Introduction to deep degradation metric in smart production ecosystems

Publikation: Beitrag in FachzeitschriftKonferenzaufsatz in FachzeitschriftForschungPeer-Review

Autoren

  • Yeremia Gunawan Adhisantoso
  • Quy Le Xuan
  • Marco Munderloh
  • Jörn Ostermann
  • Christoph Kellerman
Forschungs-netzwerk anzeigen

Details

OriginalspracheEnglisch
Seiten (von - bis)1010-1015
Seitenumfang6
FachzeitschriftProcedia CIRP
Jahrgang118
Frühes Online-Datum18 Juli 2023
PublikationsstatusVeröffentlicht - 2023
Veranstaltung16th CIRP Conference on Intelligent Computation in Manufacturing Engineering 2022 - Naples, Italien
Dauer: 13 Juli 202215 Juli 2022

Abstract

With the advent of Industry 4.0, more data is exploited to improve efficiency in production and to enable a cost-effective maintenance approach called predictive maintenance. In a production ecosystem, assets are maintained based on their corresponding internal condition. Often, there is no known ground truth or label for the internal condition of the components, especially for high-dimensional data. Furthermore, the initial degradation condition of the assets differs from each other. We present a novel approach to learns a degradation metric implicitly (with minimal information). The approach can take the initial condition of the asset into consideration.

ASJC Scopus Sachgebiete

Zitieren

Introduction to deep degradation metric in smart production ecosystems. / Adhisantoso, Yeremia Gunawan; Xuan, Quy Le; Munderloh, Marco et al.
in: Procedia CIRP, Jahrgang 118, 2023, S. 1010-1015.

Publikation: Beitrag in FachzeitschriftKonferenzaufsatz in FachzeitschriftForschungPeer-Review

Adhisantoso, YG, Xuan, QL, Munderloh, M, Ostermann, J & Kellerman, C 2023, 'Introduction to deep degradation metric in smart production ecosystems', Procedia CIRP, Jg. 118, S. 1010-1015. https://doi.org/10.1016/j.procir.2023.06.173
Adhisantoso, Y. G., Xuan, Q. L., Munderloh, M., Ostermann, J., & Kellerman, C. (2023). Introduction to deep degradation metric in smart production ecosystems. Procedia CIRP, 118, 1010-1015. https://doi.org/10.1016/j.procir.2023.06.173
Adhisantoso YG, Xuan QL, Munderloh M, Ostermann J, Kellerman C. Introduction to deep degradation metric in smart production ecosystems. Procedia CIRP. 2023;118:1010-1015. Epub 2023 Jul 18. doi: 10.1016/j.procir.2023.06.173
Adhisantoso, Yeremia Gunawan ; Xuan, Quy Le ; Munderloh, Marco et al. / Introduction to deep degradation metric in smart production ecosystems. in: Procedia CIRP. 2023 ; Jahrgang 118. S. 1010-1015.
Download
@article{aab9b44734b246318f7f775abf255f51,
title = "Introduction to deep degradation metric in smart production ecosystems",
abstract = "With the advent of Industry 4.0, more data is exploited to improve efficiency in production and to enable a cost-effective maintenance approach called predictive maintenance. In a production ecosystem, assets are maintained based on their corresponding internal condition. Often, there is no known ground truth or label for the internal condition of the components, especially for high-dimensional data. Furthermore, the initial degradation condition of the assets differs from each other. We present a novel approach to learns a degradation metric implicitly (with minimal information). The approach can take the initial condition of the asset into consideration.",
keywords = "computer vision, predictive maintenance, prognostic health management",
author = "Adhisantoso, {Yeremia Gunawan} and Xuan, {Quy Le} and Marco Munderloh and J{\"o}rn Ostermann and Christoph Kellerman",
note = "Funding Information: The authors acnk oledw ge the inf ancial support by the Federal Ministry of r Economic Afaf irs and Climate Action of Germany (BWMK) in the rf ameow r k of IIP -Ecosphere project (project number 01MK20006A ). We ow uld also lie k to thank Gerresheimer Bn{\"u} de GmbH for providing the materials in this work.; 16th CIRP Conference on Intelligent Computation in Manufacturing Engineering 2022, CIRP ICME ; Conference date: 13-07-2022 Through 15-07-2022",
year = "2023",
doi = "10.1016/j.procir.2023.06.173",
language = "English",
volume = "118",
pages = "1010--1015",

}

Download

TY - JOUR

T1 - Introduction to deep degradation metric in smart production ecosystems

AU - Adhisantoso, Yeremia Gunawan

AU - Xuan, Quy Le

AU - Munderloh, Marco

AU - Ostermann, Jörn

AU - Kellerman, Christoph

N1 - Funding Information: The authors acnk oledw ge the inf ancial support by the Federal Ministry of r Economic Afaf irs and Climate Action of Germany (BWMK) in the rf ameow r k of IIP -Ecosphere project (project number 01MK20006A ). We ow uld also lie k to thank Gerresheimer Bnü de GmbH for providing the materials in this work.

PY - 2023

Y1 - 2023

N2 - With the advent of Industry 4.0, more data is exploited to improve efficiency in production and to enable a cost-effective maintenance approach called predictive maintenance. In a production ecosystem, assets are maintained based on their corresponding internal condition. Often, there is no known ground truth or label for the internal condition of the components, especially for high-dimensional data. Furthermore, the initial degradation condition of the assets differs from each other. We present a novel approach to learns a degradation metric implicitly (with minimal information). The approach can take the initial condition of the asset into consideration.

AB - With the advent of Industry 4.0, more data is exploited to improve efficiency in production and to enable a cost-effective maintenance approach called predictive maintenance. In a production ecosystem, assets are maintained based on their corresponding internal condition. Often, there is no known ground truth or label for the internal condition of the components, especially for high-dimensional data. Furthermore, the initial degradation condition of the assets differs from each other. We present a novel approach to learns a degradation metric implicitly (with minimal information). The approach can take the initial condition of the asset into consideration.

KW - computer vision

KW - predictive maintenance

KW - prognostic health management

UR - http://www.scopus.com/inward/record.url?scp=85173576129&partnerID=8YFLogxK

U2 - 10.1016/j.procir.2023.06.173

DO - 10.1016/j.procir.2023.06.173

M3 - Conference article

AN - SCOPUS:85173576129

VL - 118

SP - 1010

EP - 1015

JO - Procedia CIRP

JF - Procedia CIRP

SN - 2212-8271

T2 - 16th CIRP Conference on Intelligent Computation in Manufacturing Engineering 2022

Y2 - 13 July 2022 through 15 July 2022

ER -

Von denselben Autoren