Abstract : Due to increasingly required flexibility in manufacturing systems, adaptation of monitoring and control to changing context such as reconfiguration of devices becomes more important. Referring to the usage of structured information on the Web, digital twin models of manufacturing data can be seen as knowledge graphs that constantly need to be aligned with the physical environment. With a growing number of smart devices participating in production processes, handling these alignments manually is no longer feasible. Yet, the growing availability of data coming from operations (e.g. process events) and contextual sources (e.g. equipment configurations) enables machine learning to synchronize data models with physical reality. Common knowledge graph learning approaches, however, are not designed to deal with both, static and time-dependent data.In order to overcome this, we introduce a representation learning model that shows promising results for the synchronization of semantics from existing manufacturing knowledge graphs and operational data.
https://hal.inria.fr/hal-01707253 Contributor : Hal IfipConnect in order to contact the contributor Submitted on : Monday, February 12, 2018 - 4:24:31 PM Last modification on : Tuesday, August 27, 2019 - 11:56:01 AM Long-term archiving on: : Monday, May 7, 2018 - 4:54:42 AM
Martin Ringsquandl, Steffen Lamparter, Raffaello Lepratti, Peer Kröger. Knowledge Fusion of Manufacturing Operations Data Using Representation Learning. IFIP International Conference on Advances in Production Management Systems (APMS), Sep 2017, Hamburg, Germany. pp.302-310, ⟨10.1007/978-3-319-66926-7_35⟩. ⟨hal-01707253⟩