Artificial neural network driven investigation of thermal exchange through hybrid nanofluid of polymer/CNT across parallel sheets

Present study is to investigate the flow of hybrid-nanofluid (Hnf) with thermos-material exchange considering the influence of a activation energy and magnetic effect beyond parallel, twin revolving planes, incorporating Artificial Intelligence AI-based machine learning technique. Artificial intelligence is rapidly advancing across various fields, providing innovative solutions, and significantly improving the ability to analyze complex scenarios and pattern in diverse areas. The critical parameters like Prandtl number, suction/injection parameter, Schmidt number, and material parameter are taken into consideration in order to understand the flow characteristics and thermal exchange rates in this research. To synthesize the Hnf, polymer/CNT matrix nanocomposites (MNCs) are dissolved in water. These MNCs, made from polymer and CNT, demonstrate exceptional properties and high efficiency. Their outstanding thermophysical characteristics make them highly valuable in the field of engineering and biomedical research. We have expressed the fluid flow as a system of partial differential equations (PDEs) then by the appropriate similarity transform, the system of nonlinear PDEs is converted into a set of nonlinear ODEs, thereby reducing the complexity and order of the system and solved numerically using the MATLAB. It is also noted that the fluid flow rate declines due to the combined effects of porosity and, Lorentz parameter. It was observed that velocity decreased by 25% with an increase in Lorentz coefficient from 0 to 1, while the temperature increased by 14% under thermal source influence.