Intelligent computing technique to study heat and mass transport of Casson nanofluidic flow model on a nonlinear slanted extending sheet

This paper explains the importance and benefits of using AI in fluid mechanics, emphasizing its capability of finding the solution of fluid flow systems through iterative optimization techniques. It explores how AI can enhance the understanding of fluid dynamics to improve engineering processes. In the presented studies, the heat and mass transport of the Casson nanofluidic flow model on a nonlinear slanted extending sheet (HMT-CNFM) via AI-based Levenberg Marquard methodology with backpropagated trained neural networks (TNN-BLMM) is studied. By applying an appropriate transformation, the governing PDEs representing HMT-CNFM are converted into a system of nonlinear ODEs. The dataset for Levenberg Marquard methodology with backpropagated trained neural network (TNN-BLMM) for all six scenarios of this proposed model via computational power of the Lobatto IIIA scheme using the “bvp4c” package in MATLAB and then graphically illustrate all these six scenarios through nftool to attain mean square error, regression, error histogram, performance, and fit curve. Training, testing, and validation processes of NN-BLMM are organized for the investigation of the HMT-CNFM model.