An artificial intelligence and numerical simulation-based strategy for multi-objective optimization of hemodynamics in curved vessels

On the Performance of Physics-Informed Neural Networks for Hemodynamic Predictions in Parameterized Vascular Stenoses

It is highlighted that while current PINNs can reliably reproduce velocity fields, their ability to capture localized pressure dynamics remains limited, indicating the need for more robust formulations.

Perturbation Iteration Algorithm-Based Semi-Analytical Blood Flow Model for the Jeffrey Hamel

  This study presents an enhanced approach for solving the magneto- hydrodynamic nonlinearJeffrey-Hamel (MHD-JHF) problem, modeling human arterial blood flow, using a hybridmetaheuristic combining Particle Swarm Optimization (PSO) and the Perturbation IterationAlgorithm (PIA). The model is formulated from third-order o...

Analysis and optimization of toroidal composite pressure vessels using data-driven evolutionary algorithms

Toroidal pressure vessels manufactured by filament winding are a promising solution for storing gases or liquids in confined spaces where conventional cylindrical or spherical vessels are unsuitable. This study introduces a hybrid framework that combines analytical modelling of geodesically wound toroids with a data-dr...

Characterization of Turbulent Kinetic Energy and Shear Layers in Sudden Expansion Flows: A Physics-Informed Machine Learning Approach.

Surrogate-Assisted Multi-Objective Optimization of an Axial-Flow Ventricular Assist Device Rotor Using CFD, Hybrid Surrogates, Sobol Analysis, and MOPSO.

BACKGROUND This study presents a surrogate-assisted workflow for multi-objective optimization of an axial-flow ventricular assist device (VAD) rotor using 4809 steady-state CFD simulations spanning six geometric variables. METHODS Repeated learning-curve analysis and blade-count-stratified Gaussian-process regression...

Machine learning-based design of optimal explicit Runge–Kutta schemes for compressible flow equations