Details
Original language | English |
---|---|
Title of host publication | Proceedings of the ASME 2022 41st International Conference on Ocean, Offshore and Arctic Engineering |
Subtitle of host publication | Ocean Renewable Energy |
Number of pages | 10 |
Volume | Volume 8 |
ISBN (electronic) | 9780791885932 |
Publication status | Published - 13 Oct 2022 |
Abstract
The dynamic responses analysis of floating offshore wind turbines (FOWTs) is very complex, which involves very strong nonlinear and coupling effects. This has also led to the current engineering application of FOWTs still facing critical gaps, especially in innovative design and dynamic performances prediction. Both academia and the wind industry are constantly exploring breakthroughs in terms of design and maintenance for FOWTs. The purpose of this paper is to apply a novel method, named SADA, which combines AI technology with numerical analysis methods, on full-scale measured data to optimize the platform motion prediction of the Hywind FOWT. The full-scale data used in this paper was collected by one of Hywind FOWTs in Scotland. The results show that the AI-Trained numerical model can predict the motions of Hywind supporting floater with higher accuracy. The tension of the fairlead has undergone a huge change although the deformation of the blades and the tower has been reduced. In addition, compared with the deformation of the tower and the blades, the changes in the mooring system are the most significant. In summary, the SADA method can bring an innovative vision for FOWTs full-scale measurement technology in the future.
Keywords
- DARwind, Hywind, SADA, floating offshore wind turbine, full-scale measurement
ASJC Scopus subject areas
- Engineering(all)
- Ocean Engineering
- Energy(all)
- Energy Engineering and Power Technology
- Engineering(all)
- Mechanical Engineering
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
Proceedings of the ASME 2022 41st International Conference on Ocean, Offshore and Arctic Engineering: Ocean Renewable Energy. Vol. Volume 8 2022. V008T09A042.
Research output: Chapter in book/report/conference proceeding › Conference contribution › Research › peer review
}
TY - GEN
T1 - Transferability of Meta-Model Configurations for Different Wind Turbine Types
AU - Müller, Franziska
AU - Hübler, Clemens
AU - Rolfes, Raimund
N1 - Funding Information: We gratefully acknowldege the financial support of the German Federal Ministry for Economic Affairs and Energy (research
PY - 2022/10/13
Y1 - 2022/10/13
N2 - The dynamic responses analysis of floating offshore wind turbines (FOWTs) is very complex, which involves very strong nonlinear and coupling effects. This has also led to the current engineering application of FOWTs still facing critical gaps, especially in innovative design and dynamic performances prediction. Both academia and the wind industry are constantly exploring breakthroughs in terms of design and maintenance for FOWTs. The purpose of this paper is to apply a novel method, named SADA, which combines AI technology with numerical analysis methods, on full-scale measured data to optimize the platform motion prediction of the Hywind FOWT. The full-scale data used in this paper was collected by one of Hywind FOWTs in Scotland. The results show that the AI-Trained numerical model can predict the motions of Hywind supporting floater with higher accuracy. The tension of the fairlead has undergone a huge change although the deformation of the blades and the tower has been reduced. In addition, compared with the deformation of the tower and the blades, the changes in the mooring system are the most significant. In summary, the SADA method can bring an innovative vision for FOWTs full-scale measurement technology in the future.
AB - The dynamic responses analysis of floating offshore wind turbines (FOWTs) is very complex, which involves very strong nonlinear and coupling effects. This has also led to the current engineering application of FOWTs still facing critical gaps, especially in innovative design and dynamic performances prediction. Both academia and the wind industry are constantly exploring breakthroughs in terms of design and maintenance for FOWTs. The purpose of this paper is to apply a novel method, named SADA, which combines AI technology with numerical analysis methods, on full-scale measured data to optimize the platform motion prediction of the Hywind FOWT. The full-scale data used in this paper was collected by one of Hywind FOWTs in Scotland. The results show that the AI-Trained numerical model can predict the motions of Hywind supporting floater with higher accuracy. The tension of the fairlead has undergone a huge change although the deformation of the blades and the tower has been reduced. In addition, compared with the deformation of the tower and the blades, the changes in the mooring system are the most significant. In summary, the SADA method can bring an innovative vision for FOWTs full-scale measurement technology in the future.
KW - DARwind
KW - Hywind
KW - SADA
KW - floating offshore wind turbine
KW - full-scale measurement
UR - http://www.scopus.com/inward/record.url?scp=85140839885&partnerID=8YFLogxK
U2 - 10.1115/OMAE2022-79698
DO - 10.1115/OMAE2022-79698
M3 - Conference contribution
SN - 978-0-7918-8593-2
VL - Volume 8
BT - Proceedings of the ASME 2022 41st International Conference on Ocean, Offshore and Arctic Engineering
ER -