AI-Assisted thermographic and visual classification of leading-edge erosion of wind turbine blades

  • The wind industry is crucial for carbon neutrality, with turbines featuring blades over 100 meters long. Regular inspections, often manual and visual, struggle to capture subsurface damage or airflow dynamics. Leading-edge erosion, caused by rain and hail, significantly reduces turbine efficiency. The Federal Institute for Materials Research and Testing (BAM) in Berlin is working with industry partners to classify leading-edge damage and estimate yield loss using ground-based thermographic images. These images visualize airflow disruptions caused by erosion. AI models, trained on 1500 thermographic images, can detect and classify this damage. BAM aims to create a reference dataset by 2024, using data from 30 wind turbines. This dataset will include simultaneous thermographic and high-resolution visual images. The project also explores predicting stall and calculating performance loss due to erosion. A secure data platform facilitates data exchange and federated learning,The wind industry is crucial for carbon neutrality, with turbines featuring blades over 100 meters long. Regular inspections, often manual and visual, struggle to capture subsurface damage or airflow dynamics. Leading-edge erosion, caused by rain and hail, significantly reduces turbine efficiency. The Federal Institute for Materials Research and Testing (BAM) in Berlin is working with industry partners to classify leading-edge damage and estimate yield loss using ground-based thermographic images. These images visualize airflow disruptions caused by erosion. AI models, trained on 1500 thermographic images, can detect and classify this damage. BAM aims to create a reference dataset by 2024, using data from 30 wind turbines. This dataset will include simultaneous thermographic and high-resolution visual images. The project also explores predicting stall and calculating performance loss due to erosion. A secure data platform facilitates data exchange and federated learning, enhancing AI systems with diverse data.zeige mehrzeige weniger

Volltext Dateien herunterladen

  • NDE Outlook-June 2024 Materials Evaluation.pdf
    eng

Metadaten exportieren

Weitere Dienste

Suche bei Google Scholar Anzahl der Zugriffe auf dieses Dokument
Metadaten
Autor*innen:Michael StammORCiD
Dokumenttyp:Zeitschriftenartikel
Veröffentlichungsform:Verlagsliteratur
Sprache:Englisch
Titel des übergeordneten Werkes (Englisch):Materials Evaluation
Jahr der Erstveröffentlichung:2024
Organisationseinheit der BAM:8 Zerstörungsfreie Prüfung
8 Zerstörungsfreie Prüfung / 8.3 Thermografische Verfahren
Herausgeber (Institution):ASNT
Jahrgang/Band:82
Ausgabe/Heft:6
Erste Seite:14
Letzte Seite:15
DDC-Klassifikation:Technik, Medizin, angewandte Wissenschaften / Ingenieurwissenschaften / Angewandte Physik
Freie Schlagwörter:AI; KI-VISIR; NDT; Thermography; Wind Turbine Blades
Themenfelder/Aktivitätsfelder der BAM:Energie
Energie / Windenergie
URL:https://source.asnt.org/226h005/
ISSN:0025-5327
Verfügbarkeit des Dokuments:Datei im Netzwerk der BAM verfügbar ("Closed Access")
Datum der Freischaltung:27.01.2025
Referierte Publikation:Ja
Datum der Eintragung als referierte Publikation:27.01.2025
Einverstanden
Diese Webseite verwendet technisch erforderliche Session-Cookies. Durch die weitere Nutzung der Webseite stimmen Sie diesem zu. Unsere Datenschutzerklärung finden Sie hier.