Anomaly detection in formed sheet metals using convolutional autoencoders

Research output: Journal contributionsConference article in journalResearchpeer-review

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
Original languageEnglish
JournalProcedia CIRP
Volume93
Pages (from-to)1281-1285
Number of pages5
ISSN2212-8271
DOIs
Publication statusPublished - 01.01.2020
Event53rd CIRP Conference on Manufacturing Systems - CMS 2020 - Chicago, United States
Duration: 01.07.202003.07.2020
Conference number: 53

Bibliographical note

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).

    Research areas

  • Engineering - Artifical intelligence, Deep autoencoders, Process monitoring, Surface quality inspection

Documents

DOI

Recently viewed

Publications

  1. Multidimensional recurrence quantification analysis (MdRQA) for the analysis of multidimensional time-series
  2. Cognitive load and instructionally supported learning with provided and learner-generated visualizations
  3. The role of spatial ability in learning from instructional animations - Evidence for an ability-as-compensator hypothesis
  4. A Lean Convolutional Neural Network for Vehicle Classification
  5. Assessment of university students’ understanding of abstract binary operations
  6. Obstacle Coordinates Transformation from TVS Body-Frame to AGV Navigation-Frame
  7. Collaborative open science as a way to reproducibility and new insights in primate cognition research
  8. Neural Networks for Energy Optimization of Production Processes in Small and Medium Sized Enterprises
  9. Project-Mentoring in Engineering Education - a competence-oriented teaching and learning approach
  10. Making the matrix matter
  11. Comparative study on corrosion behavior of we33 in immersion and polarization influenced by heat treatment
  12. Multi-agent systems' asset for smart grid applications
  13. Learning to rule
  14. Enhancing Community Interactions with Data-Driven Chatbots - The DBpedia Chatbot
  15. Teaching content and language in the multilingual classroom
  16. On-Board-Diagnose und On-Board-Measurement
  17. Conceptual Dimensions of Embodiment
  18. Credit constraints and exports: A survey of empirical studies using firm level data
  19. Extrinsic Calibration Method under Low-Light Conditions for Hybrid Vision System
  20. Impact of above- and below-ground invertebrates on temporal and spatial stability of grassland of different diversity
  21. Transcending Methodological Nationalism through a Transversal Method?
  22. Mit Pixel und Korn
  23. Investigation of the deformation behavior of Fe-3%Si sheet metal with large grains via crystal plasticity and finite-element modeling
  24. Reconstructing the “biopiracy” debate from a justice perspective
  25. Challenges and opportunities in linking carbon sequestration, livelihoods and ecosystem service provision in drylands
  26. [Paul Celan und] Martin Heidegger
  27. When mortality knocks
  28. User Participation in the Quality Assurance of Requirements Specifications
  29. Hot working mechanisms and texture development in Mg-3Sn-2Ca-0.4Al alloy
  30. The Fibreculture Journal
  31. International Master’s Programme in Sustainable Development and Management