Statistical approaches for semi-supervised anomaly detection in machining

Research output: Contribution to journal › Article › Research › peer review

Authors

  • B. Denkena
  • M. A. Dittrich
  • H. Noske
  • M. Witt

Research Organisations

View graph of relations

Details

Original languageEnglish
Pages (from-to)385-393
Number of pages9
JournalProduction Engineering
Volume14
Issue number3
Publication statusPublished - 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

Cite this

Statistical approaches for semi-supervised anomaly detection in machining. / Denkena, B.; Dittrich, M. A.; Noske, H. et al.
In: Production Engineering, Vol. 14, No. 3, 19.03.2020, p. 385-393.

Research output: Contribution to journal › Article › Research › peer review

Denkena, B, Dittrich, MA, Noske, H & Witt, M 2020, 'Statistical approaches for semi-supervised anomaly detection in machining', Production Engineering, vol. 14, no. 3, pp. 385-393. https://doi.org/10.1007/s11740-020-00958-9
Denkena, B., Dittrich, M. A., Noske, H., & Witt, M. (2020). Statistical approaches for semi-supervised anomaly detection in machining. Production Engineering, 14(3), 385-393. https://doi.org/10.1007/s11740-020-00958-9
Denkena B, Dittrich MA, Noske H, Witt M. Statistical approaches for semi-supervised anomaly detection in machining. Production Engineering. 2020 Mar 19;14(3):385-393. doi: 10.1007/s11740-020-00958-9
Denkena, B. ; Dittrich, M. A. ; Noske, H. et al. / Statistical approaches for semi-supervised anomaly detection in machining. In: Production Engineering. 2020 ; Vol. 14, No. 3. pp. 385-393.
Download
@article{fe6c7484ffbe496c89ed2156b2e2c7f7,
title = "Statistical approaches for semi-supervised anomaly detection in machining",
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",
author = "B. Denkena and Dittrich, {M. A.} and H. Noske and M. Witt",
note = "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.",
year = "2020",
month = mar,
day = "19",
doi = "10.1007/s11740-020-00958-9",
language = "English",
volume = "14",
pages = "385--393",
number = "3",

}

Download

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 -