the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
Overview of normal behavior modeling approaches for SCADA-based wind turbine condition monitoring demonstrated ondata from operational wind farms
Xavier Chesterman
Timothy Verstraeten
Pieter-Jan Daems
Ann Nowé
Jan Helsen
Abstract. Condition monitoring and failure prediction for wind turbines is currently a hot research topic. This follows from the fact that investments in the wind energy sector have increased dramatically due to the transition to renewable energy production. This paper reviews and implements several techniques from state-of-the-art research on condition monitoring for wind turbines using SCADA data and the Normal Behavior Modelling framework. The first part of the paper consists of an in-depth overview of 5 the current state-of-the-art. In the second part, several techniques from the overview are implemented and compared using data (SCADA and failure data) from five operational wind farms. To this end, 6 demonstration experiments are designed. The first 5 experiments test different techniques for the modeling of the normal behavior. The sixth experiment compares several techniques that can be used for identifying anomalous patterns in the prediction error. The paper concludes with several directions for future work.
Xavier Chesterman et al.
Status: final response (author comments only)
-
RC1: 'Comment on wes-2022-120', Anonymous Referee #1, 09 Mar 2023
This is an interesting paper on an important topic. It is well written. I have some critcal comments listed below.
The literature review is reasonable but not complete. Useful research has been published on the application of Copula models and also Gaussian Process models in wind turbine normal behaviour modeling. These should be included in the review.
I'm not clear why the data filtering reduced the normall 10 minute data to hourly. Better results may have been obtained using the 10 minute data directly (after error and gap removal). If noise reduction was the main reason this should be demonstrated statistically.
The mathematics of the modelling and error prediction should be presented in more detail. The terms in equation 2 should be explained.
Cooling transients are a major cause of modelling difficulty. However they do not represent an operational turbine and I'm surprised such data was not excluded from the analysis by using status or power data from the SCADA,
Citation: https://doi.org/10.5194/wes-2022-120-RC1 - RC2: 'Comment on wes-2022-120', Anonymous Referee #2, 10 Mar 2023
Xavier Chesterman et al.
Xavier Chesterman et al.
Viewed
HTML | XML | Total | BibTeX | EndNote | |
---|---|---|---|---|---|
154 | 70 | 9 | 233 | 3 | 3 |
- HTML: 154
- PDF: 70
- XML: 9
- Total: 233
- BibTeX: 3
- EndNote: 3
Viewed (geographical distribution)
Country | # | Views | % |
---|
Total: | 0 |
HTML: | 0 |
PDF: | 0 |
XML: | 0 |
- 1