Building an Air Turbine Conditional Anomaly Detection Approachfor Wave Power Plants

  1. Jose Ignacio Aizpurua 1
  2. Markel Penalba 1
  3. Natalia Kirillova 1
  4. Illart Alcorta 1
  5. Jon Lekube 2
  6. Dorleta Marina 3
  1. 1 Universidad de Mondragón/Mondragon Unibertsitatea
    info

    Universidad de Mondragón/Mondragon Unibertsitatea

    Mondragón, España

    ROR https://ror.org/00wvqgd19

  2. 2 Ente Vasco de la Energía (EVE)
  3. 3 Biscay Marine Energy Platform
Mostrar afiliaciones +
Actas:
Annual Conference of the PHM Society 2021

Editorial: PHM Society

ISSN: 2325-0178

Año de publicación: 2021

Volumen: 13

Número: 1

Congreso: Proceedings of the Annual Conference of the PHM Society Vol. 13. N. 1, 2021

Tipo: Aportación congreso

DOI: 10.36001/PHMCONF.2021.V13I1.3028 GOOGLE SCHOLAR lock_openAcceso abierto editor

Resumen

The Mutriku Wave Power Plant (WPP) is a wave energy conversion plant based on the oscillating water column technology (OWC). The energy production and the health state of the plant are directly dependent on the sea-state conditions along with component-specific operation efficiency and failure modes. In this context, this paper presents a preliminary air turbine conditional anomaly detection (CAD) approach for condition monitoring of the Mutriku WPP. The proposed approach is developed based on an ensemble of Gaussian Mixture models, where each anomaly detection model learns the expected air turbine operation conditioned on specific seastates information. Early results show that the integration of sea-states in the anomaly detection learning process improves the discrimination capability of the anomaly detection model.