A Symmetry-Aware Pitch Feature Encoder–Decoder Network for Condition Monitoring of Pitch Bearings in Wind Turbines
- 3 March 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 25 (8) , 14379-14392
Abstract
Pitch bearing is one of the critical components of the electric pitch system in wind turbines, and its early and reliable fault warning is of great significance to ensure the operational reliability and safety of the entire system. In this paper, we develop a condition monitoring system for pitch bearing with available Supervisory Control Data Acquisition (SCADA) data. Motivated by the three-blade symmetrical structure of wind turbines, we propose a new symmetry-aware pitch feature encoder-decoder network named PitchNet. A group feature encoding strategy is first designed to extract intra-group variable-wise feature information. Then, a feature attention mechanism is applied to discover important inter-group features by dynamically assigning different weights to learned pitch representations. Finally, a feature decoder is used to reconstruct the pitch input features and derive the reconstruction residuals for early fault detection. The proposed PitchNet is evaluated using real cases of pitch bearing cracks. Results have demonstrated that the proposed PitchNet presents better early fault warning ability and lower false alarm rates, which can provide promising and reliable monitoring results for wind farm operators.Keywords
Funding Information
- National Natural Science Foundation of China (62273299)
- Hebei Province Science and Technology Support Program (216Z2101G)
This publication has 33 references indexed in Scilit:
- Towards more reliable photovoltaic energy conversion systems: A weakly-supervised learning perspective on anomaly detectionEnergy Conversion and Management, 2024
- Sensor-aware CapsNet: Towards trustworthy multisensory fusion for remaining useful life predictionJournal of Manufacturing Systems, 2023
- Challenges and opportunities for battery health estimation: Bridging laboratory research and real-world applicationsJournal of Energy Chemistry, 2023
- Fault diagnosis of wind turbine pitch system based on LSTM with multi-channel attention mechanismEnergy Reports, 2023
- Imbalanced learning for wind turbine blade icing detection via spatio-temporal attention model with a self-adaptive weight loss functionExpert Systems with Applications, 2023
- Memory-augmented skip-connected autoencoder for unsupervised anomaly detection of rocket engines with multi-source fusionISA Transactions, 2022
- Data annotation and feature extraction in fault detection in a wind turbine hydraulic pitch systemRenewable Energy, 2022
- WSFNet: An efficient wind speed forecasting model using channel attention-based densely connected convolutional neural networkEnergy, 2021
- Identifying early defects of wind turbine based on SCADA data and dynamical network markerRenewable Energy, 2020
- Reviewing resource criticality assessment from a dynamic and technology specific perspective – using the case of direct-drive wind turbinesJournal of Cleaner Production, 2016