2021
DOI: 10.1109/tpwrd.2020.2992796
|View full text |Cite
|
Sign up to set email alerts
|

Detection of Lightning Damage on Wind Turbine Blades Using the SCADA System

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
12
0

Year Published

2021
2021
2023
2023

Publication Types

Select...
6

Relationship

2
4

Authors

Journals

citations
Cited by 24 publications
(13 citation statements)
references
References 1 publication
0
12
0
Order By: Relevance
“…The features of the anomaly detection model are extracted from the SCADA data based on a previous study [5]. First, the wind speed and rotational speed at which the most noticeable anomaly appeared are extracted as basic features.…”
Section: Feature Extractormentioning
confidence: 99%
See 2 more Smart Citations
“…The features of the anomaly detection model are extracted from the SCADA data based on a previous study [5]. First, the wind speed and rotational speed at which the most noticeable anomaly appeared are extracted as basic features.…”
Section: Feature Extractormentioning
confidence: 99%
“…In this study, the simple moving average (SMA), weighted moving average (WMA), exponentially weighted moving average (EWMA), and sine weighted moving average (SWMA) are used. Each moving average is shown in (2) to (5). Note that x i denotes the i th data.…”
Section: Moving Average Of Wind Speed and Rotational Speedmentioning
confidence: 99%
See 1 more Smart Citation
“…It was clarified in previous research [17] that, if a wind turbine blade is damaged by a lightning strike, the outliers will occur frequently and continuously in wind speed rotational speed characteristic, wind speed power characteristic, and wind speed pitch degree characteristis of SCADA data. Based on this result, anomaly detection is performed using the wind speed rotational speed characteristic, which show the most outliers.…”
Section: Scada Data Of Wind Turbine At the Accident Due To Lightning Strikementioning
confidence: 99%
“…However, this method aims to predict failure due to deterioration over time from months to weeks in advance, and it is not applicable to sudden damage such as lightning damage. Therefore, our research group proposed the method that can immediately detect blade anomalies caused by a sudden event such as a lightning strike [17]. Accordingly, it is necessary to continue to consider the optimal anomaly detection model and effective features based on this result.…”
Section: Introductionmentioning
confidence: 99%