Full load estimation of an offshore wind turbine based on SCADA and accelerometer data

Noppe, Nymfa; Iliopoulos, Alexandros; Weijtjens, Wout; Devriendt, Christof

doi:10.1088/1742-6596/753/7/072025

Cited by 21 publications

(29 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For offshore wind turbines with significant wave loading, e.g., large diameter monopiles, the effect of waves on the structure also needs to be included. A full load reconstruction can be performed by combining the proposed approach with acceleration measurements (Noppe et al, 2016).…”

Section: Future Workmentioning

confidence: 99%

See 1 more Smart Citation

Modeling of quasi-static thrust load of wind turbines based on 1 s SCADA data

2018

View full text Add to dashboard Cite

Offshore wind infrastructure lab (OWI-lab), Vrije Universiteit Brussel, Pleinlaan 2, 1050 Brussels, Belgium Abstract. A reliable load history is crucial for a fatigue assessment of wind turbines. However, installing strain sensors on every wind turbine is not economically feasible. In this paper, a technique is proposed to reconstruct the thrust load history of a wind turbine based on high-frequency Supervisory Control and Data Acquisition (SCADA) data. Strain measurements recorded during a short period of time are used to train a neural network. The selection of appropriate input parameters is performed based on Pearson correlation and mutual information. Once the training is done, the model can be used to predict the thrust load based on SCADA data only. The technique is validated on two different datasets, one consisting of simulation data (using the software FAST v8, created by Jonkman and Jonkman, 2016) obtained in a controllable environment and one consisting of measurements taken at an offshore wind turbine. In general, the relative error between simulated or measured and predicted thrust load barely exceeds 15 % during normal operation.

show abstract

Section: Future Workmentioning

confidence: 99%

“…Wind turbines installed on monopiles are more affected by waves than those installed on jacket substructures. An approach using SCADA data and accelerometers is proposed by Noppe et al (2016) to account for the higher-frequency loads as well. However, it was concluded an improvement of the quasi-static model was needed.…”

Section: Introductionmentioning

confidence: 99%

Modeling of quasi-static thrust load of wind turbines based on 1 s SCADA data

2018

View full text Add to dashboard Cite

show abstract

“…However, for OWTs wave loading and resonant behavior play a vital role in their fatigue life. As a consequence, techniques solely based on SCADA data are not suited for application on OWTs .…”

Section: Virtual Sensingmentioning

confidence: 99%

Fatigue assessment of offshore wind turbines on monopile foundations using multi‐band modal expansion

Iliopoulos¹,

Weijtjens

Hemelrijck³

et al. 2017

Wind Energy

View full text Add to dashboard Cite

Offshore wind turbines (OWTs) are subjected to both quasi-static loads originating from variations in the thrust force and dynamic loads linked to turbulence, waves and turbine dynamics. Both types of loads contribute to fatigue life progression and thus define the turbine's age. As a structural health monitoring solution, one could thus directly measure the stress history at fatigue critical locations. However, for OWTs on monopile foundations some fatigue critical locations are located below the seabed. Installing strain sensors at these hotspots is therefore impossible for existing wind turbines. This measurement restriction is overcome by reconstructing the full-field response of the structure based on the limited number of accelerometers and strain sensors (installed at a few easily accessible locations) and a calibrated finite element model of the system. The system model uses a multi-band modal expansion approach constituted of the quasi-static and dynamic contributions. These contributions are superimposed to reconstruct the stress history at all degrees of freedom of the finite element model, and the subsequent assess fatigue life consumption at all fatigue hot spots of the OWT. In this paper, the proposed virtual sensing technique is validated by predicting the stresses in the transition piece with 12 days of consecutive measurements from an operational OWT. The data set contains both variations in environmental and operating conditions as well as extreme events. Finally, a full-field strain assessment in the tower and foundation system of the OWT is demonstrated.

show abstract

“…design knowledge) and algorithms for dimensionality reduction and clustering. Several works exist that use data from the SCADA system for CM and SHM [1][2][3][4][5][6][7], fault-detection [8][9][10][11][12], and performance assessment [13,14]. Some of these applied signal processing techniques and learning algorithms such as Artificial Neural Networks (ANN).…”

Section: Introductionmentioning

confidence: 99%