Abstract
Wind turbine component’s failure prognosis allows wind farm owners to apply predictive maintenance techniques to their fleets. This permits optimal scheduling of the maintenance actions considering the best time to stop the turbines and perform those actions. Determining the health status of a turbine’s component typically requires verifying a wide number of variables that should be monitored simultaneously. The scope of this study is the investigation and the selection of an effective combination of variables and smoothing and forecasting methodologies for obtaining a wind turbine gearbox health status indicator, in order to interpret clearly the remaining lifetime of the gearbox. The proposed methodology is based on Gaussian Mixture Copula Model (GMCM) models combined with the smoothing treatment and the forecasting model to define the health index of the wind turbine gearbox. Then, the resulting index is tested using various warning and critical thresholds. These thresholds should be chosen adequately in order to indicate appropriate inspection visit and preventive maintenance intervention date. Then, the best combination found, for the studied cases, was 50% and 70% for warning and critical respectively. This combination ensures that the developed procedure is capable of providing long enough time window for maintenance decision making.
Highlights
Wind energy is a mature technology capable nowadays of providing 15% of the EU’s electricity demand according to recent statistics [1]
The smoothed Failure Index (FI) resulting from the Gaussian Mixture Copula Model (GMCM) and the cubic spline smoothing techniques (CS) shows a growing trend starting at approximately 50% on September the 5th and reaching a value of 95% on November the 18th, the day when the failure occurred. 24 days prior to the gearbox failure occurrence, the FI reaches 60%
The FI enters in a special surveillance mode Monitoring the FI, an apparent increase in the index is observed between 26 October and 5 November, when the FI reaches 70%, which is illustrated via vertical dashed red line
Summary
Wind energy is a mature technology capable nowadays of providing 15% of the EU’s electricity demand according to recent statistics [1]. European wind turbine fleets are facing with serious Operations & Maintenance (O&M) problems as they are getting older [2]. O&M strategies for wind farms are always focused on keeping the turbines in operation as much as possible in order to provide the demanded electricity maximising the revenue. This results in seeking the most reliable and effective strategy for planning the different maintenance actions including corrective and preventive tasks. Current developments focus on preventive tasks resulting from scheduled activities and condition based interventions. Condition monitoring methodologies have been classified as a high
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
