Gebäude 41/100, Zimmer 5124 | |
089/6004 4449 | |
d.wolff@unibw.de |
Dr.-Ing. Daniel Wolff
Research Interests
In my research, I was so far concerned with the data-driven construction of reduced simulation models. The following methods were used for this purpose:
- Physics-Informed Neural Networks (PINNs)
- Reinforcement Learning
The methods were applied for shape optimization of flow channels in profile extruders as well as for the prediction of flow fields in bioreactors.
Academic Career
I started studying Computational Engineering Science at RWTH Aachen University 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.
Starting in March 2020, I did my PhD as part of the HDS-LEE Graduate School, which deepened my knowledge about machine learning.
02/2024 – present | Postdoctoral Researcher, Institute for Mathematics and Computer-Based Simulation, University of the Bundeswehr Munich, Germany |
03/2020 – 12/2023 | Doctoral Researcher, Chair for Computational Analysis of Technical Systems, RWTH Aachen University, Germany |
10/2018 – 02/2020 | Master of Science, Computational Engineering Science, RWTH Aachen University, Germany |
10/2014 – 06/2018 | Bachelor of Science, Computational Engineering Science, RWTH Aachen University, Germany |
Publications
Peer-reviewed publications
Clemens Fricke, Daniel Wolff, Marco Kemmerling, Stefanie Elgeti. Investigation of reinforcement learning for shape optimization of 2D profile extrusion die geometries. Advances in Computational Science and Engineering, 2023, 1(1): 1-35. DOI: 10.3934/acse.2023001 |
Peer-Reviewed Proceedings and Book Contributions
Idzik, C. et al. (2024). Decision Support for the Optimization of Continuous Processes using Digital Shadows. In: Brecher, C., Schuh, G., van der Aalst, W., Jarke, M., Piller, F.T., Padberg, M. (eds) Internet of Production. Interdisciplinary Excellence Accelerator Series. Springer, Cham. DOI: 10.1007/978-3-031-44497-5_12 |
Wolff, D., Fricke, C., Kemmerling, M. and Elgeti, S. (2023), Towards shape optimization of flow channels in profile extrusion dies using reinforcement learning. Proc. Appl. Math. Mech., 22: e202200009. DOI: 10.1002/pamm.202200009 |
Monographs
Wolff, D. (2023). Learning-based approaches for the analysis and optimization of profile extrusion dies and bioreactors. Dissertation. RWTH Aachen University. DOI: 10.18154/RWTH-2023-10706 |
Wolff, D. (2020). Modern Design of a C++17 Finite Element Continuum Mechanics Simulation Code: Automatized Differentiation and Flexible Coupling Strategies. Master's Thesis. RWTH Aachen University. DOI: 10.18154/RWTH-2020-09061 |