2020
DOI: 10.3390/app10196972
|View full text |Cite
|
Sign up to set email alerts
|

Damage Diagnosis for Offshore Wind Turbine Foundations Based on the Fractal Dimension

Abstract: Cost-competitiveness of offshore wind depends heavily in its capacity to switch preventive maintenance to condition-based maintenance. That is, to monitor the actual condition of the wind turbine (WT) to decide when and which maintenance needs to be done. In particular, structural health monitoring (SHM) to monitor the foundation (support structure) condition is of utmost importance in offshore-fixed wind turbines. In this work a SHM strategy is presented to monitor online and during service a WT offshore jack… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
2
1

Citation Types

0
14
2

Year Published

2021
2021
2023
2023

Publication Types

Select...
7
1

Relationship

3
5

Authors

Journals

citations
Cited by 15 publications
(16 citation statements)
references
References 36 publications
0
14
2
Order By: Relevance
“…On the left side of the figure, it can be seen that the model is overfitting since the validation loss is higher than the training loss. On the other hand, on the right side of the figure the confusion matrix is observed where it is evident that this model is not capable of Finally, to comprehensively verify the algorithm's functional properties, a comparison is done with four additional techniques that use the identical laboratory setup ( 19), ( 15), (35), and (16). The first method is based on principal component analysis and support vector machines, as described in (19).…”
Section: Resultsmentioning
confidence: 99%
“…On the left side of the figure, it can be seen that the model is overfitting since the validation loss is higher than the training loss. On the other hand, on the right side of the figure the confusion matrix is observed where it is evident that this model is not capable of Finally, to comprehensively verify the algorithm's functional properties, a comparison is done with four additional techniques that use the identical laboratory setup ( 19), ( 15), (35), and (16). The first method is based on principal component analysis and support vector machines, as described in (19).…”
Section: Resultsmentioning
confidence: 99%
“…Vidal et al [ 7 ] used a combination of PCA and quadratic SVM for damage classification of the same structure and the same types of damage. The same benchmark structure was considered in [ 13 , 14 ], but with different types of damage. The overall performance of these approaches is excellent.…”
Section: Resultsmentioning
confidence: 99%
“…The CNN comprises seven convolutional layers performing feature extraction, followed by three fully connected layers and a SoftMax block for classification; an overall accuracy of is obtained. Hoxha et al [ 14 ] solved the identification and classification damage problem in an experimental laboratory wind-turbine offshore jacket-type foundation through a fractal dimension methodology that performs feature extraction in a machine learning (ML) setting. k NN, quadratic SVM, and Gaussian SVM were used as classifiers.…”
Section: Introductionmentioning
confidence: 99%
“…The operation efficiency of wind turbines is affected by defects that exist on the surface of blades. Defect detection systems based on ML and DL methods have been utilised to inspect the regular operation of WTBs damage diagnosis [ 41 , 42 ] and condition monitoring [ 43 , 44 , 45 ]. Future work includes extending the proposed pipeline for the task of condition monitoring.…”
Section: Discussionmentioning
confidence: 99%