Optimization of micro-rotation effect on magnetohydrodynamic nanofluid flow with artificial neural network

Abstract

It is a major research area in mathematics, physics, engineering, and computer science to study the heat and mass transfer properties of flow. Suspensions containing multiple nanoparticles or nanocomposites have recently gained a wide range of applications in biological research and clinical trials under certain conditions. Nanofluids are important suspensions that allow nanoparticles to disseminate and behave in a homogeneous and stable environment. Therefore, here magnetohydrodynamic micropolar nanofluid flow towards the stretching surface with artificial neural network has been considered. In this study, radiation and heat source phenomena have been presented in heat convection. Brownian and thermophoresis effects and micro-rotational particles are also taking into account. The non-linear simplified equations have been calculated numerically via Runge-Kutta fourth-order shooting process. The calculation of the Sherwood number, Nusselt number, couple stress coefficient, and skin friction coefficient has been conducted utilizing diverse parameters. Furthermore, the outcomes have been employed to create four distinct artificial neural networks. Our observation indicates that an increase in the heat source quantity leads to a rise in heat generation, resulting in a greater total heat output and an increase in the temperature field. Coefficient of determination “R” values higher than 0.99 have been obtained for the artificial neural network models. The obtained findings have shown that artificial neural networks can predict thermal parameters with high accuracy.