Artificial Intelligence‐Based Optimization of Heat Transfer in Gyrotactic‐Nanofluid Flow

This chapter presents a central composite factorial design (CCFD)-based artificial neural network (ANN) model to optimize the heat transfer rates in a two-dimensional, steady, laminar-boundary layer flow for a nanofluid consisting of gyrotactic microorganisms on a nonlinear stretching plate. The base fluid, water, is selected to facilitate fluid flow stimulation. This flow problem occurs in various industrial and engineering applications, such as aerodynamic heating and polymer processing. Appropriate similarity transformations are employed to translate the governing partial differential equations with boundary conditions into nonlinear third-order ordinary differential equations for numerical computations. The Runge–Kutta fourth-order method is employed for simulating transformed highly nonlinear ordinary differential equations. The influence of physical parameters on the temperature, velocity, concentration, and microbe density profiles is examined through visual representations. A unique neural network is designed to optimize the Nusselt number with the numerical data displayed in both graphical and tabular formats. This research is pivotal for industrial and engineering applications, enabling the precise control of heat transfer rates through the optimization of critical parameters.