Description

„Process Management in Digital Production“ (DiPro)

The goal of PM-DiPro is to establish a forum for researchers and professionals interested in understanding, envisioning and discussing the challenges and opportunities of utilizing Process Management Systems and Data Analytics in industrial settings. Currently on shop-floors data is mostly collected and stored from focusing on individual machines. The increasing digitization of
industrial processes also across organizations sometimes labeled industry 4.0 or smart manufacturing, however, requires a more holistic and connected perspective. The introduction of process management technology to orchestrate business processes from ERPs all the way down to machine control seems an appropriate answer and produces much more interconnected data. Subsequently this opens up the potential for gaining much deeper insight into industrial processes through data analytics than ever before. Insights from data analytics can be used to improve business process at design time but also to improve the execution of business processes during run time.

This interdisciplinary workshop is for experts in the field of Mechanical or Electrical Engineering, Automation Engineering, Data Science, Computer Science, Information Systems and Business Process Management.

The workshop aims at discussing the current state of ongoing research and sharing practical experiences, exchanging ideas and setting up future research directions. We aim to bring together practitioners and researchers from different communities such as business process management, automation engineering, mechanical engineering, process mining, and data mining who share
an interest in data analytics, process-aware information systems, and the shop-floor.

The list of topics that are relevant to the PM-DiPro workshop includes, but is not limited to:

  • BPMN and the shop-floor
  • Production process meta-data annotation
  • Visualization of large scale production networks
  • Mining of machining data
  • Temporal analysis of production data
  • Statistical analysis of production life-cycles
  • Predictive analytics
  • Root cause analysis for production errors
  • Vizualization of production processes and errors
  • Machine-learning and production processes

We also welcome case studies and application papers, covering:

  • Scheduling and planing
  • Process evolution / re-engineering
  • Ad-hoc changes to improve production process performance
  • Measuring production process quality
  • Production process discovery
  • Monitoring of production processes
  • Dynamic composition of production