Neural network-based advanced study of infused-nanoparticles blood flow through stenosed arteries

The study of fluid flow in stenosed arteries is important due to its direct relevance to cardiovascular disorders and biomedical applications. In the present work, the flow and heat transfer behaviour of a hybrid nanofluid in a narrowed arterial geometry is examined under the influence of key physical parameters. The mathematical formulation is developed by considering steady, laminar, and incompressible flow conditions, together with appropriate boundary conditions that represent the physical situation. The governing nonlinear equations are transformed into a system of ordinary differential equations using suitable similarity transformations. These equations are solved numerically using a boundary value approach. In addition, an artificial neural network (ANN) model is employed to predict the flow and temperature profiles using the generated numerical dataset. The results show that variations in the governing parameters directly influence the velocity and temperature distributions within the flow domain. The ANN predictions are found to closely match the numerical results, with error values of the order of \(10^{-6}\) to \(10^{-7}\) , indicating good agreement between both approaches. This agreement supports the use of the ANN model as a reliable tool for predicting flow and heat transfer behaviour in stenosed arteries. The outcomes of this study provide a useful framework for analyzing complex fluid flow problems in biomedical systems and may be extended to related applications involving hybrid nanofluids.