Bayesian regularization knack-based intelligent networks for thermo-physical analysis of 3D MHD nanofluidic flow model over an exponential stretching surface
Department of Electrical and Computer Engineering, COMSATS University Islamabad, Attock Campus, 43600, Attock, Pakistan
2 Department of Mathematics, COMSATS University Islamabad, Attock Campus, 43600, Attock, Pakistan
3 Future Technology Research Center, National Yunlin University of Science and Technology, 123 University Road, Section 3, 64002, Douliou, Yunlin, Taiwan, ROC
4 Department of Safety, Health, and Environmental Engineering, National Yunlin University of Science and Technology, 123 University Road, Section 3, 64002, Douliou, Yunlin, Taiwan, ROC
Accepted: 18 December 2022
Published online: 2 January 2023
Artificial intelligence (AI) knacks are exploited broadly by the research community in the field of engineering and technology to enhance efficacy of the outputs for rapid development of business and society. Therefore, it looks promising to explore or investigate in the novel AI-based integrated numerical computing to study the solution dynamic of computational fluid mechanics problem of utmost significance. Boundary layer methodology is invoked for the mathematical modeling of fluidic system to study the heat and mass transport improvement of nanofluid with base water 3D-MHD flow model with an exponentially stretched surface involving three types of nanoparticles (magnetite), (silver) and (graphene oxide). The representative 3D PDEs for nanofluidic system are converted into equivalent nonlinear ODE-based system via suitable similarity transformation. The results of the three nanofluidic models are calculated by applying Adams numerical technique for influential outcomes of aggressing parameters including Hartmann number , wall stretching ratio , thermal radiation and heat source/sink to observe the effecting profiles of temperature and velocity fields. The obtained numerical data are utilized for Bayesian regularization knack-based intelligent computing method to construct the networks for approximate solution dynamic of nanofluidic models. The worth and value of designed Bayesian regularization knack-based networks (BRKNs) is established by regression index measurements, error histogram studies and convergence curves with negligible level of mean square error (E-12 to E-10) for the exhaustive simulations.
© The Author(s), under exclusive licence to Società Italiana di Fisica and Springer-Verlag GmbH Germany, part of Springer Nature 2023. 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.