Prediction of Inflow Wind Field for Large-scale Wind Turbines Based on Multimodal Hybrid Deep Learning

Authors

Jiheng Wang, State Key Laboratory of Alternate Electrical Power System with Renewable Energy Sources, North China Electric Power University, Beijing 102206, China; School of Control and Computer Engineering, North China Electric Power University, Beijing 102206, China
Yang Hu, State Key Laboratory of Alternate Electrical Power System with Renewable Energy Sources, North China Electric Power University, Beijing 102206, China; School of Control and Computer Engineering, North China Electric Power University, Beijing 102206, China
Ziqiu Song, State Key Laboratory of Alternate Electrical Power System with Renewable Energy Sources, North China Electric Power University, Beijing 102206, China; School of Control and Computer Engineering, North China Electric Power University, Beijing 102206, China
Fang Fang, State Key Laboratory of Alternate Electrical Power System with Renewable Energy Sources, North China Electric Power University, Beijing 102206, China; School of Control and Computer Engineering, North China Electric Power University, Beijing 102206, China
Jizhen Liu, State Key Laboratory of Alternate Electrical Power System with Renewable Energy Sources, North China Electric Power University, Beijing 102206, China; School of Control and Computer Engineering, North China Electric Power University, Beijing 102206, China

Abstract

Abstract: To address the demand for high-precision inflow wind field prediction in large-scale wind turbines, traditional CFD methods suffer from high computational costs and poor real-time applicability. This paper proposed a multimodal hybrid deep learning-based wind field prediction method. The proposed method took turbine operating parameters and far-range wind field images as inputs and generated short-range wind field images as outputs. By employing a U-Net-Transformer-GAN hybrid architecture, the model achieved multi-scale feature extraction, temporal dependency modeling, and highresolution wind field image generation. The vorticity transport equation and Kármán-Howarth turbulence statistics were incorporated as weak constraints to enhance physical consistency, while a temporal delay-difference mechanism was introduced to mitigate input and output asynchrony. Experimental results demonstrate that the proposed method outperforms comparative models, with PSNR of 32.51 dB, SSIM of 0.894, and LPIPS of 0.025. It accurately reproduces the Kolmogorov-5/3 power law in the turbulent energy spectrum, achieving a roughly 20-fold increase in predictive efficiency over traditional large eddy simulation.

Recommended Citation

Wang, Jiheng; Hu, Yang; Song, Ziqiu; Fang, Fang; and Liu, Jizhen (2026) "Prediction of Inflow Wind Field for Large-scale Wind Turbines Based on Multimodal Hybrid Deep Learning," Journal of System Simulation: Vol. 38: Iss. 2, Article 19.
DOI: 10.16182/j.issn1004731x.joss.25-0707
Available at: https://dc-china-simulation.researchcommons.org/journal/vol38/iss2/19

First Page

501

Last Page

517

CLC

TP391.9

Recommended Citation

Wang Jiheng, Hu Yang, Song Ziqiu, et al. Prediction of Inflow Wind Field for Large-scale Wind Turbines Based on Multimodal Hybrid Deep Learning[J]. Journal of System Simulation, 2026, 38(2): 501-517.

Corresponding Author

Hu Yang

DOI

10.16182/j.issn1004731x.joss.25-0707