EUVIMEDEUVIMED entdecken
Crossref

Multi-domain physics-informed neural networks for dynamic yaw-induced wind farm wake reconstruction

Bowen Zhang, Longyan Wang, Yanxia Fu, Zhaohui Luo, Jianping Yuan, Zilu Wang, Jian Xu

Proceedings of the Institution of Mechanical Engineers, Part A: Journal of Power and Energy · 26.07.2026

DOI: 10.1177/09576509261471989 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the Institution of Mechanical Engineers, Part A: Journal of Power and Energy, online erschienen am 26.07.2026. Verfasst von Bowen Zhang und 6 weiteren Autor:innen. Die Arbeit nennt 46 Literaturangaben. Gefördert von: China Postdoctoral Science Foundation, National Natural Science Foundation of China, Postdoctoral Science Foundation of Jiangsu Province.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Wind turbine wakes significantly influence wind farm performance, particularly under active yaw control used for wake redirection. Accurate wake reconstruction requires resolving the large spatial extent and multi-scale variability of wind-farm flows, making single-network training computationally demanding. A multi-domain formulation addresses this challenge by decomposing the global domain into smaller subregions, allowing localized learning while remaining compatible with sparse offshore measurements. Accordingly, a multi-domain physics-informed neural network (md-PINN) framework is developed for reconstructing unsteady wake fields of offshore wind turbines subjected to active yaw control. We begin by developing a standard PINN to reconstruct the wake behind a single wind turbine, incorporating Navier–Stokes constraints to enforce physical consistency. Building on this, a domain decomposition strategy is applied to divide the wind farm into multiple subdomains, each modeled using an independent PINN, thus forming the md-PINN framework. Validation against large eddy simulation (LES) data shows that the md-PINN framework accurately reconstructs velocity fields, wake trajectories, wake widths, and power outputs in downstream regions affected by complex wake interactions, while exhibiting improved robustness compared to a single full-domain PINN. In addition, the proposed framework naturally supports parallel training of sub-models, leading to a significant reduction in computational cost and enhanced scalability for sparse-data-based wake reconstruction in large wind farms.

Förderung

  • China Postdoctoral Science Foundation
  • National Natural Science Foundation of China
  • Postdoctoral Science Foundation of Jiangsu Province

Zitieren

APA

Zhang, B., Wang, L., Fu, Y., Luo, Z., Yuan, J., Wang, Z., & Xu, J. (2026). Multi-domain physics-informed neural networks for dynamic yaw-induced wind farm wake reconstruction. Proceedings of the Institution of Mechanical Engineers, Part A: Journal of Power and Energy. https://doi.org/10.1177/09576509261471989

Vancouver

Zhang B, Wang L, Fu Y, Luo Z, Yuan J, Wang Z, et al. Multi-domain physics-informed neural networks for dynamic yaw-induced wind farm wake reconstruction. Proceedings of the Institution of Mechanical Engineers, Part A: Journal of Power and Energy. 2026. doi:10.1177/09576509261471989

BibTeX
@article{Zhang2026,
  author = {Zhang, Bowen and Wang, Longyan and Fu, Yanxia and Luo, Zhaohui and Yuan, Jianping and Wang, Zilu and Xu, Jian},
  title = {Multi-domain physics-informed neural networks for dynamic yaw-induced wind farm wake reconstruction},
  journal = {Proceedings of the Institution of Mechanical Engineers, Part A: Journal of Power and Energy},
  year = {2026},
  doi = {10.1177/09576509261471989}
}
Kostenlos starten →