Anomaly detection in formed sheet metals using convolutional autoencoders

Research output: Journal contributionsConference article in journalResearchpeer-review


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
Pages (from-to)1281-1285
Number of pages5
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