Details
Original language | English |
---|---|
Pages (from-to) | 385-393 |
Number of pages | 9 |
Journal | Production Engineering |
Volume | 14 |
Issue number | 3 |
Publication status | Published - 19 Mar 2020 |
Abstract
Numerous methods have been developed to detect process anomalies during machining. Statistical approaches for semi-supervised anomaly detection compute decision boundaries using information of normal running processes for process evaluation. In this paper, two statistical approaches for semi-supervised anomaly detection in machining based on envelopes are presented and compared. The proposed parametric approach assumes normal distributed envelopes to compute decision boundaries. However, experiments show that deviations from a normal distribution can reduce the monitoring quality. The new approach is non-parametric and employs kernel density estimation (KDE) to estimate the probability density function of the envelopes. Both approaches were evaluated for several machining processes. It is found that the parametric approach is robust against high scattering processes and yields low false alarm rates. By means of the selected safety factor, the number of detected anomalies can be increased using the non-parametric approach.
Keywords
- Anomaly detection, Machining, Monitoring
ASJC Scopus subject areas
- Engineering(all)
- Mechanical Engineering
- Engineering(all)
- Industrial and Manufacturing Engineering
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
In: Production Engineering, Vol. 14, No. 3, 19.03.2020, p. 385-393.
Research output: Contribution to journal › Article › Research › peer review
}
TY - JOUR
T1 - Statistical approaches for semi-supervised anomaly detection in machining
AU - Denkena, B.
AU - Dittrich, M. A.
AU - Noske, H.
AU - Witt, M.
N1 - Funding information: Open Access funding provided by Projekt DEAL. Funded by the Lower Saxony Ministry of Science and Culture under Grant Number ZN3489 within the Lower Saxony “Vorab” of the Volkswagen Foundation and supported by the Center for Digital Innovations (ZDIN). We also thank the members of the Production Innovations Network (PIN) for their support.
PY - 2020/3/19
Y1 - 2020/3/19
N2 - Numerous methods have been developed to detect process anomalies during machining. Statistical approaches for semi-supervised anomaly detection compute decision boundaries using information of normal running processes for process evaluation. In this paper, two statistical approaches for semi-supervised anomaly detection in machining based on envelopes are presented and compared. The proposed parametric approach assumes normal distributed envelopes to compute decision boundaries. However, experiments show that deviations from a normal distribution can reduce the monitoring quality. The new approach is non-parametric and employs kernel density estimation (KDE) to estimate the probability density function of the envelopes. Both approaches were evaluated for several machining processes. It is found that the parametric approach is robust against high scattering processes and yields low false alarm rates. By means of the selected safety factor, the number of detected anomalies can be increased using the non-parametric approach.
AB - Numerous methods have been developed to detect process anomalies during machining. Statistical approaches for semi-supervised anomaly detection compute decision boundaries using information of normal running processes for process evaluation. In this paper, two statistical approaches for semi-supervised anomaly detection in machining based on envelopes are presented and compared. The proposed parametric approach assumes normal distributed envelopes to compute decision boundaries. However, experiments show that deviations from a normal distribution can reduce the monitoring quality. The new approach is non-parametric and employs kernel density estimation (KDE) to estimate the probability density function of the envelopes. Both approaches were evaluated for several machining processes. It is found that the parametric approach is robust against high scattering processes and yields low false alarm rates. By means of the selected safety factor, the number of detected anomalies can be increased using the non-parametric approach.
KW - Anomaly detection
KW - Machining
KW - Monitoring
UR - http://www.scopus.com/inward/record.url?scp=85082838911&partnerID=8YFLogxK
U2 - 10.1007/s11740-020-00958-9
DO - 10.1007/s11740-020-00958-9
M3 - Article
AN - SCOPUS:85082838911
VL - 14
SP - 385
EP - 393
JO - Production Engineering
JF - Production Engineering
SN - 0944-6524
IS - 3
ER -