Artificial neural network technique for thermal evaluation of bio-nanofluid flow via extendable surface with magneto-dipole and thermal radiative effects

Abstract

In this investigation, the stream of bio-magnetic liquid specifically, blood flow containing copper nanoparticles, past a stretchy surface that is impacted by thermal radiation and a magnetic field, is studied. In this analysis, copper nanoparticles (Cu-NPs) are utilized due to their wide range of applications in biological research. Copper nanoparticles possess antibacterial, antimicrobial, and antifungal capabilities as a result of their characteristics. The non-linear partial differential equations (PDEs) are reduced to ordinary differential equations (ODEs) by the use of a similarity transformation. The physical solution was determined by applying neural network technology (NNT). The relevant dimensions of this model, including the radiation parameters, suction, slip, ferromagnetic, magnetic field, and radiation, are graphically illustrated for various profiles. One of the most important findings was that temperature and velocity decrease in proportion to increases in the ferromagnetic factor. The wall friction factor and Nusselt number exhibit a consistent declining pattern for the parameters of radiation conduction, and copper volume fraction. However, it establishes opposite trends for the ratio of free stream to stretching velocities. Also, a regression model curves, histograms, and MSE results are used to evaluate and verify the efficacy of the NNT. The outcomes achieved indicated that NNTs provide reliable predictions and performance enhancements.