Skip to main navigation Skip to search Skip to main content

Anomaly detection of a horizontal wind turbine using an extended kalman filter

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

3 Scopus citations

Abstract

Loads that have a disproportionate impact on the components and structure of a wind turbine can be induced by anomalies in the wind-field. For example, large unbalanced rotor loads could arise from blades sweeping through low level jets. The work presented in this paper proposes a novel anomaly detection scheme. Simulation results are presented demonstrating that it can be used to aid in the early detection of various anomalous conditions, such as mass imbalance, extreme wind shear and dynamic inflow, thereby allowing the wind turbine controllers to take appropriate diagnostic action to cope with such conditions.

Original languageEnglish
Title of host publicationEuropean Wind Energy Association Annual Conference and Exhibition 2015, EWEA 2015 - Scientific Proceedings
EditorsSandrine Aubrun, Sandrine Aubrun, Jakob Mann
PublisherEuropean Wind Energy Association
ISBN (Electronic)9782930670003
StatePublished - 2015
EventEuropean Wind Energy Association Annual Conference and Exhibition 2015, EWEA 2015 - Paris, France
Duration: 17 Nov 201520 Nov 2015

Publication series

NameEuropean Wind Energy Association Annual Conference and Exhibition 2015, EWEA 2015 - Scientific Proceedings

Conference

ConferenceEuropean Wind Energy Association Annual Conference and Exhibition 2015, EWEA 2015
Country/TerritoryFrance
CityParis
Period17/11/1520/11/15

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

  1. SDG 7 - Affordable and Clean Energy
    SDG 7 Affordable and Clean Energy

Keywords

  • Anomaly detection
  • Extended Kalman filter
  • Wind turbine control
  • Wind turbine monitoring

Fingerprint

Dive into the research topics of 'Anomaly detection of a horizontal wind turbine using an extended kalman filter'. Together they form a unique fingerprint.

Cite this