eBiltegia

    • Euskara
    • Español
    • English
  • Contact Us
  • English 
    • Euskara
    • Español
    • English
  • About eBiltegia  
    • What is eBiltegia? 
    •   About eBiltegia
    •   Publish your research in open access
    • Open Access at MU 
    •   What is Open Science?
    •   Open Access institutional policy
    •   The Library compiles and disseminates your publications
  • Login
View Item 
  •   eBiltegia MONDRAGON UNIBERTSITATEA
  • Scientific production - Articles
  • Articles - Engineering
  • View Item
  •   eBiltegia MONDRAGON UNIBERTSITATEA
  • Scientific production - Articles
  • Articles - Engineering
  • View Item
JavaScript is disabled for your browser. Some features of this site may not work without it.
View/Open
Context-informed conditional anomaly detection approach for wave power plants The case of air turbines.pdf (7.364Mb)
Full record
Impact

Web of Science   

Google Scholar
Microsoft Academic
Share
Save the reference
Mendely
Title
Context-informed conditional anomaly detection approach for wave power plants: The case of air turbines
Author
Aizpurua Unanue, Jose Ignacio ccMondragon Unibertsitatea
Penalba, Markel ccMondragon Unibertsitatea
Kirillova, Natalia ccMondragon Unibertsitatea
Author (from another institution)
Lekube, Jon
Marina, Dorleta
Research Group
Teoría de la señal y comunicaciones
Mecánica de fluidos
Published Date
2022
Publisher
Elsevier
Keywords
Marine Renewable Energy monitoring
anomaly detection
Prognostics and health management
Turbine ... [+]
Marine Renewable Energy monitoring
anomaly detection
Prognostics and health management
Turbine
Power curve and monitoring [-]
Abstract
The reliability and energy production of wave power plants (WPPs) depend on sea-state conditions, operation efficiency and degradation of its constituent assets. Air turbines are key assets for the ef ... [+]
The reliability and energy production of wave power plants (WPPs) depend on sea-state conditions, operation efficiency and degradation of its constituent assets. Air turbines are key assets for the efficient and reliable operation of WPPs and ensuring their correct operation leads to enhance the efficiency of WPPs. However, the lack of run-to-failure data and scarce fault records hampers the development of predictive condition monitoring solutions. In this context, focusing on unsupervised health monitoring methods, this paper presents an air turbine conditional anomaly detection (CAD) approach with a practical case study tested and validated on the Mutriku wave power plant. In contrast to anomaly detection models, which model the health-state without taking into account the influence of the operating context, the proposed CAD approach learns the expected air turbine operation conditioned on specific sea-states information modelled through wave energy flux concepts. This is achieved through an ensemble of Gaussian Mixture models and the expectation–maximization algorithm. Results show that, the integration of sea-states in the anomaly detection learning process improves the discrimination capability of the CAD model compared with the anomaly detection model without sea-state information, reducing false positive events and improving the accuracy of the CAD model. [-]
URI
https://hdl.handle.net/20.500.11984/5828
Publisher’s version
https://doi.org/10.1016/j.oceaneng.2022.111196
ISSN
0029-8018
Published at
Ocean Engineering  Vol. 253. Artículo 111196. June, 2022
Document type
Article
Version
Postprint – Accepted Manuscript
Rights
© 2022 Elsevier
Access
Embargoed Access (until 2024-06-30)
Collections
  • Articles - Engineering [483]

Browse

All of eBiltegiaCommunities & CollectionsBy Issue DateAuthorsTitlesSubjectsResearch groupsPublished atThis CollectionBy Issue DateAuthorsTitlesSubjectsResearch groupsPublished at

My Account

LoginRegister

Statistics

View Usage Statistics

Harvested by:

OpenAIREBASE

Validated by:

OpenAIRERebiun
MONDRAGON UNIBERTSITATEA | Library
Contact Us | Send Feedback
DSpace
 

 

Harvested by:

OpenAIREBASE

Validated by:

OpenAIRERebiun
MONDRAGON UNIBERTSITATEA | Library
Contact Us | Send Feedback
DSpace