Anomaly Detections for Manufacturing Systems Based on Sensor Data—Insights into Two Challenging Real-World Production Settings
Please always quote using this URN: urn:nbn:de:bvb:20-opus-193885
- o build, run, and maintain reliable manufacturing machines, the condition of their components has to be continuously monitored. When following a fine-grained monitoring of these machines, challenges emerge pertaining to the (1) feeding procedure of large amounts of sensor data to downstream processing components and the (2) meaningful analysis of the produced data. Regarding the latter aspect, manifold purposes are addressed by practitioners and researchers. Two analyses of real-world datasets that were generated in production settings areo build, run, and maintain reliable manufacturing machines, the condition of their components has to be continuously monitored. When following a fine-grained monitoring of these machines, challenges emerge pertaining to the (1) feeding procedure of large amounts of sensor data to downstream processing components and the (2) meaningful analysis of the produced data. Regarding the latter aspect, manifold purposes are addressed by practitioners and researchers. Two analyses of real-world datasets that were generated in production settings are discussed in this paper. More specifically, the analyses had the goals (1) to detect sensor data anomalies for further analyses of a pharma packaging scenario and (2) to predict unfavorable temperature values of a 3D printing machine environment. Based on the results of the analyses, it will be shown that a proper management of machines and their components in industrial manufacturing environments can be efficiently supported by the detection of anomalies. The latter shall help to support the technical evangelists of the production companies more properly.…
Author: | Klaus Kammerer, Burkhard Hoppenstedt, Rüdiger Pryss, Steffen Stökler, Johannes Allgaier, Manfred Reichert |
---|---|
URN: | urn:nbn:de:bvb:20-opus-193885 |
Document Type: | Journal article |
Faculties: | Medizinische Fakultät / Institut für Klinische Epidemiologie und Biometrie |
Language: | English |
Parent Title (English): | Sensors |
ISSN: | 1424-8220 |
Year of Completion: | 2019 |
Volume: | 19 |
Issue: | 24 |
Pagenumber: | 5370 |
Source: | Sensors 2019, 19(24), 5370; https://doi.org/10.3390/s19245370 |
DOI: | https://doi.org/10.3390/s19245370 |
Dewey Decimal Classification: | 6 Technik, Medizin, angewandte Wissenschaften / 61 Medizin und Gesundheit / 610 Medizin und Gesundheit |
Tag: | anomaly detection; machine learning; production machines; sensor data |
Release Date: | 2020/08/18 |
Date of first Publication: | 2019/12/05 |
Licence (German): | CC BY: Creative-Commons-Lizenz: Namensnennung 4.0 International |