.png){kind=icon}
.png){kind=icon}
Return
Structural Health Monitoring for Floating Offshore Wind Turbines Based on the Hilbert–Huang Transform and Random Forest Classification
.png){kind=icon}
PRE
AI
Y
Z
C
X
J
DOI：10.1109/joe.2026.3683216.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Floating offshore wind turbines (FOWTs) work in the deep sea, where severe environmental conditions threaten their structural safety. Structural health monitoring (SHM) is crucial for the safe operation of FOWTs. Currently, the SHM of FOWTs faces the problem of a lack of engineering data and effective methods. In this study, structural damage data are generated by fully coupled simulations of a FOWT to simulate blade damage and mooring line breakage. To handle nonlinear and oscillating FOWT blade acceleration and platform pitch motion, the Hilbert–Huang transform–based method is used to extract time-varying frequency domain features. Multiple random forest (RF) models are trained and tested for different types of SHM, i.e., monitoring for blade damage and mooring line breakage. The results indicate that the RF model to identify mooring line breakage by platform pitch angle presented the best accuracy. The pitch angle signal is better than the blade acceleration data for recognizing damage from the platform. The results indicate that the established method is effective for the SHM of FOWTs.
Keywords:
Blade structural damage
floating offshore wind turbine (FOWT)
Hilbert–Huang transform (HHT)
mooring line break
random forest (RF) classification
structural health monitoring (SHM)
Journal
IF:
5.3
Papers:
2.6K
Citations:
7.4K
Organization
Cited Papers