Refined Ann Predictions for Reiner–Rivlin Fluid With Dispersed Hybrid Nanoparticles Around an Isothermal Porous Cone

This study presents numerical solutions for the steady non‐Newtonian Reiner–Rivlin viscous flow around an isothermal vertical permeable porous cone with a linearly variable surface temperature of degree . The research investigates the role of hybrid nanomaterials, which consist of multiple magnetic nano‐sized particles dispersed in the base fluid, in enhancing heat and mass transfer characteristics. The governing coupled, nonlinear equations were formulated and solved using a finite difference method, leading to the identification of critical phenomena governing the flow and thermal behavior. Results reveal that the Reiner–Rivlin factor significantly enhances the velocity and its gradient , showcasing the pronounced non‐Newtonian effects. Similarly, the temperature gradient exhibits substantial variations under different physical parameter conditions, highlighting the intricate interplay between viscous forces and thermal conductivity. The study also emphasizes the influence of key parameters such as the Hartmann number, Prandtl number, and Darcy number on the flow dynamics, shedding light on their individual and combined effects. To augment the numerical analysis, an artificial neural network (ANN) model was employed to predict the values of with remarkable accuracy. The ANN model demonstrated excellent agreement with numerical computations, validating its efficacy in forecasting complex fluid behaviors. This integration of ANN with numerical techniques not only enhances predictive capabilities but also underscores the potential for machine learning in solving challenging fluid mechanics problems. These findings provide valuable insights for applications in engineering, thermal management, and material science, paving the way for optimized designs in industrial and environmental systems.