Dr.-Ing. Daniel Wolff

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

Trávníková, V., Wolff, D., Dirkes, N., Elgeti, S., von Lieres, E., & Behr, M. (2024). A model hierarchy for predicting the flow in stirred tanks with physics-informed neural networks. In Advances in Computational Science and Engineering (Vol. 2, Issue 2, pp. 91–129). American Institute of Mathematical Sciences (AIMS). https://doi.org/10.3934/acse.2024007

Fricke, C., Wolff, D., Kemmerling, M., & Elgeti, S. (2023). Investigation of reinforcement learning for shape optimization of 2D profile extrusion die geometries. In Advances in Computational Science and Engineering (Vol. 1, Issue 1, pp. 1–35). American Institute of Mathematical Sciences (AIMS). https://doi.org/10.3934/acse.2023001

Peer-Reviewed Proceedings and Book Contributions

Sahin, T., Wolff, D., von Danwitz, M., & Popp, A. (2024). Towards a Hybrid Digital Twin: Fusing Sensor Information and Physics in Surrogate Modeling of a Reinforced Concrete Beam. In 2024 Sensor Data Fusion: Trends, Solutions, Applications (SDF) (pp. 1–8). 2024 Sensor Data Fusion: Trends, Solutions, Applications (SDF). IEEE. https://doi.org/10.1109/sdf63218.2024.10773885

Idzik, C., Hilger, D., Hosters, N., Kemmerling, M., Niemietz, P., Ortjohann, L., Sasse, J., Serafeim, A., Wang, J., Wolff, D., & Hirt, G. (2023). Decision Support for the Optimization of Continuous Processesusing Digital Shadows. In Interdisciplinary Excellence Accelerator Series (pp. 281–301). Springer International Publishing. https://doi.org/10.1007/978-3-031-44497-5_12

Wolff, D., Fricke, C., Kemmerling, M., & Elgeti, S. (2023). Towards shape optimization of flow channels in profile extrusion dies using reinforcement learning. In PAMM (Vol. 22, Issue 1). Wiley. https://doi.org/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