Kontakt
Tel.:
+49(2871)2155-433
E-Mail schreiben
E-Mail-Adresse anzeigen
Raum: B1.1.22
Münsterstr. 265
46397 Bocholt
Jan Hauke Harmening
wiss. Mitarb.
Zur Person
Fachbereich Maschinenbau Bocholt (FB 6)
Informationen zur Person
Forschungsgruppe Physics-Informed Neural Networks
Forschungsgebiete
- Deep learning
- Physics-informed neural networks
- Computational fluid dynamics
- Flow control
Lehre
Forschung
Harmening, J. H., Peitzmann, F. J. & el Moctar, O. (2024). Effect of Network Architecture on Physics-Informed Deep Learning of the Reynolds-Averaged Turbulent Flow Field around Cylinders without Training Data. Frontiers in Physics, 12.
Pioch, F., Harmening, J. H., Müller, A. M., Peitzmann, F. J., Schramm, D., & el Moctar, O. (2023). Turbulence Modeling for Physics-Informed Neural Networks: Comparison of Different RANS Models for the Backward-Facing Step Flow. Fluids, 8(2), 43.
Harmening, J. H., Pioch, F., & Schramm, D. (2022). Physics Informed Neural Networks as Multidimensional Surrogate Models of CFD Simulations. Proceedings of the Machine Learning und Artificial Intelligence in Strömungsmechanik und Strukturanalyse, Wiesbaden, Germany, 16.-17.05.2022.
Harmening, J. H., Devananthan, H., Peitzmann, F. J., & el Moctar, B. O. (2022). Aerodynamic Effects of Knitted Wire Meshes—CFD Simulations of the Flow Field and Influence on the Flow Separation of a Backward-Facing Ramp. Fluids, 7(12), 370.
Bach, D., Harmening, J. H., Höfer, M., Masselter, T., & Speck, T. (2018). Separation of Entrained Air Bubbles from Oil in the Intake Socket of a Pump Using Oleophilic and Oleophobic Woven and Nonwoven Fabrics. Journal of Fluids Engineering, 140(3), 031301.