Knowledge Graphs in Digital Twins for AI in Production - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2021

Knowledge Graphs in Digital Twins for AI in Production

Pieter Lietaert
  • Fonction : Auteur
  • PersonId : 1237538
Bart Meyers
  • Fonction : Auteur
Johan Van Noten
  • Fonction : Auteur
Joren Sips
  • Fonction : Auteur
Klaas Gadeyne
  • Fonction : Auteur

Résumé

AI is increasingly penetrating the production industry. Today, however, AI is still used in a limited way in a production environment, often focusing on a single production step and using out-of-the-box AI algorithms. AI models that use information spanning a complete production line and even larger parts of the product lifecycle could add significant value for production companies. In this paper, we suggest a digital twin architecture to support the complete AI lifecycle (discovering correlations, learning, deploying and validating), based on a knowledge graph that centralizes all information. We show how this digital twin could ease information access to different heterogenous data sources and pose opportunities for a wider application of AI in production industry. We illustrate this approach using a simplified industrial example of a compressor housing production, leading to preliminary results that show how a data scientist can efficiently access, through the knowledge graph, all necessary data for the creation of an AI model.
Fichier principal
Vignette du fichier
509923_1_En_26_Chapter.pdf (943.13 Ko) Télécharger le fichier
Origine : Accord explicite pour ce dépôt

Dates et versions

hal-04030403 , version 1 (16-03-2023)

Licence

Paternité

Identifiants

Citer

Pieter Lietaert, Bart Meyers, Johan Van Noten, Joren Sips, Klaas Gadeyne. Knowledge Graphs in Digital Twins for AI in Production. IFIP International Conference on Advances in Production Management Systems (APMS), Sep 2021, Nantes, France. pp.249-257, ⟨10.1007/978-3-030-85874-2_26⟩. ⟨hal-04030403⟩
10 Consultations
11 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More