Hard sample mining-enabled supervised contrastive feature learning for wind turbine pitch system fault diagnosis
Open Access
- 14 August 2024
- journal article
- research article
- Published by IOP Publishing in Measurement Science and Technology
- Vol. 35 (11) , 116203
Abstract
The presence of multiple failure severities in the wind turbine pitch system due to the long-term wear and tear poses challenges in accurately classifying the system’s health condition, thus increasing maintenance costs or damage risks. This paper proposes a novel method based on hard sample mining (HSM)-enabled supervised contrastive learning to address this problem. The proposed method leverages the powerful feature extraction capabilities of supervised contrastive learning to extract discriminative features from highly imbalanced data. Additionally, the method incorporates a cosine similarity-based HSM framework that constructs hard sample pairs within mini-batches during both the representation learning and classifier training phases, thereby improving the diagnostic performance of the model for hard samples. The proposed method achieves macro G-mean of 0.9991 and 0.9971 on two real datasets containing data on wind turbine pitch system cog belt fractures. These results indicate significantly superior fault diagnosis performance compared to existing methods, highlighting its potential for enhancing the reliability and efficiency of fault diagnosis in wind turbine pitch systems.Keywords
All Related Versions
Funding Information
- National Natural Science Foundation of China (62276230)
This publication has 24 references indexed in Scilit:
- Fault Diagnosis of Wind Turbine Bearings Based on CNN and SSA–ELMJournal of Vibration Engineering & Technologies, 2022
- Data annotation and feature extraction in fault detection in a wind turbine hydraulic pitch systemRenewable Energy, 2022
- Fault detection and diagnosis of a blade pitch system in a floating wind turbine based on Kalman filters and artificial neural networksRenewable Energy, 2021
- Deep learning algorithms for rotating machinery intelligent diagnosis: An open source benchmark studyISA Transactions, 2020
- G-mean based extreme learning machine for imbalance learningDigital Signal Processing, 2020
- Distance learning by mining hard and easy negative samples for person re-identificationPattern Recognition, 2019
- Model-based fault detection, fault isolation and fault-tolerant control of a blade pitch system in floating wind turbinesRenewable Energy, 2018
- Fault-tolerant wind turbine pitch control using adaptive sliding mode estimationRenewable Energy, 2018
- Fault analysis of wind turbines in ChinaRenewable and Sustainable Energy Reviews, 2016
- Wind turbine reliability analysisRenewable and Sustainable Energy Reviews, 2013