Artificial intelligent computing of advanced nanomaterials under electrothermal heating

Hybrid nanofluid technologies incorporating multiple nanoparticles have become increasingly important for enhancing thermal transport in contemporary engineering systems. In this work, the transport characteristics of hybrid nanofluid are explored in the presence of Joule heating, magnetic field effects, thermal radiation, through vertically stretched surface. The physical model is formulated to examine the coupled momentum and heat transfer mechanisms associated with electrically conducting nanofluids under dissipative energy effects. By employing suitable similarity transformations and thermophysical relations, the governing nonlinear equations are converted into a dimensionless mathematical system. The computational investigation performed through an Artificial Neural Network (ANN) framework, which provides efficient prediction and analysis of the transport phenomena with high computational accuracy. The analysis reveals that the stretching of the surface ( $$\:\lambda\:=\text{0.1,0.2,0.3,0.4}$$ ) intensifies the fluid motion, whereas Hartman number ( $$\:M=\text{0.2,0.4,0.6,0.8}$$ ) opposes the flow and reduces the velocity distribution due to electromagnetic resistance. Additionally, stronger Joule heating, radiation ( $$\:Rd=\text{1.0,3.0,5.0,7.0}$$ ), and Eckert number ( $$\:Ec=\text{0.1,0.2,0.3,0.4}$$ ) effects produce considerable enhancement in the thermal distribution. The role of concentration $$\:{\phi\:}_{i}$$ for $$\:i=\text{1,2},\text{3,4},5$$ in the range of 0.1% to 0.4% is observed beneficial for the heat mechanism. These momentum and heat mechanisms together with these effects provide a theoretical framework for improving thermal electromagnetic control in high temperature stretching surface processes, coatings, material processing and extrusion.