Machine learning examination based on Bayesian regularized algorithm for slip effects on solarized Boger nanofluid with activation energy

Abstract

This model is highly helpful in thermal management and complex energy systems, particularly where precise control over heat and mass transfer is required. Solarized nanofluids can be used to improve heat absorption and transfer in solar thermal collectors, photovoltaic cooling systems, and energy storage devices. The inclusion of slip effects, thermophoresis, and Brownian motion makes the model applicable to micro- and nano-scale devices such as MEMS, micro reactors, and biomedical cooling systems. Furthermore, Bayesian regularization-based machine learning analysis enhances prediction accuracy for complex nonlinear behaviors, making the model effective in industrial process optimization, polymer processing, and chemical reactors that use non-Newtonian fluids with activation energy effects. The heat generation influence on magnetohydrodynamic (MHD) solarized Boger nanofluid under slip velocity and activation energy effects are examined in this paper. The nonlinear relationship between the governing physical parameters and the resulting flow and heat transfer behaviour is modelled using an artificial intelligence-based neural network framework that has been optimized using the Intelligent Bayesian Regularization technique. The neural network is trained using 80% of the generated dataset, with the remaining 20% being utilized for testing to ensure the suggested model is correct, dependable, and predictive. As the values of the chemical reaction parameter grow, the concentration profile decreases.