Location: Mensa-Room 0001; digital participation (link shared via e-mail)
Ali Khalifa: Neural Network-Based Multiscale Modeling of Deagglomeration due to Wall Impact and Collisions
Predicting the evolution of micron-sized particle system in fluid flows is crucial for natural processes and industrial applications like pharmaceuticals. Fully-resolved simulations are costly due to scale variations. Hence, data-driven approaches offer an attractive alternative. This study enhances an Euler-Lagrange method with neural-network models for deagglomeration from collisions and wall impacts, integrated into LES-based simulations. Tested in various turbulent flows, such as funnel-duct dispersers and bend pipes, this approach provides cost-effective predictions.
Denis Kramer: Designing Functional Materials: Dream, Predict, Synthesise, Characterise, Repeat