The proposed comparative model can be used to solve advanced thermal management problems that require accurate heat and momentum transfer predictions. It can be utilized in aerospace and automotive systems that use \({\text{Ti}}_{6} {\text{Al}}_{4}\text{ V}\) and aluminum-based nanocomposites to cool high-temperature components including turbine blades, heat exchangers, and braking systems. The proposed framework is also relevant to mineral processing and metallurgical operations, where rotating equipment, slurry-based thermal systems, and porous extraction environments require accurate prediction of heat and momentum transfer for energy-efficient operation. The inclusion of activation energy and velocity slip impacts makes the model appropriate for micro-/nanoscale flows, which are relevant to microfluidic devices. Furthermore, the trihybrid nanofluid framework with NaAlg as a base fluid has utilizations in energy systems, biomedical thermal transport, and polymer processing, where increased conductivity, controlled reaction rates, and non-Newtonian behavior must be reliably captured using intelligent technique such as the Levenberg–Marquardt neural network method. This study uses artificial neural networks trained using a Levenberg–Marquardt strategy to analyze the activation energy and heat generation effect on slip flow of Boger \({\text{Ti}}_{6} {\text{Al}}_{4}\text{ V}-\text{AA}7072-\text{AA}7075/\text{NaAlg}\) -based trihybrid nanofluid across a disk. The two distinct models of thermal conductivity used in this study are the Hamilton–Crosser model and the Xue model. Similarity transformations are used to reduce the original nonlinear partial differential equations to non-dimensional ordinary differential equations, and the resulting boundary-value problem is then numerically resolved using the bvp4c program. The concentration profile rises as the activation energy parameter values increase.
Graphical Abstract
