Application of Levenberg-Marquardt artificial neural network to study nanoparticle aggregation phenomena in stagnation point flow towards an off-centered rotating disk

The off-centered stagnation point flow of nanoliquid past a revolving disk has applications in numerous industrial and engineering procedures. This phenomenon is crucial in improving heat transport capability in cooling systems like heat exchangers, turbine blades, and high-performance electronics. In view of this, the current study inspects the off-centric stagnation point flow of nanoliquid with the consequence of nonlinear thermal radiation and heat source/sink via a revolving disk. Additionally, the significance of nanoparticle aggregation is considered in analyzing the liquid flow and heat transport properties. Using appropriate similarity transformations, the governing partial differential equations (PDEs) are transformed into ordinary differential equations (ODEs). Further, the Runge-Kutta Fehlberg's fourth-fifth order (RKF-45) technique is subsequently employed to solve the resultant ODEs numerically. Moreover, the Levenberg-Marquardt artificial neural network (LM-ANN) is implemented to assess the liquid flow and heat transport attributes. The Levenberg-Marquardt procedure builds and trains the artificial neural network technique for thermal and velocity profiles. The consequence of subsequent parameters on the thermal and velocity profiles is demonstrated in the graphs. For the radiation parameter, the heat transmission rate is around 4.99% for without aggregation case, and 7.18% for with aggregation case. An increment in the rotation parameter increases the radial velocity profile, whereas it reduces the azimuthal velocity profile. The heat source/sink and radiation parameters enhance the thermal profile.