I started studying Computational Engineering Science at RWTH in October 2014. In my bachelor's degree, I broadened my knowledge in energy technology with a focus on renewable energies. After my bachelor, I continued my studies with a master in the same subject, but then focused on numerical methods for fluid dynamics simulations.
Since March 2020 I have been working as a research associate at CATS and I am part of the HDS-LEE Graduate School.
In my research, I am concerned with the data-driven construction of reduced simulation models. The following methods are used for this purpose:
- Invertible Neural Networks (INNs)
- Physics-Informed Neural Networks (PINNs)
- Reinforcement Learning
The methods are applied for shape optimization of flow channels in profile extruders as well as for the prediction of flow fields in bioreactors.
Supervised student theses
Advanced Strategies for Improving Physics-Informed Neural Networks as Reduced
Simulation Models, Master Thesis, RWTH Aachen, 2022
Improving Reinforcement Learning for Shape Optimization of Profile Extrusion Die
Flow Channels through Multi-Environment Training and Custom Flow Field Feature
Extractors, Master Thesis, RWTH Aachen, 2022
Physics-Informed Neural Networks for Predicting the Flow Field in Bioreactors, Master Thesis, RWTH Aachen, 2022
Development of a Python Framework for Shape Optimization based on Reinforcement Learning, Seminar Thesis, RWTH Aachen, 2021
Shape Optimization based on Reinforcement Learning, Master Thesis, TU Vienna, 2021
Physics-Informed Neural Networks as Reduced Simulation Models, Seminar Thesis, RWTH Aachen, 2021
Automatic Mesh Generation for Thermal FEM Simulations of Laser-Irradiated Lenses, Master Thesis, RWTH Aachen, 2021