Novel numerical and artificial neural computing with experimental validation towards unsteady micropolar nanofluid flow across a Riga plate.

Fluid flow across a Riga Plate is a specialized phenomenon studied in boundary layer flow and magnetohydrodynamic (MHD) applications. The Riga Plate is a magnetized surface used to manipulate boundary layer characteristics and control fluid flow properties. Understanding the behavior of fluid flow over a Riga Plate is critical in many applications, including aerodynamics, industrial, and heat transfer operations. The unsteady Micropolar nanofluid (UMNF) flow across a vertically oriented, nonlinearly stretchable Riga sheet is examined in the present study. The effects of variable thermal conductivity, thermophoretic force, and Brownian diffusion on flow and heat transfer are analyzed. The fluid flow has been expressed in the form of a nonlinear system of PDEs (partial differential equations), which are reduced into the non-dimensional form of ordinary differential (ODEs) by employing the similarity transformation approach. The dataset for training the ANNs using the Levenberg-Marquardt backpropagation (LMBP) technique is generated using numerical simulation methods. The influence of physical constraints on the dimensionless temperature, concentration, microrotation, and velocity distributions are graphically displayed and discussed. Numerical results for skin friction, Sherwood, and Nusselt numbers are presented in tabular form. The numerical outcomes are compared to both published numerical and experimental results for validity purposes. It can be noticed that the flow rate is enhanced with the rising influence of the Hartmann number, buoyancy force, and velocity slip parameter. The UMNF flow model is validated, tested, and trained with an average numerical error of 10^-9, ensuring high accuracy in energy, velocity, microorganism motility, and concentration predictions.