A Model-Agnostic Meta-Baseline Method for Few-Shot Fault Diagnosis of Wind Turbines

• Published in: Sensors (Basel, Switzerland) Vol. 22; no. 9; p. 3288
• Main Authors: Liu, Xiaobo, Teng, Wei, Liu, Yibing
• Format: Journal Article
• Language: English
• Published: Switzerland MDPI AG 25.04.2022; MDPI
• Subjects: Air-turbines; Algorithms; Buildings and facilities; Classification; Deep learning; Fault diagnosis; few-shot learning; Methods; model-agnostic meta-learning; Monitoring systems; Neural networks; Signal processing; Turbines; Vibration; Wavelet transforms; Wind power; wind turbines; Working conditions; fault diagnosis; wind turbines; few-shot learning; model-agnostic meta-learning

The technology of fault diagnosis is helpful to improve the reliability of wind turbines, and further reduce the operation and maintenance cost at wind farms. However, in reality, wind turbines are not allowed to operate with faults, so few fault samples could be obtained. With a small amount of tra...