Wind turbine generator fault maintenance

What is a wind turbine generator failure analysis & fault diagnosis?

In this article, a comprehensive and up-to-date review of wind turbine generators failure analysis and fault diagnosis are presented. First, the electrical and mechanical failures of various WTG components, including stator, rotor, air gap, and bearings, are analyzed. Then, the fault characteristics and root causes of WTG are studied.

Which approach is best for wind turbine generator fault diagnosis?

Finally, the application of four categories of model-based, signal-based, knowledge-based and hybrid approaches to wind turbine generator fault diagnosis is summarized. The comprehensive review shows that the hybrid approach is now the leading and most accurate tool for real-time fault diagnosis for wind turbine generators.

What are the common faults of a wind turbine generator?

Common faults of wind turbine generator. Generator electrical faults are mainly stator eccentricity, rotor eccentricity, broken rotor bars, and looseness. The main manifestations of generator stator faults are overheating of stator windings, insulation damage, and grounding.

Why do we need a fault diagnosis for wind turbines?

The development of highly reliable and low-maintenance wind turbines is an urgent demand in order to achieve the low-carbon goals, and the arrival of fault diagnosis provides assurance for its satisfactory operation and maintenance.

How accurate is wind turbine generator RUL prediction and fault diagnosis?

This paper presents a solution for wind turbine generator RUL prediction and fault diagnosis, which has been adopted by two real-world wind power plants. The experimental study shows that, using the proposed method, wind turbine generator RUL can be predicted with about an 80% accuracy 18 days ahead.

What is the literature about wind turbine maintenance?

The literature related to WT maintenance is rich in complex attempts to anticipate failures, ranging from signal processing analyses to physical simulations and machine learning algorithms 17, 18. Researchers often neglect the scalability of solutions, likely due to a lack of large-scale datasets, including multiple wind farms and manufacturers.