Anomaly detection in formed sheet metals using convolutional autoencoders
Research output: Journal contributions › Conference article in journal › Research › peer-review
Standard
In: Procedia CIRP, Vol. 93, 01.01.2020, p. 1281-1285.
Research output: Journal contributions › Conference article in journal › Research › peer-review
Harvard
APA
Vancouver
Bibtex
}
RIS
TY - JOUR
T1 - Anomaly detection in formed sheet metals using convolutional autoencoders
AU - Heger, Jens
AU - Desai, Gururaj
AU - Zein El Abdine, Mazhar
N1 - Conference code: 53
PY - 2020/1/1
Y1 - 2020/1/1
N2 - 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
AB - 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
KW - Engineering
KW - Artifical intelligence
KW - Deep autoencoders
KW - Process monitoring
KW - Surface quality inspection
UR - http://www.scopus.com/inward/record.url?scp=85092439400&partnerID=8YFLogxK
U2 - 10.1016/j.procir.2020.04.106
DO - 10.1016/j.procir.2020.04.106
M3 - Conference article in journal
AN - SCOPUS:85092439400
VL - 93
SP - 1281
EP - 1285
JO - Procedia CIRP
JF - Procedia CIRP
SN - 2212-8271
T2 - 53rd CIRP Conference on Manufacturing Systems - CMS 2020
Y2 - 1 July 2020 through 3 July 2020
ER -