Details
| Originalsprache | Englisch |
|---|---|
| Seiten (von - bis) | 1480-1486 |
| Seitenumfang | 7 |
| Fachzeitschrift | Procedia CIRP |
| Jahrgang | 130 |
| Frühes Online-Datum | 27 Nov. 2024 |
| Publikationsstatus | Veröffentlicht - 2024 |
| Veranstaltung | 57th CIRP Conference on Manufacturing Systems 2024, CMS 2024 - Povoa de Varzim, Portugal Dauer: 29 Mai 2024 → 31 Mai 2024 |
Abstract
The manufacturing industry faces an increasing demand for high product customization and high delivery performance in a volatile market environment. To meet these market demands, companies are reliant on high-performing production logistics. In case of underperformance, root causes must be identified, and appropriate countermeasures must be initiated to avoid jeopardizing customer satisfaction. However, complex logistic cause-effect relationships often obscure the root causes of underperformance. Existing approaches to logistic modeling enable a root cause analysis based on generally valid cause-effect relationships in production logistics. Due to increasing data availability, Data Analytics (DA) and Machine Learning (ML) enable context-specific analysis at a high level of granularity and individuality. Systematically integrating DA/ML with logistic models promises a high potential for revealing actual root causes, thus enabling data-driven and target-oriented countermeasure derivation. This paper presents a production monitoring and control framework for identifying the root causes of logistics underperformance and deriving target-oriented countermeasures that systematically combines the benefits of logistic models and DA/ML. The developed framework comprises a hierarchical target system, a data architecture, and a catalog of countermeasures combined into a monitoring and control procedure. In a case study, the root causes of delayed material availability in the procurement of an electrical machinery manufacturer are analyzed using logistic models and DA/ML to demonstrate the potential of hybrid analysis.
ASJC Scopus Sachgebiete
- Ingenieurwesen (insg.)
- Steuerungs- und Systemtechnik
- Ingenieurwesen (insg.)
- Wirtschaftsingenieurwesen und Fertigungstechnik
Zitieren
- Standard
- Harvard
- Apa
- Vancouver
- BibTex
- RIS
in: Procedia CIRP, Jahrgang 130, 2024, S. 1480-1486.
Publikation: Beitrag in Fachzeitschrift › Konferenzaufsatz in Fachzeitschrift › Forschung › Peer-Review
}
TY - JOUR
T1 - Production Monitoring and Control Framework for data-driven improvement of Logistics Performance
AU - Welzel, Kira
AU - Kulaszewski, Dario
AU - Mütze, Alexander
AU - Lucht, Torben
AU - Nyhuis, Peter
AU - Schmidt, Matthias
N1 - Publisher Copyright: © 2024 The Authors. Published by Elsevier B.V.
PY - 2024
Y1 - 2024
N2 - The manufacturing industry faces an increasing demand for high product customization and high delivery performance in a volatile market environment. To meet these market demands, companies are reliant on high-performing production logistics. In case of underperformance, root causes must be identified, and appropriate countermeasures must be initiated to avoid jeopardizing customer satisfaction. However, complex logistic cause-effect relationships often obscure the root causes of underperformance. Existing approaches to logistic modeling enable a root cause analysis based on generally valid cause-effect relationships in production logistics. Due to increasing data availability, Data Analytics (DA) and Machine Learning (ML) enable context-specific analysis at a high level of granularity and individuality. Systematically integrating DA/ML with logistic models promises a high potential for revealing actual root causes, thus enabling data-driven and target-oriented countermeasure derivation. This paper presents a production monitoring and control framework for identifying the root causes of logistics underperformance and deriving target-oriented countermeasures that systematically combines the benefits of logistic models and DA/ML. The developed framework comprises a hierarchical target system, a data architecture, and a catalog of countermeasures combined into a monitoring and control procedure. In a case study, the root causes of delayed material availability in the procurement of an electrical machinery manufacturer are analyzed using logistic models and DA/ML to demonstrate the potential of hybrid analysis.
AB - The manufacturing industry faces an increasing demand for high product customization and high delivery performance in a volatile market environment. To meet these market demands, companies are reliant on high-performing production logistics. In case of underperformance, root causes must be identified, and appropriate countermeasures must be initiated to avoid jeopardizing customer satisfaction. However, complex logistic cause-effect relationships often obscure the root causes of underperformance. Existing approaches to logistic modeling enable a root cause analysis based on generally valid cause-effect relationships in production logistics. Due to increasing data availability, Data Analytics (DA) and Machine Learning (ML) enable context-specific analysis at a high level of granularity and individuality. Systematically integrating DA/ML with logistic models promises a high potential for revealing actual root causes, thus enabling data-driven and target-oriented countermeasure derivation. This paper presents a production monitoring and control framework for identifying the root causes of logistics underperformance and deriving target-oriented countermeasures that systematically combines the benefits of logistic models and DA/ML. The developed framework comprises a hierarchical target system, a data architecture, and a catalog of countermeasures combined into a monitoring and control procedure. In a case study, the root causes of delayed material availability in the procurement of an electrical machinery manufacturer are analyzed using logistic models and DA/ML to demonstrate the potential of hybrid analysis.
KW - Cause-Effect Relationships
KW - Data Analytics
KW - Logistic Key Performance Indicators
KW - Production Logistics
UR - http://www.scopus.com/inward/record.url?scp=85215014214&partnerID=8YFLogxK
U2 - 10.1016/j.procir.2024.10.270
DO - 10.1016/j.procir.2024.10.270
M3 - Conference article
AN - SCOPUS:85215014214
VL - 130
SP - 1480
EP - 1486
JO - Procedia CIRP
JF - Procedia CIRP
SN - 2212-8271
T2 - 57th CIRP Conference on Manufacturing Systems 2024, CMS 2024
Y2 - 29 May 2024 through 31 May 2024
ER -