• Medientyp: E-Artikel; Sonstige Veröffentlichung
  • Titel: A Framework For The Domain-Driven Utilization Of Manufacturing Sensor Data In Process Mining: An Action Design Approach
  • Beteiligte: Brock, Jonathan [VerfasserIn]; Rempe, Niclas [VerfasserIn]; von Enzberg, Sebastian [VerfasserIn]; Kühn, Arno [VerfasserIn]; Dumitrescu, Roman [VerfasserIn]; Herberger, David [VerfasserIn]; Hübner, Marco [VerfasserIn]
  • Erschienen: Hannover : publish-Ing., 2023
  • Erschienen in: Proceedings of the Conference on Production Systems and Logistics: CPSL 2023 - 2 ; https://doi.org/10.15488/15326
  • Ausgabe: published Version
  • Sprache: Englisch
  • DOI: https://doi.org/10.15488/15267; https://doi.org/10.15488/15326
  • Schlagwörter: Framework ; Sensor Data ; Manufacturing ; Process Mining ; Real-World ; Konferenzschrift
  • Entstehung:
  • Anmerkungen: Diese Datenquelle enthält auch Bestandsnachweise, die nicht zu einem Volltext führen.
  • Beschreibung: Manufacturers install and rely on a large number of sensors to operate and control their processes. However, the collected sensor data is rarely used to analyse and improve the higher-level, aggregated business processes. Process mining (PM) appears to be a promising solution, with the ability to automatically generate and analyse business process models based on data. However, the atomic events of sensor measurements need to be refined, aggregated, and enriched to properly represent a business process. In this paper, we propose a novel framework to make manufacturing sensor data analysable with PM. The framework allows manufacturers with batch and continuous processes (BCP) to systematically enrich their sensor data to use it for optimization purposes. Following the action design research, we demonstrate the applicability of the framework in a use case study using sensor data from a BCP beverage production.
  • Zugangsstatus: Freier Zugang