Intelligent neuron based interpretation of carreau trihybrid nanofluid model with streamline analysis: Configuration of distinct geometries

This current attempt develops a more efficient predictive model that can accurately simulate the behavior of Carreau trihybrid nanofluids in non-trivial configurations. This study interprets thermal behavior of Carreau trihybrid nanofluid model with streamline analysis considering the two geometries wedge and cone. Three nanoparticles are involved in base fluid (water) with physical effects of non-uniform heat sink source and nonlinear thermal radiation are assumed for heat transport and Lorentz forces are considered for velocity inspection. Furthermore, this study employs intelligent neural networks to interpret data for streamline and thermal transport analysis, focusing on the specific cases of wedge and cone geometries. Initial data fetched through bvp4c and further, obtained data trained through supervised neural scheme, Levenberg marquardt neural network (LM-NN) is applied and required predictions are made. Higher “Gc” indicates stronger solutal buoyancy forces, which promote upward fluid movement, thereby increasing the velocity gradient. With increasing (M), the velocity profile decreases. Fluid exhibits enhancing the velocity gradient with higher (n). Higher particle concentration enhances the fluid's viscosity and resistance.