Wind power fault prediction method based on IGWO‑Seq2Seq

Authors

Chuqi XU, Trisun Petroleum Group Co., Ltd., Mudanjiang 157011, China
Chenhao SUN, School of Electrical & Information Engineering, Changsha University of Science &Technology, Changsha 410114, ChinaFollow
Mingyu ZHAN, School of Electrical & Information Engineering, Changsha University of Science &Technology, Changsha 410114, China
Gangtao ZHOU, School of Electrical & Information Engineering, Changsha University of Science &Technology, Changsha 410114, China
Ziwei LI, School of Electrical & Information Engineering, Changsha University of Science &Technology, Changsha 410114, China

Keywords

wind power fault prediction; grey wolf optimizer; encoder-decoder; attention mechanism; deep learning technology

Abstract

Wind turbines face various fault risks during operation, making precise fault diagnosis and prediction crucial for improving wind farm operation efficiency and ensuring system safety. Traditional fault diagnosis methods primarily rely on rule-based models or shallow machine learning algorithms, which often exhibit low accuracy and poor generalization ability when dealing with complex, nonlinear, and strongly time-dependent data. To address these challenges, this paper proposes an encoder-decoder (Seq2Seq) model based on an improved grey wolf optimizer (IGWO) for fault diagnosis and prediction of wind turbines. The model enhances the feature expression of key input moments through an attention mechanism and leverages IGWO to perform global optimization of hyperparameters, improving both prediction accuracy and generalization ability. Compared with traditional models, this approach demonstrates high efficiency and reliability in wind turbine fault prediction, providing technical support for the intelligent operation and maintenance of wind farms.

DOI

10.19781/j.issn.1673-9140.2024.06.021

First Page

203

Last Page

211

Recommended Citation

XU, Chuqi; SUN, Chenhao; ZHAN, Mingyu; ZHOU, Gangtao; and LI, Ziwei (2025) "Wind power fault prediction method based on IGWO‑Seq2Seq," Journal of Electric Power Science and Technology: Vol. 39: Iss. 6, Article 21.
DOI: 10.19781/j.issn.1673-9140.2024.06.021
Available at: https://jepst.researchcommons.org/journal/vol39/iss6/21