Behavior Anomaly Indicators Based on Reference Patterns—Application to the Gearbox and Electrical Generator of a Wind Turbine

Angel Gil, Miguel A. Sanz-Bobi and Miguel A. Rodríguez-López
Additional contact information
Angel Gil: Institute for Research in Technology and Telematics and Computer Science Department, Comillas Pontifical University, 28015 Madrid, Spain
Miguel A. Sanz-Bobi: Institute for Research in Technology and Telematics and Computer Science Department, Comillas Pontifical University, 28015 Madrid, Spain
Miguel A. Rodríguez-López: Acciona Energía S.A., 31621 Sarriguren, Navarra, Spain

Energies, 2018, vol. 11, issue 1, 1-15

Abstract: This paper presents indicators of non-expected behavior in components of a wind turbine. These indicators are used to alert about the working conditions of these components that are not usual, according to the normal behavior observed for similar conditions of wind speed and power generated. In order to obtain these indicators, reference patterns of behavior for the components studied were defined. The patterns were obtained from real data of the wind turbine covering all of the possible working conditions. The technique of self-organized maps was used for discovering such reference patterns. Once they were obtained, new data, not included in the training set, was passed through the patterns in order to verify if the behavior observed corresponds or not to that expected. If they do not coincide, an anomaly of behavior is detected than can be useful for soon alert of possible failure mode or at least to know that the component was under working conditions that could cause risk of fault. The periods of unexpected behavior are the base for the indicators proposed in this paper. Real cases to show the elaboration of the indicators, and their corresponding results are provided.

Keywords: anomaly detection; pattern discovering; self-organized maps; wind turbine; normal behavior characterization (search for similar items in EconPapers)
JEL-codes: Q Q0 Q4 Q40 Q41 Q42 Q43 Q47 Q48 Q49 (search for similar items in EconPapers)
Date: 2018
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (6)

Downloads: (external link)
https://www.mdpi.com/1996-1073/11/1/87/pdf (application/pdf)
https://www.mdpi.com/1996-1073/11/1/87/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jeners:v:11:y:2018:i:1:p:87-:d:125048

Access Statistics for this article

Energies is currently edited by Ms. Agatha Cao

More articles in Energies from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().