Anomaly detection in formed sheet metals using convolutional autoencoders

Publikation: Beiträge in ZeitschriftenKonferenzaufsätze in FachzeitschriftenForschungbegutachtet

Authors

Autoencoders are used to compress data and learn how to reliably reconstruct it. Through comparing the reconstruction error with a set threshold, they are able to detect anomalies in unseen datasets where the data does not quite match the reconstructed input samples. In this work, we attempt to investigate the use of convolutional autoencoders in the field of visual quality inspection, where images of formed sheet metals from a real production line are inspected for the occurrence of cracks and wrinkle formation. This approach tackles the problem of needing enough defective samples to attain reliable detection accuracies
OriginalspracheEnglisch
ZeitschriftProcedia CIRP
Jahrgang93
Seiten (von - bis)1281-1285
Anzahl der Seiten5
ISSN2212-8271
DOIs
PublikationsstatusErschienen - 01.01.2020
Veranstaltung53rd CIRP Conference on Manufacturing Systems - CMS 2020 - Chicago, USA / Vereinigte Staaten
Dauer: 01.07.202003.07.2020
Konferenznummer: 53

Bibliographische Notiz

The authors gratefully acknowledge the financial support given by the Federal Ministry for Economic Affairs and Energy (BMWi) under the Central Innovation Programme for SMEs IM)(Zorfe thopjrectartSPm“”ress on the basis of a decision of the German Bundestag (grant number: ZF4084503GR7).

Dokumente

DOI

Zuletzt angesehen

Publikationen

  1. Proxies
  2. Taking the pulse of Earth's tropical forests using networks of highly distributed plots
  3. E-stability and stability of adaptive learning in models with asymmetric information
  4. Active and semi-supervised data domain description
  5. Spaces for challenging experiences, indeterminacy, and experimentation
  6. Efficient Order Picking Methods in Robotic Mobile Fulfillment Systems
  7. THE PARALLAX OF INDIVIDUATION
  8. Control of an Electromagnetic Linear Actuator Using Flatness Property and Systems Inversion
  9. Restricted nonlinear approximation and singular solutions of boundary integral equations
  10. Using sequential injection analysis for fast determination of phosphate in coastal waters
  11. Performance predictors for graphics processing units applied to dark-silicon-aware design space exploration
  12. Industrial applications using wavelet packets for gross error detection
  13. Metaheuristics approach for solving personalized crew rostering problem in public bus transit
  14. On the Difficulty of Forgetting
  15. Spectral Early-Warning Signals for Sudden Changes in Time-Dependent Flow Patterns
  16. Octanol-Water Partition Coefficient Measurement by a Simple 1H NMR Method
  17. Governing Objects from a Distance
  18. Performance Saga: Interview 01
  19. A Multilevel Inverter Bridge Control Structure with Energy Storage Using Model Predictive Control for Flat Systems
  20. On the Direct Kinematics Problem of Parallel Mechanisms
  21. Pushing the Envelope: Creating Public Value in the Labor Market
  22. Making mutual learning tangible
  23. How can problems be turned into something good? The role of entrepreneurial learning and error mastery orientation
  24. Theorie des Quantum Computings
  25. Petri net based EMIS-mappers for flexible manufacturing systems
  26. Determination of 10 particle-associated multiclass polar and semi-polar pesticides from small streams using accelerated solvent extraction
  27. Performance concepts and performance theory
  28. Convergence of adaptive learning and expectational stability
  29. Introduction
  30. Analysis of the mechanical properties of an arc-sprayed WC-FeCSiMn coating