MHD-hybrid nanofluidic model on rotating plate with impact of thermal slip and heat absorption: a solution predictive neuro-computing approach

Abstract

The main objective of this research is to design a numerical computational solver-based two-layers structure of Levenberg–Marquardt backpropagation neural networks, i.e. LMB-NNs for the analyses of the heat transfer phenomenon and velocities structure in the MHD incompressible hybrid nanofluidic flow (MHD-IHNF) model with thermal slip and heat absorption/generation over the rotating plate through varying involved parameters, including velocity slip parameter, thermal slip parameter, concentration of Al2O3 nanoparticles, heat generation parameter, Prandtl number, Hartman number, and thermophoresis for sundry scenarios. The MHD-IHNF model is mathematically formulated as a system of PDEs that are converted in the desired system of ODEs by means of suitable transformation. The data-sets are constructed by explicit Runge–Kutta numerical technique that is exploited as a target data-set for the learning of LMP-NNs based on the process of validation, training, and testing to determine the solution of MHD-IHNF model for sundry physical scenarios. The validation, convergence, stability, and verification of LMP-NNs for solution predictive strength of the MHD-IHNF problem are certified in terms of achieved accuracy, regression index measurements, and analysis of error histogram illustrations.