Within Industry 4.0, Digital Twins (DTs) have become essential services for monitoring, analysing, and optimising manufacturing systems. However, when multiple digital services – such as distinct DTs for machines and for production systems – operate within the same physical environment, a lack of integration can lead to fragmented decision-making and reduced overall system efficiency. This paper addresses this challenge by proposing a multi-level integration approach that connects machine-level and production system-level digital services, specifically the Digital Monitoring Service (DSM) and the Digital What-if Simulation Service (DWSS), to support joint decision-making. Using a proof-of-concept example focussed on integrating maintenance and production planning analyses, the paper demonstrates the main objectives of the proposed integration, namely (i) the event-driven multi-level integration – to determine how event-based local anomalies, such as increased machine downtime, can be propagated to assess their impact at production system-level; (ii) DWSS usage with a Simulated DSM (SDMS) – to determine how evaluations based on what-if scenario analyses that simulate also the monitoring service of the real system, that is, data and/or KPIs, enable consistent decision-making establishing coherent thresholds or control policies in production system with the overall production objectives. Furthermore, this paper discusses the practical benefits and challenges of implementing the proposed integration in real industrial environments, which can contribute in the long term to integrated decision-making among digital services in Cyber Physical Systems (CPSs).
Building similarity graph...
Analyzing shared references across papers
Loading...
Chiara Cimino
Laila El Warraqi
Elisa Negri
Proceedings of the Institution of Mechanical Engineers Part O Journal of Risk and Reliability
Politecnico di Milano
Building similarity graph...
Analyzing shared references across papers
Loading...
Cimino et al. (Tue,) studied this question.
www.synapsesocial.com/papers/69fd7ec6bfa21ec5bbf070ff — DOI: https://doi.org/10.1177/1748006x261433749