A neural network approach to modeling magnetohydrodynamic stagnation point Ree-Eyring flow over a convectively heated stretched surface

This study investigates the application of artificial intelligence (AI) in fluid dynamics, mainly using a neural network trained by the Levenberg–Marquardt method (NN-BLMM), to model magnetohydrodynamic (MHD) stagnation point Ree–Eyring flow. We focus on this flow over a convectively heated stretched surface by integrating the Cattaneo–Christov heat model. The initial complex nonlinear partial differential equations (PDEs) are transformed into ordinary differential equations (ODEs) using suitable similarity variables. A dataset was generated using the Lobatto IIIA numerical solver to analyze the effects of various fluid flow and thermal parameters. The NN-BLMM model was then rigorously evaluated through training, testing, and validation phases and compared with reference data. This ensures the model’s precision and effectiveness. We observe that an increase in the Powell–Eyring fluid parameter notably reduces the fluid’s shear resistance, implying a decrease in viscosity. Concurrently, the heat transfer rate within the fluid medium increases with an increase in the internal heat generation parameter. These findings highlight the robustness of NN-BLMM in simulating complex fluid dynamics, emphasizing AI’s potential to provide a deeper understanding of non-Newtonian fluid behaviors. This research has important implications for industrial applications in which precise control over fluid properties and heat transfer is crucial.