Details
| Original language | English |
|---|---|
| Title of host publication | Lecture Notes in Production Engineering |
| Publisher | Springer Nature |
| Pages | 479-487 |
| Number of pages | 9 |
| ISBN (electronic) | 978-3-030-78424-9 |
| ISBN (print) | 978-3-030-78423-2 |
| Publication status | Published - 2022 |
Publication series
| Name | Lecture Notes in Production Engineering |
|---|---|
| Volume | Part F1160 |
| ISSN (Print) | 2194-0525 |
| ISSN (electronic) | 2194-0533 |
Abstract
Monitoring process errors and tool condition in single item production is challenging, as a teach-in is not possible due to a missing reference process. An approach to this problem is anomaly detection, e.g. based on motor currents or axis position signals from metal cutting processes. However, with no references anomaly detection struggles to detect failures from signals, because failure patterns are often too similar to regular process dynamics. While single items inherently constitute an anomaly by themselves, they do contain repetitive elements, like boreholes or milled pockets. These elements are similar, what provides an anomaly detection with additional information on regular processes. Hierarchical K-Means clustering combined with Dynamic Time Warping (DTW) and Barycenter Averaging (DBA) enables the identification of similar process elements. The algorithm allows ordering similar process segments by similarity in a tree structure. The introduced method supports querying subsequences from any given cutting process, for which it returns the closest cluster in the tree. This allows to (a) improve the data basis for anomaly detection and (b) to transfer labels with errors between processes. The article demonstrates the transfer of labels (for errors) from a turning process, to a single item milling process.
Keywords
- Barycenter averaging, Machining, Monitoring, Pattern recognition, Time series clustering
ASJC Scopus subject areas
- Engineering(all)
- Industrial and Manufacturing Engineering
- Economics, Econometrics and Finance(all)
- Economics, Econometrics and Finance (miscellaneous)
- Engineering(all)
- Safety, Risk, Reliability and Quality
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
Lecture Notes in Production Engineering. Springer Nature, 2022. p. 479-487 (Lecture Notes in Production Engineering; Vol. Part F1160).
Research output: Chapter in book/report/conference proceeding › Contribution to book/anthology › Research › peer review
}
TY - CHAP
T1 - Time Series Search and Similarity Identification for Single Item Monitoring
AU - Denkena, B.
AU - Bergmann, B.
AU - Becker, J.
AU - Stiehl, T. H.
N1 - Funding Information: Acknowledgements. The authors thank the Federal Ministry of Economics (BMWi) for its financial and organizational support of the project “IIP Ecosphere” (01MK20006A).
PY - 2022
Y1 - 2022
N2 - Monitoring process errors and tool condition in single item production is challenging, as a teach-in is not possible due to a missing reference process. An approach to this problem is anomaly detection, e.g. based on motor currents or axis position signals from metal cutting processes. However, with no references anomaly detection struggles to detect failures from signals, because failure patterns are often too similar to regular process dynamics. While single items inherently constitute an anomaly by themselves, they do contain repetitive elements, like boreholes or milled pockets. These elements are similar, what provides an anomaly detection with additional information on regular processes. Hierarchical K-Means clustering combined with Dynamic Time Warping (DTW) and Barycenter Averaging (DBA) enables the identification of similar process elements. The algorithm allows ordering similar process segments by similarity in a tree structure. The introduced method supports querying subsequences from any given cutting process, for which it returns the closest cluster in the tree. This allows to (a) improve the data basis for anomaly detection and (b) to transfer labels with errors between processes. The article demonstrates the transfer of labels (for errors) from a turning process, to a single item milling process.
AB - Monitoring process errors and tool condition in single item production is challenging, as a teach-in is not possible due to a missing reference process. An approach to this problem is anomaly detection, e.g. based on motor currents or axis position signals from metal cutting processes. However, with no references anomaly detection struggles to detect failures from signals, because failure patterns are often too similar to regular process dynamics. While single items inherently constitute an anomaly by themselves, they do contain repetitive elements, like boreholes or milled pockets. These elements are similar, what provides an anomaly detection with additional information on regular processes. Hierarchical K-Means clustering combined with Dynamic Time Warping (DTW) and Barycenter Averaging (DBA) enables the identification of similar process elements. The algorithm allows ordering similar process segments by similarity in a tree structure. The introduced method supports querying subsequences from any given cutting process, for which it returns the closest cluster in the tree. This allows to (a) improve the data basis for anomaly detection and (b) to transfer labels with errors between processes. The article demonstrates the transfer of labels (for errors) from a turning process, to a single item milling process.
KW - Barycenter averaging
KW - Machining
KW - Monitoring
KW - Pattern recognition
KW - Time series clustering
UR - http://www.scopus.com/inward/record.url?scp=85135164335&partnerID=8YFLogxK
U2 - 10.1007/978-3-030-78424-9_53
DO - 10.1007/978-3-030-78424-9_53
M3 - Contribution to book/anthology
AN - SCOPUS:85135164335
SN - 978-3-030-78423-2
T3 - Lecture Notes in Production Engineering
SP - 479
EP - 487
BT - Lecture Notes in Production Engineering
PB - Springer Nature
ER -