Artificial neural network modeling of mixed convection viscoelastic hybrid nanofluid across a circular cylinder with radiation effect: Case study

Abstract

As a result of its use in the manufacturing and construction industries, research on the flow of nanofluid is rather well-known among academics and professionals in related fields. It is helpful for electrical equipment to utilize it for cooling reasons, which has shown promising results in terms of reducing energy use. As a result, the primary objective of this research is to inspect the impacts that radiation has on the mixed convection of Walters'-B hybridity nanofluid flow of stagnant point in a horizontal circular cylinder under the circumstances of a constant heat flux. It is considered a conventional fluid despite the presence of copper (Cu) and alumina (Al2O3) nanoparticles in the water (H2O) hybridity nanofluid. To make the solution to the resulting controlling system of equations more straightforward, the numerical approach of a neural network with a back-propagation algorithm (NN-BPA) is used. It follows by clarifying how various physical characteristics, such as blended convection, thermal radiation, and stagnant movement, affect temperature, skin friction, thermal transfer, velocity, and graphical profiles of those variables. The LMNN-BPA has the quickest processing algorithm and performs well in general, corresponding to the thorough analysis. Additionally, the mixed convective and viscoelastic properties exhibit both rising and dropping developments regarding skin friction and heat transmission.

Keywords

• Hybrid nanofluid
• Mixed convection
• Thermal radiation
• Levenberg-Marquardt neural network
• Stagnation point