There is rising demand for automated digital twin construction based on point cloud scans, especially in the domain of industrial facilities. Yet, current automation approaches focus almost exclusively on geometric modelling. The output of these methods is a disjoint cluster of individual elements, while element relationships are ignored. This research demonstrates the feasibility of adopting Graph Neural Networks (GNN) for automated detection of connectivity relationships between elements in industrial facility scans. We propose a novel method which represents elements and relationships as graph nodes and edges respectively. Element geometry is encoded into graph node features. This allows relationship inference to be modelled as a graph link prediction task. We thereby demonstrate that connectivity relationships can be learned from existing design files, without requiring domain specific, hand-coded rules, or manual annotations. Preliminary results show that our method performs successfully on a synthetic point cloud testset generated from design files with a 0.64 F1 score. We further demonstrate that the method adapts to occluded real-world scans. The method can be further extended with the introduction of more descriptive node features. Additionally, we present tools for relationship annotation and visualisation to aid relationship detection
University of Cambridge, United Kingdom - ORCID: 0000-0002-6236-8092
University of Cambridge, United Kingdom - ORCID: 0000-0003-1829-2083
Titolo del capitolo
Topological Relationship Modelling for Industrial Facility Digitisation Using Graph Neural Networks
Autori
Haritha Jayasinghe, Ioannis Brilakis
DOI
10.36253/979-12-215-0289-3.88
Opera sottoposta a peer review
Anno di pubblicazione
2023
Copyright
© 2023 Author(s)
Licenza d'uso
Licenza dei metadati
Titolo del libro
CONVR 2023 - Proceedings of the 23rd International Conference on Construction Applications of Virtual Reality
Sottotitolo del libro
Managing the Digital Transformation of Construction Industry
Curatori
Pietro Capone, Vito Getuli, Farzad Pour Rahimian, Nashwan Dawood, Alessandro Bruttini, Tommaso Sorbi
Opera sottoposta a peer review
Anno di pubblicazione
2023
Copyright
© 2023 Author(s)
Licenza d'uso
Licenza dei metadati
Editore
Firenze University Press
DOI
10.36253/979-12-215-0289-3
eISBN (pdf)
979-12-215-0289-3
eISBN (xml)
979-12-215-0257-2
Collana
Proceedings e report
ISSN della collana
2704-601X
e-ISSN della collana
2704-5846