Current-Based Fault Detection for Wind Turbine Systems via Hilbert-Huang Transform

Authors

Dingguo Lu, University of Nebraska-LincolnFollow
Wei Qiao, University of Nebraska-LincolnFollow
Xiang Gong, University of Nebraska–LincolnFollow
Liyan Qu, University of Nebraska-LincolnFollow

Date of this Version

2013

Citation

D. Lu, W. Qiao, X. Gong, and L. Qu, “Current-based fault detection for wind turbine systems via Hilbert-Huang transform,” in Proceedings of IEEE PES General Meeting 2013 (PES 2013), Vancouver, British Columbia, Canada, July 21-25, 2013, pp. 1-5

Comments

© 2013 IEEE

Abstract

Mechanical failures of wind turbines represent a significant cost in both repairs and downtime. Detecting incipient faults of wind turbine components permits maintenance to be scheduled and failed parts to be repaired or replaced before causing failures of other components or catastrophic failure of the system. This paper proposes a Hilbert-Huang transform (HHT)-based algorithm to effectively extract fault signatures in generator current signals for wind turbine fault diagnosis by using the HHT’s capability of accurately representing the instantaneous amplitude and frequency of nonlinear and nonstationary signals. A phase-lock-loop (PLL) method is integrated to estimate wind turbine rotating speed, which is then used to facilitate the fault detection. The proposed method is validated by a real direct-drive wind turbine with different types of faults. The experimental results demonstrate that the proposed method is effective to detect various faults in wind turbine systems as well as to reveal the severities of the faults.