• Treffer 669 von 774
Zurück zur Trefferliste

Toward Data based corrosion analysis of concrete with supervised machine learning

  • Half-Cell-Potential Mapping (HP) is the most popular non-destructive testing (NDT) method for the detection of active corrosion in reinforced concrete. HP is influenced by parameters such as moisture and chloride gradients in the component. The sensitivity to the spatially small, but dangerous pitting is low. In this study we show how additional measurement information can be used with multi-sensor data fusion to improve the detection performance and to automate data evaluation. The fusion is based on supervised machine learning (SML). SML are methods that recognize relationships in (sensor) data based on given labels. We use SML to distinguish "defective" and "intact" labeled areas in our dataset. It consists of 18 measurement - each contains HP, ground radar, microwave moisture and Wenner resistivity data. Exact labels for changing environmental conditions were determined in a laboratory study on a reinforced concrete slab, which deteriorated controlled and accelerated. TheHalf-Cell-Potential Mapping (HP) is the most popular non-destructive testing (NDT) method for the detection of active corrosion in reinforced concrete. HP is influenced by parameters such as moisture and chloride gradients in the component. The sensitivity to the spatially small, but dangerous pitting is low. In this study we show how additional measurement information can be used with multi-sensor data fusion to improve the detection performance and to automate data evaluation. The fusion is based on supervised machine learning (SML). SML are methods that recognize relationships in (sensor) data based on given labels. We use SML to distinguish "defective" and "intact" labeled areas in our dataset. It consists of 18 measurement - each contains HP, ground radar, microwave moisture and Wenner resistivity data. Exact labels for changing environmental conditions were determined in a laboratory study on a reinforced concrete slab, which deteriorated controlled and accelerated. The deterioration progress was monitored continuously and corrosion was generated targeted at a predefined location. The detection results are quantified and statistically evaluated. The data fusion shows a significant improvement over the best single method (HP). We describe the challenges of data-driven approaches in nondestructive testing and show possible solutions.zeige mehrzeige weniger

Volltext Dateien herunterladen

  • SMT_NDTCE_Data_Fusion_final.pdf
    eng

Metadaten exportieren

Weitere Dienste

Teilen auf Twitter Suche bei Google Scholar Anzahl der Zugriffe auf dieses Dokument
Metadaten
Autor*innen:Christoph VölkerORCiD
Koautor*innen:Sabine KruschwitzORCiD, Gino EbellORCiD, J. Shen
Dokumenttyp:Vortrag
Veröffentlichungsform:Präsentation
Sprache:Englisch
Jahr der Erstveröffentlichung:2018
Organisationseinheit der BAM:8 Zerstörungsfreie Prüfung
8 Zerstörungsfreie Prüfung / 8.2 Zerstörungsfreie Prüfmethoden für das Bauwesen
DDC-Klassifikation:Naturwissenschaften und Mathematik / Chemie / Analytische Chemie
Freie Schlagwörter:NDT-CE; SMT
Themenfelder/Aktivitätsfelder der BAM:Chemie und Prozesstechnik
Veranstaltung:SMT/NDT-CE 2018
Veranstaltungsort:New Brunswick, NJ, USA
Beginndatum der Veranstaltung:26.08.2018
Enddatum der Veranstaltung:29.08.2018
Verfügbarkeit des Dokuments:Datei im Netzwerk der BAM verfügbar ("Closed Access")
Datum der Freischaltung:25.10.2018
Referierte Publikation:Nein
Eingeladener Vortrag:Nein
Einverstanden
Diese Webseite verwendet technisch erforderliche Session-Cookies. Durch die weitere Nutzung der Webseite stimmen Sie diesem zu. Unsere Datenschutzerklärung finden Sie hier.