Fine-grained fault diagnosis methods for offshore wind turbine gearboxes driven by artificial intelligence - by multi-source data analysis and deep learning
Aug 2026· EAI Endorsed Transactions on Energy Web· Vol 13· 0 citations· 26 references
Computer Science
TL;DR
The proposed method improves diagnostic accuracy, robustness, and engineering applicability for offshore wind turbine gearbox fault diagnosis.
Abstract
INTRODUCTION: Offshore wind turbine gearboxes operate under complex conditions and are highly prone to faults. Traditional single-source diagnostic methods are sensitive to noise and load fluctuations, limiting diagnostic reliability.
Objectives
This study aims to improve the diagnostic accuracy and recognition performance of gearbox fault categories.
Methods
Multi-source monitoring data were preprocessed and fused, followed by feature optimization and construction of a deep learning-based diagnosis model for fault detection and classification.
Results
The proposed model achieved accuracies of 0.951, 0.947, and 0.938 under different load conditions, with Area Under the Curve AUC values above 0.96, outperforming benchmark models.
Conclusion
The proposed method improves diagnostic accuracy, robustness, and engineering applicability for offshore wind turbine gearbox fault diagnosis.
Wind turbine blade failures, such as icing and damage, risk safety and efficiency, but limited fault data hinders diagnosis. This study proposes a hybrid framework combining ResNet50-SVM and transfer learning for small-sample fault diagnosis. A coupled simulation model first generates comprehensive dynamic fault data....
Tianyu Zhang, Nai-Chao Chen, Qiu-Jie Xu et al.· Wind Engineering : The Inter...· 0 citations
Gearbox faults are a major cause of downtime and maintenance costs in offshore wind turbines. This paper presents a gearbox fault identification method that combines multi-domain feature fusion with a hybrid ensemble learning framework. Time-domain statistical features and frequency-domain spectral features are extract...
Chunying Xu, Wei Wei, Zhan Lian et al.· International Conference on...· 0 citations
A method combining hierarchical deep dictionary learning (HDDL) with ConvNeXt is proposed, demonstrating that a recognition accuracy of 99.89% is achievable even with limited sample sizes, thereby effectively resolving the issue of low recognition rates caused by insufficient data.
Guohui Xu, Jianbin Cao, Wenyi Liu et al.· Proceedings of the Instituti...· 0 citations
Wind turbine blades, as critical components of modern wind power systems, are subjected to variable loads and harsh environmental conditions over extended periods, making them susceptible to surface contamination, leading-edge erosion, coating delamination, and other damage. Failure to detect these defects in a timely...
Jian-Wei Yang, Xin-Ye Ji, Chang Liu et al.· Engineering Research Express· 0 citations
Inspired by few-shot learning, a support–query task construction strategy is introduced, reformulating classification as conditional task reasoning and a global coverage and local balance task sampling strategy is designed to enhance task diversity and mitigate sample imbalance.
This study proposes an integrated condition-monitoring and predictive-maintenance framework for offshore wind turbines operating in harsh marine environments. To address the challenges of signal degradation, environmental interference, and limited fault-warning capability, a multi-source sensing architecture is develop...
Yanqing Ouyang, W. Liang· Advanced Electromagnetics· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
