Knowledge Graphs in Digital Twins for AI in Production

Lietaert, Pieter; Meyers, Bart; Noten, Johan Van; Sips, Joren; Gadeyne, Klaas

doi:10.1007/978-3-030-85874-2_26

Cited by 8 publications

(2 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, a data scientist, or any other engineer, that wants to investigate this data, is confronted with this heterogeneity and will spend considerable time searching for the correct data, thereby also trying to understand its context. In order to reduce this effort, in this work, we use a knowledge graph, which acquires and integrates information into a semantic data model and uses this data model to provide central information access for data scientists [37]. The knowledge graph is integrated in the digital twin, as shown in the architecture in Figure 2.…”

Section: Knowledge Graphmentioning

confidence: 99%

Development and deployment of a digital twin for monitoring of an adaptive clamping mechanism, used for high performance composite machining

Weckx

Meyers

Jordens

et al. 2022

IET Collab Intel Manufact

Self Cite

View full text Add to dashboard Cite

In this work, we present a cloud‐based digital twin for monitoring of a clamping technology for machining of composite parts. Supporting large and/or freeform composite parts is crucial to avoid bending during drilling. Bending of the part will lead to delamination and frayed edges of the drilled holes. The new active clamping technology allows to realise a stabilised fixture, localised in the area where the drilling occurs, to avoid bending. This significantly improves the quality of the drilled holes. The clamping device is equipped with an IoT edge device, with a bidirectional communication to the cloud. The cloud‐based digital twin analyses the quality of the drilled holes based on computer vision, monitors the drill wear and detects incorrect operation of the active clamping device. All data is stored in the cloud. By means of a knowledge graph, which acquires and integrates information into an ontology and provides a central information access, it will be easier for a data scientist to query this data and to gain new insights in the operation of the drill with active clamping device. The full deployment occurs on the Microsoft Azure cloud platform. This transforms the standard machine into an Industry 4.0 compliant machine.

show abstract

Section: Knowledge Graphmentioning

confidence: 99%

Development and deployment of a digital twin for monitoring of an adaptive clamping mechanism, used for high performance composite machining

Weckx

Meyers

Jordens

et al. 2022

IET Collab Intel Manufact

Self Cite

View full text Add to dashboard Cite

show abstract

“…Similarly, Kalayci et al [17] shows how to manage industry data with semantic models. Lietaert et al [21] presents a Digital Twin architecture for Industry 4.0. Chevallier et al [10] proposes one for Smart Buildings.…”

Section: State Of the Artmentioning

confidence: 99%

Scaling Knowledge Graphs for Automating AI of Digital Twins

Ploennigs

Semertzidis

Lorenzi

et al. 2022

The Semantic Web – ISWC 2022

View full text Add to dashboard Cite

Digital Twins are digital representations of systems in the Internet of Things (IoT) that are often based on AI models that are trained on data from those systems. Semantic models are used increasingly to link these datasets from different stages of the IoT systems life-cycle together and to automatically configure the AI modelling pipelines. This combination of semantic models with AI pipelines running on external datasets raises unique challenges particular if rolled out at scale. Within this paper we will discuss the unique requirements of applying semantic graphs to automate Digital Twins in different practical use cases. We will introduce the benchmark dataset DTBM that reflects these characteristics and look into the scaling challenges of different knowledge graph technologies. Based on these insights we will propose a reference architecture that is in-use in multiple products in IBM and derive lessons learned for scaling knowledge graphs for configuring AI models for Digital Twins.

show abstract