A Novel Approach to Wind Turbine Blade Icing Detection With Limited Sensor Data via Spatiotemporal Attention Siamese Network

This article focuses on data-driven approaches for icing detection (ID) on wind turbine blades. In light of the widespread application of sensor technologies in wind turbines, such data-driven ID methods have become increasingly prominent. However, current methods have deficiencies, particularly in...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on industrial informatics 2024-06, Vol.20 (6), p.8993-9005
Main Authors: Wang, Lei, He, Yigang, Zhou, Yazhong, Li, Lie, Wang, Jing, Zhao, Yingying, Du, Bolun
Format: Article
Language:English
Subjects:
Artificial neural networks
Blades
Bridge failure
Correlation
Data models
Feature extraction
Few-shot learning (FSL)
graph attention network (GAT)
icing detection (ID)
Multivariate analysis
Sensors
Siamese network (SN)
Spatiotemporal phenomena
Supervisory control and data acquisition
Task analysis
Turbine blades
wind turbine blade
Wind turbines
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This article focuses on data-driven approaches for icing detection (ID) on wind turbine blades. In light of the widespread application of sensor technologies in wind turbines, such data-driven ID methods have become increasingly prominent. However, current methods have deficiencies, particularly in acknowledging the structural properties of multivariate sensor data and in differentiating icing stages, both critical for the identification of failure patterns. To bridge these gaps, we propose a spatiotemporal attention Siamese network (SN) for blade ID. This model employs a Siamese network architecture for efficient few-shot learning amidst class imbalance. It uniquely incorporates a graph attention network and gated recurrent unit for extracting spatiotemporal features from sensor data. This design not only acknowledges the spatial structure of the data but also distinctly identifies features pertinent to various icing stages. The efficacy of STASN was validated using actual sensor data from supervisory control and data acquisition systems. The results demonstrate SN's capability in discerning distinct icing stage features and its potential in early icing prediction. This research underscores SN's utility in providing advanced, flexible fault alarms for blade icing, representing a significant stride in wind turbine maintenance and safety.
ISSN:1551-3203
1941-0050
DOI:10.1109/TII.2024.3378775