Neural computing analysis on synergistic impacts of micro-polarity and particle rotation across an off-centered stagnation point ternary hybrid nanofluid flow

This study explores the off-centered stagnation point flow and thermal behaviour of a micropolar ternary hybrid nanofluid over a revolving disk, with the aim of understanding how microstructural effects and nanoparticles influence heat transfer. The governing model incorporates key physical mechanisms such as quadratic thermal radiation, magnetic field, heat sink/source, and convective heat transfer, allowing a realistic representation of practical thermal systems. Similarity transformations are used to solve the governing equations and convert them into ordinary differential equations (ODEs). The Runge-Kutta-Fehlberg fourth-fifth order (RKF-45) approach is used to solve the simplified ODEs, and an artificial neural network (ANN) is used to increase forecast accuracy in a variety of operating scenarios. The analysis reveals that the convective boundary conditions and heat sinks/sources play a significant role in energy distribution, quadratic radiation and magnetohydrodynamic forces significantly alter the thermal boundary layer. Ternary hybrid nanoparticles with micropolar characteristics greatly enhance heat transfer, underscoring their importance in complex energy systems, microfluidic technologies, and biomedical cooling. The results further reveal that temperature rises with increasing Biot number and radiation parameter, while higher spin-gradient viscosity and micro-inertia density intensify radial microrotation but suppress azimuthal microrotation.