https://doi.org/10.1140/epjp/s13360-024-05525-0
Regular Article
Exploring hybrid Sisko nanofluid on a stretching sheet: an improved cuckoo search-based machine learning approach
1
School of Mechnical Engineering, Jiangsu University, 212013, Zhenjiang, Jiangsu, People’s Republic of China
2
Department of Mathematics, College of Science, Qassim University, 51452, Buraydah, Saudi Arabia
3
School of Mathematical Sciences, Jiangsu University, 212013, Zhenjiang, Jiangsu, People’s Republic of China
4
Department of Computer Science and Mathematics, Lebanese American university, Beirut, Lebanon
b
wangyun@ujs.edu.cn
c
s.boularas@qu.edu.sa
Received:
7
February
2024
Accepted:
29
July
2024
Published online:
26
August
2024
Due to its efficacy and adaptability, neural networks are widely employed for real-world and engineering problems. In this article, the dynamics of the flow, heat, and mass transfer in a hybrid Sisko nanofluid are investigated using an unsupervised artificial neural networks (ANN) tuned with hybrid cuckoo search algorithm. The given set of differential equations with the boundary conditions are transformed to mean squared error as a loss function and then minimized using the hybrid cuckoo search technique to achieve more accuracy. To show the accuracy of our designed methodology, we have compared the results with the supervised learning. We observed that, the solutions obtained from HCS-ANN are more accurate as compared to supervised ANN. The solutions, which are mesh-free and convergent, are put to use in an investigation of heat and mass transfer. From the obtained results when parameter of the materials is increased, the fluid velocity also increases. When compared to nanofluids, the wall heat transfer rate in hybrid nanofluid has the greatest value. Similarly, hybrid nanofluid has the greater wall mass flux compared to nanofluid. The temperature and concentration decrease with the increasing values of the Prandtl and Schmidt numbers.
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 Società Italiana di Fisica and Springer-Verlag GmbH Germany, part of Springer Nature 2024. 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.
