Details
| Original language | English |
|---|---|
| Title of host publication | Turbomachinery - Multidisciplinary Design Approaches, Optimization, and Uncertainty Quantification; Radial Turbomachinery Aerodynamics; Unsteady Flows in Turbomachinery |
| Publisher | American Society of Mechanical Engineers(ASME) |
| ISBN (electronic) | 9780791887110 |
| Publication status | Published - 2023 |
| Event | ASME Turbo Expo 2023: Turbomachinery Technical Conference and Exposition, GT 2023 - Boston, United States Duration: 26 Jun 2023 → 30 Jun 2023 |
Publication series
| Name | Proceedings of the ASME Turbo Expo |
|---|---|
| Volume | 13D |
Abstract
Recent advances in deep learning have led to its increased application in the field of fluid dynamics. By using a data-driven approach instead of a more conventional numerical approach, it is possible to reduce the computational cost of fluid simulations significantly. Especially unsteady computational fluid dynamics (CFD) are known to require a considerable amount of time and resources. Hence, it is common practice in turbomachinery to model the flow as steady by averaging the flow between the rotor and stator in a so-called mixing plane. While this approach is numerically efficient, the full interactions between the rotor and the stator can no longer be predicted accurately due to the averaged upstream flow field. Contrary to this, the time-average of an actual unsteady flow does not contain such a modeling error while still resulting in a flow field that is decoupled from its temporal fluctuations. In this work, we introduce a graph neural network (GNN), which predicts the time-averaged flow field of a rotor stage in an axial compressor based on its steady solution. Because GNNs are able to operate directly on the high-fidelity CFD mesh, we are able to retain the spatial resolution necessary to depict more complex flow behaviour. Consequently, the fidelity of our predictions can compete with conventional high-accuracy flow simulations. Our model is capable of predicting the velocity, pressure, density, and temperature field of a single rotor stage from a 4½-stage axial compressor test case and shows significant improvements compared to the steady state solution, while also being substantially faster than conventional unsteady CFD simulations.
Keywords
- Axial Compressors, Deep Learning, Machine Learning, Unsteady Flow
ASJC Scopus subject areas
- Engineering(all)
- General Engineering
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
Turbomachinery - Multidisciplinary Design Approaches, Optimization, and Uncertainty Quantification; Radial Turbomachinery Aerodynamics; Unsteady Flows in Turbomachinery. American Society of Mechanical Engineers(ASME), 2023. v13dt36a023 (Proceedings of the ASME Turbo Expo; Vol. 13D).
Research output: Chapter in book/report/conference proceeding › Conference contribution › Research › peer review
}
TY - GEN
T1 - A Machine Learning Approach for the Prediction of Time-Averaged Unsteady Flows in Turbomachinery
AU - Blechschmidt, Dominik
AU - Mimic, Dajan
N1 - Funding Information: We would like to acknowledge the funding by the Deutsche Forschungsgemeinschaft (DFG, German Research Foundation) under Germany’s Excellence Strategy EXC 2163/1 Sustainable and Energy Efficient Aviation Project ID 390881007. We also gratefully acknowledge the contribution of the DLR Institute of Propulsion Technology and MTU Aero Engines AG for providing TRACE. This work was supported by the Leibniz Universität Hannover IT Services (LUIS) compute cluster, which is funded by the Leibniz Universität Hannover, the Lower Saxony Ministry of Science and Culture (MWK) and the German Research Association (DFG).
PY - 2023
Y1 - 2023
N2 - Recent advances in deep learning have led to its increased application in the field of fluid dynamics. By using a data-driven approach instead of a more conventional numerical approach, it is possible to reduce the computational cost of fluid simulations significantly. Especially unsteady computational fluid dynamics (CFD) are known to require a considerable amount of time and resources. Hence, it is common practice in turbomachinery to model the flow as steady by averaging the flow between the rotor and stator in a so-called mixing plane. While this approach is numerically efficient, the full interactions between the rotor and the stator can no longer be predicted accurately due to the averaged upstream flow field. Contrary to this, the time-average of an actual unsteady flow does not contain such a modeling error while still resulting in a flow field that is decoupled from its temporal fluctuations. In this work, we introduce a graph neural network (GNN), which predicts the time-averaged flow field of a rotor stage in an axial compressor based on its steady solution. Because GNNs are able to operate directly on the high-fidelity CFD mesh, we are able to retain the spatial resolution necessary to depict more complex flow behaviour. Consequently, the fidelity of our predictions can compete with conventional high-accuracy flow simulations. Our model is capable of predicting the velocity, pressure, density, and temperature field of a single rotor stage from a 4½-stage axial compressor test case and shows significant improvements compared to the steady state solution, while also being substantially faster than conventional unsteady CFD simulations.
AB - Recent advances in deep learning have led to its increased application in the field of fluid dynamics. By using a data-driven approach instead of a more conventional numerical approach, it is possible to reduce the computational cost of fluid simulations significantly. Especially unsteady computational fluid dynamics (CFD) are known to require a considerable amount of time and resources. Hence, it is common practice in turbomachinery to model the flow as steady by averaging the flow between the rotor and stator in a so-called mixing plane. While this approach is numerically efficient, the full interactions between the rotor and the stator can no longer be predicted accurately due to the averaged upstream flow field. Contrary to this, the time-average of an actual unsteady flow does not contain such a modeling error while still resulting in a flow field that is decoupled from its temporal fluctuations. In this work, we introduce a graph neural network (GNN), which predicts the time-averaged flow field of a rotor stage in an axial compressor based on its steady solution. Because GNNs are able to operate directly on the high-fidelity CFD mesh, we are able to retain the spatial resolution necessary to depict more complex flow behaviour. Consequently, the fidelity of our predictions can compete with conventional high-accuracy flow simulations. Our model is capable of predicting the velocity, pressure, density, and temperature field of a single rotor stage from a 4½-stage axial compressor test case and shows significant improvements compared to the steady state solution, while also being substantially faster than conventional unsteady CFD simulations.
KW - Axial Compressors
KW - Deep Learning
KW - Machine Learning
KW - Unsteady Flow
UR - http://www.scopus.com/inward/record.url?scp=85177432510&partnerID=8YFLogxK
U2 - 10.1115/GT2023-103914
DO - 10.1115/GT2023-103914
M3 - Conference contribution
AN - SCOPUS:85177432510
T3 - Proceedings of the ASME Turbo Expo
BT - Turbomachinery - Multidisciplinary Design Approaches, Optimization, and Uncertainty Quantification; Radial Turbomachinery Aerodynamics; Unsteady Flows in Turbomachinery
PB - American Society of Mechanical Engineers(ASME)
T2 - ASME Turbo Expo 2023: Turbomachinery Technical Conference and Exposition, GT 2023
Y2 - 26 June 2023 through 30 June 2023
ER -