JZUS - Journal of Zhejiang University SCIENCE

Journal of Zhejiang University SCIENCE A

Accepted manuscript available online (unedited version)

Hierarchical learning method for array flow field prediction integrated with deep neural network

Author(s): Shanxun SUN¹, Zijiang XU¹, Zhuoheng WANG¹, Shuangshuang CUI², Ting HE¹, Yang CAI¹
Affiliation(s): ¹Energy and Electricity Research Center, Jinan University, Zhuhai 519070, China ²Guangdong-Hong Kong-Macao Greater Bay Area Meteorological Intelligent Equipment Research Center, Guangzhou 511430, China
Corresponding email(s): Ting HE, heting@jnu.edu.cn Yang CAI, thomascai301@163.com
Key Words: Hierarchical learning; Integrated neural network; Wind farms; Ultra-short-term wake prediction

Share this article to： More <<< Previous Paper \|Next Paper >>>

Shanxun SUN¹, Zijiang XU¹, Zhuoheng WANG¹, Shuangshuang CUI², Ting HE¹, Yang CAI¹. Hierarchical learning method for array flow field prediction integrated with deep neural network[J]. Journal of Zhejiang University Science A,in press.Frontiers of Information Technology & Electronic Engineering,in press.https://doi.org/10.1631/jzus.A2500344

@article{title="Hierarchical learning method for array flow field prediction integrated with deep neural network",
author="Shanxun SUN¹, Zijiang XU¹, Zhuoheng WANG¹, Shuangshuang CUI², Ting HE¹, Yang CAI¹",
journal="Journal of Zhejiang University Science A",
year="in press",
publisher="Zhejiang University Press & Springer",
doi="https://doi.org/10.1631/jzus.A2500344"
}

%0 Journal Article
%T Hierarchical learning method for array flow field prediction integrated with deep neural network
%A Shanxun SUN¹
%A Zijiang XU¹
%A Zhuoheng WANG¹
%A Shuangshuang CUI²
%A Ting HE¹
%A Yang CAI¹
%J Journal of Zhejiang University SCIENCE A
%P
%@ 1673-565X
%D in press
%I Zhejiang University Press & Springer
doi="https://doi.org/10.1631/jzus.A2500344"

TY - JOUR
T1 - Hierarchical learning method for array flow field prediction integrated with deep neural network
A1 - Shanxun SUN¹
A1 - Zijiang XU¹
A1 - Zhuoheng WANG¹
A1 - Shuangshuang CUI²
A1 - Ting HE¹
A1 - Yang CAI¹
J0 - Journal of Zhejiang University Science A
SP -
EP -
%@ 1673-565X
Y1 - in press
PB - Zhejiang University Press & Springer
ER -
doi="https://doi.org/10.1631/jzus.A2500344"

Abstract
Chinese Summary
Academic Network
Reviewer Comment

Abstract: Real-time and accurate dynamic wake information is essential for wind resource assessment and the optimization of wind farm operations. To further understand the wake characteristics of wind turbines, we propose a hierarchical learning approach integrated with a deep neural network-based prediction method. The integrated framework combines physical and mathematical models, enabling three-dimensional spatiotemporal wind field predictions with minimal measured data requirements. Evaluation and validation results demonstrate that the proposed method achieves accurate short-term wake predictions across the entire domain with minimal prediction errors. Compared with conventional methods, the proposed hierarchical learning framework markedly lowers the training-data requirements of physics-informed neural networks for large-scale flow-field prediction while maintaining high accuracy. In addition, it demonstrates superior performance in both local and global wake forecasts, offering practical insights for efficient turbine operation and wake analysis.

Darkslateblue:Affiliate; Royal Blue:Author; Turquoise:Article

Reference

Open peer comments: Debate/Discuss/Question/Opinion

<1>

- Go to

Darkslateblue:Affiliate; Royal Blue:Author; Turquoise:Article

Reference