Intelligent computing paradigm for the Buongiorno model of nanofluid flow with partial slip and MHD effects over a rotating disk

This study examines the Buongiorno model for the MHD nano-fluid flow through a rotating disk under the influence of partial slip effects using the Levenberg Marquardt back-propagation neural networks scheme (LMB-NNS). The basic system of nonlinear PDEs used to describe the Buongiorno model of MHD nanofluid flow over rotating disk (BM-MHD-NRD) model is converted into an analogous nonlinear ODEs system utilizing similarity transformations. A data set for the recommended LMB-NNS is spawned using the Explicit Runge-Kutta numerical method for a variety of BM-MHD-NRD scenarios by varying the magnetic field number (M), velocity slip parameter (γ), thermophoresis parameter (Nt), Brownian motion parameter (Nb), thermal slip parameter (α) and Schmidt number (Sc). The estimate solution of separate cases has been examined using the LMB-NNS testing, validation, and training method, and the suggested model has been matched for verification. The MSE, regression analysis, and histogram studies have been used to authenticate the recommended LMB-NNS. The LMB-NNS technique has various applications such as disease diagnosis, Robotic control systems, Ecosystem evaluation etc. Analysis of some statistical date like gradient, performance and epoch of the model. With a level of accuracy ranging from 10⁻⁰⁹ to 10⁻¹², the suggested approach is differentiated as the closest of the suggested and reference results.