Levenberg–Marquardt artificial neural network approach to analyze tetra hybrid nanofluid flow over a rough rotating disk under low/high oscillating magnetic fields

The present analysis elucidates the impact of low-oscillating and high-oscillating magnetic fields on the tetra hybrid nanofluid flow past a rough revolving disk. Additionally, the influence of nonlinear thermal radiation and non-uniform heat source/sink on the fluid flow is considered to evaluate the heat transport attributes. The classical von Karman issue of a revolving disk is examined with partial slip at the disk surface. The similarity variables are used to convert the governing partial differential equations (PDEs) into ordinary differential equations (ODEs). Furthermore, the resultant ODEs are solved numerically using the Runge–Kutta Fehlberg’s fourth-fifth order (RKF-45) approach. Moreover, the Levenberg–Marquardt artificial neural network (LM-ANN) is employed to assess the heat transmission rate for various parameters. Also, the results of RKF-45 are compared with the outcomes of the LM-ANN technique. A sensitivity analysis is performed using response surface methodology (RSM) with analysis of variance (ANOVA) to investigate the heat transport rate for various parameters. The graphical depictions are utilized to investigate the notable impact of several dimensionless parameters on the thermal and velocity profiles. The comparison of the low-oscillating magnetic field and high-oscillating magnetic field for various parameters on the velocity profile is elucidated in this study. The rise in the thermal radiation parameter, along with temperature-and space-dependent heat source/sink parameters, increases the temperature profile.