TY - JOUR U1 - Wissenschaftlicher Artikel A1 - Kiefer, Daniel A1 - Wezel, Stefan A1 - Böttcher, Alexander A1 - Grimm, Florian A1 - Straub, Tim A1 - Bitsch, Günter A1 - van Dinther, Clemens T1 - Anomaly detection in hobbing tool images: using an unsupervised deep learning approach in manufacturing industry JF - Procedia computer science N2 - This study explores the application of the PatchCore algorithm for anomaly classification in hobbing tools, an area of keen interest in industrial artificial intelligence application. Despite utilizing limited training images, the algorithm demonstrates capability in recognizing a variety of anomalies, promising to reduce the time-intensive labeling process traditionally undertaken by domain experts. The algorithm demonstrated an accuracy of 92%, precision of 84%, recall of 100%, and a balanced F1 score of 91%, showcasing its proficiency in identifying anomalies. However, the investigation also highlights that while the algorithm effectively identifies anomalies, it doesn't primarily recognize domain-specific wear issues. Thus, the presented approach is used only for pre-classification, with domain experts subsequently segmenting the images indicating significant wear. The intention is to employ a supervised learning procedure to identify actual wear. This premise will be further investigated in future research studies. KW - anomaly detection KW - industrial machine learning applications KW - tool image analysis KW - unsupervised deep learning Y1 - 2024 UN - https://nbn-resolving.org/urn:nbn:de:bsz:rt2-opus4-49315 SN - 1877-0509 SS - 1877-0509 U6 - https://doi.org/10.1016/j.procs.2024.02.058 DO - https://doi.org/10.1016/j.procs.2024.02.058 VL - 232 IS - 5th International Conference on Industry 4.0 and Smart Manufacturing (ISM 2023) SP - 2396 EP - 2405 S1 - 10 PB - Elsevier CY - Amsterdam ER -