Abstract
I will present a versatile computational framework that employs Physics-Informed Neural Networks (PINNs) to discover constitutive equations for the extra-stress in rheological models of polymer solutions. In this framework, the training of the neural network is guided by a meta-model for the conformation tensor that adheres to the GENERIC formalism (General Equation for Non-Equilibrium Reversible–Irreversible Coupling). The use of GENERIC enables a reduction of the parameter space by restricting the search to thermodynamically admissible fluid models—that is, those that strictly satisfy the First and Second Laws of Thermodynamics. The discovery of different geometric blocks within GENERIC includes irreversible entropic contributions, anisotropic mobility terms related to the friction tensor, and specific choices of the objective derivative for the microstructural variables. We discuss the potential of data-driven PINN approaches to identify such models and compare various training strategies, including viscometric and complex flow data. The PINN strategy is incorporated into CFD tools for the simulation of polymeric flows using RheoTool-OpenFOAM. Fluid dynamics results will be presented to assess the accuracy of the aforementioned methodology. Finally, I will discuss possible outlooks and perspectives on using this approach to accelerate multiscale polymer simulations and/or to directly incorporate experimental data into the model.
About the Speaker
Marco Ellero is an Ikerbasque Research Professor and Head of the Computational Fluid Dynamics Group at the Basque Center for Applied Mathematics in Bilbao (Spain), and an Honorary Professor at the Complex Fluids Research Group at Swansea University (UK). Previously, he was an Associate Professor at the Zienkiewicz Center for Computational Engineering, Swansea University, and he worked as a postdoctoral researcher in the Department of Mechanical Engineering at the Technical University of Munich and the University of Sydney. He obtained his undergraduate degree and Ph.D. in Theoretical Physics from the Technical University Berlin in 2004. His research focuses on multiscale modeling of microstructural non-Newtonian fluids using meshless methods, particularly pioneering the application of Smoothed Particle Hydrodynamics to viscoelastic fluids and complex suspensions, as well as to the stochastic regimes of fluctuating viscoelasticity.
Host: Professor Randy Ewoldt