleigh numbers enhance heat transfer by increasing the average Nusselt number, while the thermal radiation parameter further improves efficiency. Isotherms and streamlines depict flow and thermal patterns, exhibiting stratification and asymmetry as the Rayleigh number increases. The velocity and temperature patterns along the hollow centerline provide more information. The results underscore the promise of hybrid nanoparticles in enhancing technology such as solar collectors, heat exchangers, microvascular devices, and photothermal cancer treatment. The purpose of this research is to build a unique framework that integrates AC-FDM and machine learning in order to improve thermal control and system efficiency in engineering and biomedical applications.
Copyright comment Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
© The Author(s), under exclusive licence to EDP Sciences, Springer-Verlag GmbH Germany, part of Springer Nature 2025
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
