A Machine Learning Approach to Predicting the Heat Convection and Thermodynamics of an External Flow of Hybrid Nanofluid

Abstract This study numerically investigates heat convection and entropy generation in a hybrid nanofluid (Al2O3–Cu–water) flowing around cylinder embedded porous media. An artificial neural network is used for predictive analysis, which numerical data are generated to train an intelligence algorithm optimize the prediction errors. Results show that transfer of system increases when Reynolds number, permeability parameter, or volume fraction nanoparticles increases. However, functional forms these dependencies complex. In particular, increasing nanoparticle concentration found have nonmonotonic effect on generation. The simulated predicted subjected particle swarm optimization produce correlations shear stress Nusselt number. demonstrates capability algorithms predicting thermohydraulics thermodynamics thermal solutal systems.