Simulated Acceleration Data for Floating Wind Turbine Mooring Damage Detection

Encompassing simulated acceleration data representing healthy and damaged chain or synthetic mooring lines for Floating Offshore Wind Turbines. It was generated within the AIMWind project to validate machine learning methods for damage detection. The data is associated with research on end-of-life decisions for wind farms.

Use Cases

• Validate machine learning models for damage detection in chain and synthetic mooring lines using simulated acceleration signals.
• Train classifiers to distinguish between healthy and damaged states of floating offshore wind turbine mooring systems.
• Analyze acceleration patterns specific to chain and synthetic mooring line materials for structural health monitoring.

Strengths

• Data is simulated for a controlled validation of damage detection methods, allowing for precise scenario testing.
• Generated within the context of the AIMWind project, which focuses on big data analytics for wind farm asset integrity management.
• Targets a specific and critical engineering application: damage detection in floating offshore wind turbine mooring lines.

Limitations

• Data is simulated rather than measured from physical systems, which may not capture all real-world noise and variability.
• The specific volume (rows), features (columns), and file formats of the data are unknown.
• The temporal and geographic coverage of the underlying simulation scenarios is not specified.

Provenance

Source

Author: Sakaris, Christos; Organization: DataverseNO Harvested Dataverse.

Collection Method

Simulated data generated for the AIMWind project.

Freshness

Last updated on 2026-02-22.