https://doi.org/10.1140/epjp/s13360-025-06474-y
Regular Article
Thermal property prediction in blood-based MHD Casson tri-hybrid nanofluids with 
and carbon nanotubes using ANN and Tiwari–Das model
Centre for High Energy Physics, University of the Punjab, 54590, Lahore, Pakistan
Received:
26
February
2025
Accepted:
25
May
2025
Published online:
11
June
2025
In a basic fluid-dynamic arrangement, the revolving disk is prized for its simplicity and significance in theoretical and real-world settings. Researchers, engineers, mathematicians, and medical experts are interested in the complicated flow problem around a rotating disk. Various natural phenomena, including oceanic currents, cyclones, galaxy formations, and the vortices formed by swirling liquids in a cup, exhibit rotating movements. In addition to being visible, these fluxes constitute an important field of study with multidisciplinary applications. To analyze the magnetohydrodynamics (MHD) flow of a Casson tri-hybrid nanofluid (THNF) over a rotating disk, this study explores the use of artificial neural networks (ANNs), taking into account the effects of porosity, Darcy–Forchheimer, and thermal radiation. In this work, blood is used as the base fluid, while , SWCNT, and MWCNT are used as nanoparticles. Furthermore, the governing equations with slip boundary conditions are formulated using the Tiwari and Das model. These nonlinear governing equations are converted to ordinary differential equations (ODEs) using self-similarity transforms. For increased accuracy and dependability, the Bvp4c method is used in conjunction with a shooting methodology and ANN in MATLAB. The study uses ANN-based analysis in conjunction with numerical simulations to evaluate the behavior of velocity profiles, temperature profiles, Nusselt number, and skin friction coefficient under various parameter settings. The axial and radial velocity profiles of tri-, hybrid, and mono-nanoparticles increase as the Casson fluid parameter increases, while both velocity profiles decrease with increasing Darcy–Forchheimer parameter. The thermal transfer rate in the ternary hybrid nanofluid case is higher than that in the hybrid and mono-nanofluid scenarios. The thermal transfer rate of cylindrical nanoparticles is more than that of brick-shaped and spherically shaped nanoparticles. The developed ANN model demonstrated exceptional accuracy and reliability in every study phase. The results are more accurately validated by regression analysis, mean-squared error (MSE), error histograms, state transition analysis, and other tabular and graphical representations.
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 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.
