• français
    • English
    français
  • Login
Help
View Item 
  •   Home
  • Laboratoire d’Ingénierie des Systèmes Physiques Et Numériques (LISPEN)
  • View Item
  • Home
  • Laboratoire d’Ingénierie des Systèmes Physiques Et Numériques (LISPEN)
  • View Item
JavaScript is disabled for your browser. Some features of this site may not work without it.

Multi-part kinematic constraint prediction for automatic generation of CAD model assemblies using graph convolutional networks

Article dans une revue avec comité de lecture
Author
VERGEZ, Lucas
543315 Laboratoire d’Ingénierie des Systèmes Physiques et Numériques [LISPEN]
1003434 Arts et Métiers Sciences et Technologies
ccPOLETTE, Arnaud
1003434 Arts et Métiers Sciences et Technologies
543315 Laboratoire d’Ingénierie des Systèmes Physiques et Numériques [LISPEN]
ccPERNOT, Jean-Philippe
543315 Laboratoire d’Ingénierie des Systèmes Physiques et Numériques [LISPEN]
1003434 Arts et Métiers Sciences et Technologies

URI
http://hdl.handle.net/10985/26195
DOI
10.1016/j.cad.2024.103805
Date
2025-01
Journal
Computer-Aided Design

Abstract

This paper presents a machine learning-based approach to predict kinematic constraints between CAD models that have potentially never been assembled together before. During the learning phase, the algorithm is trained to predict the next-possible-constraints between a set of parts candidate to the assembly. Assemblies are represented in a new graph-based formalism that is capable of capturing features associated with parts, interfaces between parts and constraints between them. Using such a multi-level feature extraction strategy coupled to a state-by-state graph decomposition, the approach does not need to be trained on a large database. This formalism is used to model both the network input and output where the next-possibleconstraints appear after evaluation. The core of the approach relies on a series of networks based on a link-prediction encoder–decoder architecture, integrating the capabilities of several convolutional networks trained in an end-to-end manner. A decision-making algorithm is added to post-process the output and drive the prediction process in finding one among the set of next-possible-constraints. This process is repeated until no more constraints can be added. The experimental results show that the proposed approach outperforms state-of-the-art methods on such assembly tasks. Although the state-by-state assembly algorithm is iterative, it still takes into account the whole set of parts as well as the whole set of constraints already predicted, and this makes it possible to handle constraint cycles, which is generally not possible when not considering multiple parts as input.

Files in this item

Name:
LISPEN_CAD_2024_PERNOT_2.pdf
Size:
3.144Mb
Format:
PDF
Embargoed until:
2025-07-01
View/Open

Collections

  • Laboratoire d’Ingénierie des Systèmes Physiques Et Numériques (LISPEN)

Related items

Showing items related by title, author, creator and subject.

  • Automatic CAD Assemblies Generation by Linkage Graph Overlay for Machine Learning Applications 
    Article dans une revue avec comité de lecture
    VERGEZ, Lucas; ccPERNOT, Jean-Philippe; ccPOLETTE, Arnaud (CAD Solutions, LLC, 2021-11-29)
    This paper introduces an approach to synthetize new CAD assemblies from existing STEP files. The algorithm first generates linkage graph by detecting linkage between components. Then it detects linkages similarities ...
  • Automatic CAD Assemblies Generation by Linkage Graph Overlay for Machine Learning Applications 
    Communication avec acte
    VERGEZ, Lucas; ccPERNOT, Jean-Philippe; ccPOLETTE, Arnaud (CAD, 2021-07-05)
    Enlarging 3D model databases by shape synthesis is a large field of research. Indeed, the use of machine learning techniques requires a huge amount of labeled CAD models, and it is therefore crucial to rely on large ...
  • Interface-Based Search and Automatic Reassembly of CAD Models for Database Expansion and Model Reuse 
    Article dans une revue avec comité de lecture
    VERGEZ, Lucas; ccPOLETTE, Arnaud; ccPERNOT, Jean-Philippe (Elsevier BV, 2024-02)
    This paper introduces a new framework for reassembling CAD models of mechanical parts. The generated CAD assemblies are well-constrained, with collision-free parts, and they are ready-to-use for downstream applications. ...
  • Survey on the View Planning Problem for Reverse Engineering and Automated Control Applications 
    Article dans une revue avec comité de lecture
    PEUZIN-JUBERT, Manon; NOZAIS, Dominique; MARI, Jean-Luc; ccPERNOT, Jean-Philippe; ccPOLETTE, Arnaud (Elsevier BV, 2021-12)
    At present, optical sensors are being widely used to realize high quality control or reverse engineering of products, systems, buildings, environments or human bodies. Although the intrinsic characteristics of such ...
  • A Data Structure for Developing Data-Driven Digital Twins 
    Ouvrage scientifique
    ORUKELE, Oghenemarho; ccPOLETTE, Arnaud; GONZALEZ LORENZO, Aldo; MARI, Jean-Luc; ccPERNOT, Jean-Philippe (Springer Nature Switzerland, 2024-06)
    Digital twins have the potential to revolutionize the way we design, build and maintain complex systems. They are high-fidelity representations of physical assets in the digital space and thus allow advanced simulations ...

Browse

All SAMCommunities & CollectionsAuthorsIssue DateCenter / InstitutionThis CollectionAuthorsIssue DateCenter / Institution

Newsletter

Latest newsletterPrevious newsletters

Statistics

Most Popular ItemsStatistics by CountryMost Popular Authors

ÉCOLE NATIONALE SUPERIEURE D'ARTS ET METIERS

  • Contact
  • Mentions légales

ÉCOLE NATIONALE SUPERIEURE D'ARTS ET METIERS

  • Contact
  • Mentions légales