Preprints
https://doi.org/10.5194/wes-2024-25
https://doi.org/10.5194/wes-2024-25
22 Mar 2024
 | 22 Mar 2024
Status: this preprint is currently under review for the journal WES.

Machine learning based virtual load sensors for mooring lines using motion and lidar measurements

Moritz Johann Gräfe, Vasilis Pettas, Nikolay Dimitrov, and Po Wen Cheng

Abstract. Floating offshore wind turbines are equipped with a diverse array of sensors, offering valuable data for turbine control and monitoring. However, reliable measurements can be elusive and costly for specific physical parameters, particularly load estimations for mooring lines and fairleads. This research delves into a methodology where floater motion measurements and wind speed measurements, derived from forward-looking nacelle-based lidar, are utilized as inputs for different types of neural networks to estimate fairlead tension time series and damage equivalent loads (DELs). Mooring line loads are intrinsically linked to the dynamics and the position of the floater. Therefore, we systematically analyze the individual contribution of floater dynamics on the prediction quality of fairlead tension time series and DELs. Wind speed measurements obtained via nacelle-based lidar on floating offshore wind turbines are influenced inherently by the platform's dynamics, notably the rotational pitch displacement and surge displacement of the floater. Consequently, the lidar wind speed data indirectly contains the dynamic behavior of the floater, which, in turn, governs the fairlead loads. This study directly leverages lidar-measured Line of Sight (LOS) wind speeds to estimate mooring line tensions. Training data for the model is generated by the aero-elastic wind turbine simulation tool, openFAST, in conjunction with the numerical lidar simulation framework ViConDAR. The fairlead tension time series are predicted using long-short-term-memory (LSTM) networks. DEL predictions are made using three different approaches. First, DELs are calculated from predicted time series; second, DELs are predicted using a sequence-to-one LSTM architecture, and third, DELs are predicted using a convolutional neural network architecture. Results indicate that fairlead tension time series and DELs can be accurately estimated from floater motion time series. Further, we found that lidar LOS measurements do not improve time series or DEL predictions if motion measurements are available. However, using lidar measurements as model inputs for DEL predictions leads to similar accuracies as using displacement measurements of the floater.

Moritz Johann Gräfe, Vasilis Pettas, Nikolay Dimitrov, and Po Wen Cheng

Status: open (until 03 May 2024)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
  • RC1: 'Comment on wes-2024-25', Anonymous Referee #1, 30 Mar 2024 reply
Moritz Johann Gräfe, Vasilis Pettas, Nikolay Dimitrov, and Po Wen Cheng
Moritz Johann Gräfe, Vasilis Pettas, Nikolay Dimitrov, and Po Wen Cheng

Viewed

Total article views: 211 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
166 37 8 211 9 4
  • HTML: 166
  • PDF: 37
  • XML: 8
  • Total: 211
  • BibTeX: 9
  • EndNote: 4
Views and downloads (calculated since 22 Mar 2024)
Cumulative views and downloads (calculated since 22 Mar 2024)

Viewed (geographical distribution)

Total article views: 192 (including HTML, PDF, and XML) Thereof 192 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 19 Apr 2024
Download
Short summary
This study explores a methodology using floater motion and nacelle-based lidar wind speed measurements to estimate the tension and damage equivalent loads (DELs) on floating offshore wind turbines' mooring lines. Results indicate that fairlead tension time series and DELs can be accurately estimated from floater motion time series. Using lidar measurements as model inputs for DEL predictions leads to similar accuracies as using displacement measurements of the floater.
Altmetrics