Nacelle lidar wind speed prediction under spatial-temporal correlation

Dandan Jiang; Zhixin Liu; Yiran Wang; Chunxiao Hao; Zuopeng Wang; Xing Chen

doi:10.1117/12.3030177

5 June 2024 Nacelle lidar wind speed prediction under spatial-temporal correlation

Dandan Jiang, Zhixin Liu, Yiran Wang, Chunxiao Hao, Zuopeng Wang, Xing Chen

Proceedings Volume 13163, Fourth International Conference on Mechanical, Electronics, and Electrical and Automation Control (METMS 2024); 131635E (2024) https://doi.org/10.1117/12.3030177
Event: International Conference on Mechanical, Electronics, and Electrical and Automation Control (METMS 2024), 2024, Xi'an, China

Abstract

In order to solve the problem of missing nacelle lidar measured wind speed data, a research study was conducted to predict the wind speed using the cabin lidar data as the primary data source. The study involved data preprocessing, where spatial features of wind speed at different distance layers and time series features were combined. A recurrent neural network model based on gated recurrent unit (GRU) was constructed for wind speed prediction. The predicted wind speed data were evaluated for accuracy. The experimental results showed that the proposed method achieved high prediction accuracy, with a correlation coefficient greater than 0.98, root mean square error below 0.85m/s, and average relative error less than 10%. This approach improved the effectiveness and completeness of the nacelle lidar wind speed data, providing valuable insights for the feedforward control and wake control of wind turbine units.

(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Dandan Jiang, Zhixin Liu, Yiran Wang, Chunxiao Hao, Zuopeng Wang, and Xing Chen "Nacelle lidar wind speed prediction under spatial-temporal correlation", Proc. SPIE 13163, Fourth International Conference on Mechanical, Electronics, and Electrical and Automation Control (METMS 2024), 131635E (5 June 2024); https://doi.org/10.1117/12.3030177

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available