EUVIMEDEUVIMED entdecken
Crossref

Hybrid linear potential flow - machine learning model for enhanced prediction of WEC performance

Claes Eskilsson, Sepideh Pashami, Anders Holst, Johannes Palm

Proceedings of the European Wave and Tidal Energy Conference · 02.09.2023 · 15

DOI: 10.36688/ewtec-2023-321 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the European Wave and Tidal Energy Conference, online erschienen am 02.09.2023. Verfasst von Claes Eskilsson und 3 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Numerical models based on the linear potential flow equations are of paramount importance in the design of wave energy converters (WECs). Over the years methods such as wave stretching, nonlinear Froude-Krylov and Morrison drag have been developed to overcome the short-comings of the underlying assumptions of small amplitude wave, small motion and inviscous flow. In this work we present a different approach to enhance the performance of the linear method: a hybrid linear potential flow – machine learning (LPF-ML) model. A hierarchy of high-fidelity models – Reynolds-Averaged Navier-Stokes, Euler and fully nonlinear potential flow – is used to create training data for correction factors targeting nonlinear hydrodynamics, pressure drag and skin friction, respectively. Long short-term memory (LSTM) networks are then trained and added to the LPF model. LSTM networks are heavy to train but fast to evaluate so the computational efficiency of the LPF model is kept high. Simple decay tests of generic bodies (sphere, box, etc) are used to validate the LPF-ML model. Finally, the LPF-ML is applied to a model-scale point-absorber WEC to assess the power production.

Zitieren

APA

Eskilsson, C., Pashami, S., Holst, A., & Palm, J. (2023). Hybrid linear potential flow - machine learning model for enhanced prediction of WEC performance. Proceedings of the European Wave and Tidal Energy Conference, 15. https://doi.org/10.36688/ewtec-2023-321

Vancouver

Eskilsson C, Pashami S, Holst A, Palm J. Hybrid linear potential flow - machine learning model for enhanced prediction of WEC performance. Proceedings of the European Wave and Tidal Energy Conference. 2023;15. doi:10.36688/ewtec-2023-321

BibTeX
@article{Eskilsson2023,
  author = {Eskilsson, Claes and Pashami, Sepideh and Holst, Anders and Palm, Johannes},
  title = {Hybrid linear potential flow - machine learning model for enhanced prediction of WEC performance},
  journal = {Proceedings of the European Wave and Tidal Energy Conference},
  year = {2023},
  volume = {15},
  doi = {10.36688/ewtec-2023-321}
}
Kostenlos starten →