Analysis of Williamson Fluid under Thermal Radiation and Inclined Magnetic Field over a Stretching Surface with Slip Effects Using Feedforward Neural Networks

This investigation analyzed the effects of multiple slip conditions on Williamson fluid flow over a stretching surface under thermal radiation and an inclined magnetic field. The governing equations were derived from established conservation laws and solved using feedforward neural networks (FNNs) together with finite-difference solutions. By appropriate similarity transformations, the partial differential equations (PDEs) are reduced to a system of nonlinear ordinary differential equations (ODEs). The finite difference method (FDM) is employed as a computational solution in conjunction with FNN. Moreover, visual analysis is conducted to explore the role of dimensionless properties in flow behavior, with tabulated data on friction, Nusselt value, and mass transfer rates demonstrating the impact of physical parameters. With a higher magnetic parameter, the fluid flow experiences a decline in velocity, whereas mixed convection increases it. An elevation in Brownian motion and thermophoresis parameters results in a rise in temperature. This research contributes to obtaining more precise results in fluid dynamics and heat transfer analysis, particularly in the context of slip effects, radiative influences, and magnetic field interactions.