2020
DOI: 10.3390/app10238649
|View full text |Cite
|
Sign up to set email alerts
|

Wind Fleet Generator Fault Detection via SCADA Alarms and Autoencoders

Abstract: A hybrid health monitoring system for wind turbine generators is introduced. The novelty of this research consists in approaching a 115-wind turbine fleet by using the fusion of multiple sources of information. Analog SCADA data is analyzed through an autoencoder which allows to identify anomalous patterns within the input variables. Alarm logs are processed and merged to the anomaly detection output, creating a reliable health estimator of generator conditions. The proposed methodology has been tested on a fl… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

1
19
0

Year Published

2021
2021
2024
2024

Publication Types

Select...
6
2

Relationship

1
7

Authors

Journals

citations
Cited by 19 publications
(20 citation statements)
references
References 23 publications
1
19
0
Order By: Relevance
“…The use of fleet information is not new, e.g. Beretta et al, (2020), Hendrickx et al (2020). The latter is most similar to our work.…”
Section: Gcwt Olse)supporting
confidence: 77%
See 1 more Smart Citation
“…The use of fleet information is not new, e.g. Beretta et al, (2020), Hendrickx et al (2020). The latter is most similar to our work.…”
Section: Gcwt Olse)supporting
confidence: 77%
“…This has great advantages when the amount of healthy data is limited. Beretta, Cárdenas, Koch and Cusidó (2020) detect generator faults using a combination of an autoencoder and alarm log data of several fleets of wind turbines. They find that combining the two methods increases the performance drastically.…”
Section: Related Workmentioning
confidence: 99%
“…Where * defines element-wise multiplication between vectors, the information flow from the present cell state c t is controlled by the output gate O t to the current output, described by (15).…”
Section: B: Xgboost Regression Model and Hyperparameter Optimizationmentioning
confidence: 99%
“…The sensors forming the SCADA system are in the main components of the wind turbine; the data is usually sampled at a frequency of 10-min. This sampling interval makes it easy for data transfer and storage in a database for ultimate retrieval [15]. SCADA Systems on a WT typically record wind parameters like wind speed and wind deviations; performance parameters like power output, rotor speed, blade pitch angle; vibration parameters like tower acceleration and drive train acceleration; temperature parameters like bearing temperature and gearbox temperature.…”
Section: Introductionmentioning
confidence: 99%
“…This goal can, e.g., be pursued by physical models [31] or neural networks [32]. Alternative approaches based on anomaly detection and fusion of multiple indicators and alarm logs, addressing generator and main bearing failures, have been proposed in [33,34]. When located in a wind farm, also adjacent turbines can serve as a reference value [31].…”
Section: Previous Workmentioning
confidence: 99%