Bayesian-regularized neural network analysis of heat and mass transmission in CMC and water hybrid nanofluid with local thermal non equilibrium conditions.

The influences of Marangoni convection and local thermal non-equilibrium effects on CuO-TiO₂/CMC (Carboxymethyl Cellulose)-Water based hybrid nanofluid flow via a sheet with thermophoretic particle deposition have been assessed in this work using an artificial intelligence technique. In electrical and aerosolution engineering, thermophoretic particle deposition is a simple method for transferring tiny particles over a thermal gradient. This model can be used to build and optimize advanced cooling systems for electronics, particularly where exact heat dissipation is required. It can also be used in thermal management for the automotive and aerospace industries, where hybrid nanofluid improve heat transfer efficiency. Additionally, the model can aid in the growth of energy-effective systems for solar thermal energy collectors, industrial heat exchangers, and biological uses like as targeted drug administration, where precise temperature control is required. By capturing complicated fluid behaviors under changing conditions, the model helps to improve heat exchanger performance, increase device cooling efficiency, and provide insight into nanofluid behaviour in useful uses. The outcomes of the research demonstrate that the generated ANN model is a high-performance engineering tool that can be used to represent Marangoni convection effects and can make predictions with a high degree of accuracy. The concentration field declines as the values of the thermophoretic parameters grow.