Physics-Informed Machine Learning for complex fluids and soft matter
| When |
Jul 10, 2023
from 11:00 to 12:00 |
|---|---|
| Where | Salle des Thèses |
| Attendees |
Safa Jamali |
| Add event to calendar |
vCal
iCal
|
Reliable and accurate prediction of complex fluids’ response under flow, or mechanical properties of soft materials in general are of great interest across many disciplines, from biological systems to manufacturing. The challenges include solving non-trivial time and rate dependent constitutive relations to describe these structured materials under various flow protocols, and in correlating constituents of a complex material to its rheological behavior. On the other hand, advances in data-driven approaches to material design and discovery promise a leap in accelerated design cycles for new materials. I will introduce the general methodology of data-driven science and engineering briefly, and then present Rheology-Informed Neural Networks (RhINNs) as a general platform for prediction of rheological behavior in complex fluids. This includes a neural network architecture capable of solving Ordinary Differential Equations (ODEs) adopted for complex fluids, in forward and reverse problems, as well as a multi-fidelity approach in which scarcity of experimental data is compensated by readily-available model predictions to train the machine learning platform. The proposed RhINNs are presented as a unified platform for prediction of rheological properties, with unprecedented accuracy and efficiency. This is done by ensuring that the main physical governing laws of the system are respected by the machine learning platform. Finally, I will show the results of our hybrid RhINNs platforms as “digital rheometer twins” that can be used in place of a physical rheometer.