Supervised Learning Algorithm to Study the Magnetohydrodynamic Flow of a Third Grade Fluid for the Analysis of Wire Coating

In the present study, modeling of intelligent numerical computing through Levenberg–Marquardt back propagation-based supervised neural network (LMB-SNN) is incorporated to analyze the magnetohydrodynamic flow of a third grade fluid for wire coating analysis (MHD-TGFWCA). The original mathematical formulations in terms of partial differential equations for MHD-TGFWCA are converted into a system of ordinary differential equations through dimensionless parameters and a suitable transformation mechanism. A reference dataset for the LMB-SNNs scheme is created with Adam’s numerical technique for various scenarios by variation of different physical quantities such as third grade fluid parameter, magnetic parameter, and the velocity ratio parameter. To compute the approximate solution for MHD-TGFWCA in terms of various scenarios, the training, testing, and validation operations are carried out in parallel to adjust neural networks by developing the mean square error function (MSEF) through Levenberg–Marquardt back-propagation. The comparative analyses and performance studies through outputs of MSEF, regression illustrations, and error histograms validate the effectiveness of the suggested solver LMB-SNNs. The method’s precision is verified by the closest numerical outputs of both built and dataset values with similar levels [Formula: see text] to [Formula: see text] .