The current analysis investigates the classification of thermal transport of tri-hybrid radiative viscous nanofluid with the Hall current aspect over a rotating disk. The chief motive of the research is to link Hall currents, radiation and rotating geometries in optimizing the thermal performance of nanofluids.
The integration of intelligent machine learning techniques, such as the Levenberg–Marquardt Neural Network (LM-NN), in modeling nanofluid behavior is motivated by the need for precise and efficient solutions to complex flow phenomena.
The governing partial differential equations (PDEs) representing the ternary radiative viscous nanofluid flow with effects of uniformly shaped nanoparticles, Hall current, and radiative heat transfer are formulated. A hybrid computational framework, LM-NN, is used for numerical prediction of temperature and velocity fields after converting PDEs into ordinary differential equations (ODEs).
Velocity profile of tri-hybrid nanofluid (THNF) decreases with augmented values of magnetic parameters because of the strong impact of Lorentz force. Increasing values of the Hall current parameter cause a decline in the velocity profile. The best validation performance for the Hall current parameter is noted at 2.34e−06 for 1,000 epochs. Increasing values of the unsteadiness parameter (S) intensified the temperature profile, and the best validation performance was noted at 2.0782e−06 for 1,000 epochs.
Enhanced heat transport mechanism in Trihybrid Carreau nanofluid flows by using a rotating disk. Integration of diverse factors such as viscous dissipation, uniform heat sink/source and thermal radiation in the physical model. Incorporation of magnetohydrodynamics (MHD) and Hall current consequences in a flow of THNF. Dual computational approaches such as bvp4c and LM-NN. Role of emerging parameters on velocity and temperature profile via MATLAB illustrations and statistical data.
