AI multi-parameters Bayesian with Genetic optimization for the Hall effect on squeezing slip flow

This study presents an AI-driven hybrid optimization framework that integrates Bayesian Optimization (BO) and Genetic Algorithms (GA) to efficiently determine the optimal parameters maximizing the upper-plate Nusselt number ( N u upper ) and minimizing the lower-plate skin friction coefficient ( C f , x lower ). An unsteady MHD slip flow of a MoS₂–SiO₂ / EG–water hybrid nanofluid is examined between two displaceable parallel plates under a strong magnetic field, incorporating Hall current, thermal radiation, Darcy porous medium, and viscous dissipation effects. The finite difference method (FDM) implemented in Python is used to solve the transformed nonlinear equations. Results indicate that the hybrid nanofluid significantly enhances heat transfer compared with the mono-nanofluid, particularly at the upper plate. Increasing the Eckert number raises the temperature due to viscous heating, while stronger magnetic and Hall effects elevate wall shear at the lower plate. The proposed AI-based optimization framework reduces computational cost and provides a robust strategy for multi-objective tuning in complex thermal systems, offering promising applications in smart thermal management, microfluidics, and energy recovery technologies.