Bitte benutzen Sie diese Referenz, um auf diese Ressource zu verweisen: doi:10.22028/D291-39416
Titel: Learned Anomaly Detection with Terahertz Radiation in Inline Process Monitoring
VerfasserIn: Meiser, Clemens
Wald, Anne
Schuster, Thomas
Sprache: Englisch
Titel: Sensing and Imaging
Bandnummer: 23
Heft: 1
Verlag/Plattform: Springer Nature
Erscheinungsjahr: 2022
Freie Schlagwörter: Terahertz radiation
Terahertz tomography
Inline monitoring
Anomaly detection
Learned defect detection
Machine learning
Nondestructive testing
Supervised learning
Gaussian distribution
Eikonal equation
DDC-Sachgruppe: 510 Mathematik
Dokumenttyp: Journalartikel / Zeitschriftenartikel
Abstract: Terahertz tomographic imaging as well as machine learning tasks represent two emerging felds in the area of nondestructive testing. Detecting outliers in measurements that are caused by defects is the main challenge in inline process monitoring. An efcient inline control enables to intervene directly during the manufacturing process and, consequently, to reduce product discard. We focus on plastics and ceramics, for which terahertz radiation is perfectly suited because of its characteristics, and propose a density based technique to automatically detect anomalies in the measured radiation data. The algorithm relies on a classifcation method based on machine learning. For a verifcation, supervised data are generated by a measuring system that approximates an inline process. The experimental results show that the use of terahertz radiation, combined with the classifcation algorithm, has great potential for a real inline manufacturing process. In a further investigation additional data are simulated to enlarge the data set, especially the variety of defects. We model the propagation of terahertz radiation by means of the Eikonal equation.
DOI der Erstveröffentlichung: 10.1007/s11220-022-00402-5
URL der Erstveröffentlichung: https://link.springer.com/article/10.1007/s11220-022-00402-5
Link zu diesem Datensatz: urn:nbn:de:bsz:291--ds-394165
hdl:20.500.11880/35537
http://dx.doi.org/10.22028/D291-39416
ISSN: 1557-2072
1557-2064
Datum des Eintrags: 30-Mär-2023
Fakultät: MI - Fakultät für Mathematik und Informatik
Fachrichtung: MI - Mathematik
Professur: MI - Prof. Dr. Thomas Schuster
Sammlung:SciDok - Der Wissenschaftsserver der Universität des Saarlandes

Dateien zu diesem Datensatz:
Datei Beschreibung GrößeFormat 
s11220-022-00402-5.pdf2,22 MBAdobe PDFÖffnen/Anzeigen


Diese Ressource wurde unter folgender Copyright-Bestimmung veröffentlicht: Lizenz von Creative Commons Creative Commons