Artificial Neural Network Prediction and Numerical Analysis of Hall Current and Darcy-Forchheimer Effects on Dissipative Casson Fluid Flow Over a Thinner Surface

This study investigates heat transfer in a thinner using artificial neural networks (ANNs) and explores the behavior of Casson fluids under Hall current and Darcy-Forchheimer effects. The aim is to predict heat transfer rates in complex non-Newtonian fluid flows, where traditional models may not provide accurate results. The study demonstrates the significance of modeling dissipative Casson fluids in engineering applications, particularly in biomedical and industrial systems, where Hall current and Darcy-Forchheimer effects are present. Using similarity transformations, the governing partial differential equations (PDEs) are converted into ordinary differential equations (ODEs). Numerical solutions are obtained using MATLAB’s BVP4C function. The results are visualized through graphs, showing the Casson fluid behavior under the specified conditions. The study highlights the accuracy of using ANNs to predict the Nusselt number, with results closely matching the training data and theoretical predictions. This work illustrates the power of combining numerical methods and machine learning to improve fluid behavior modeling. The findings contribute to more efficient heat transfer predictions and have practical implications for optimizing industrial processes and biomedical applications.