MVGCN: Multi-View Graph Convolutional Neural Network for Surface Defect Identification Using Three-Dimensional Point Cloud
Journal of Manufacturing Science and Engineering · 01.03.2023 · 145 (3)
DOI: 10.1115/1.4056005 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Manufacturing Science and Engineering, online erschienen am 02.12.2022. Verfasst von Yinan Wang und 4 weiteren Autor:innen. Die Arbeit wurde bisher 45-mal zitiert (Crossref) und nennt 41 Literaturangaben. Gefördert von: National Science Foundation, Office of Naval Research.
Abstract (Originalsprache)
Surface defect identification is a crucial task in many manufacturing systems, including automotive, aircraft, steel rolling, and precast concrete. Although image-based surface defect identification methods have been proposed, these methods usually have two limitations: images may lose partial information, such as depths of surface defects, and their precision is vulnerable to many factors, such as the inspection angle, light, color, noise, etc. Given that a three-dimensional (3D) point cloud can precisely represent the multidimensional structure of surface defects, we aim to detect and classify surface defects using a 3D point cloud. This has two major challenges: (i) the defects are often sparsely distributed over the surface, which makes their features prone to be hidden by the normal surface and (ii) different permutations and transformations of 3D point cloud may represent the same surface, so the proposed model needs to be permutation and transformation invariant. In this paper, a two-step surface defect identification approach is developed to investigate the defects’ patterns in 3D point cloud data. The proposed approach consists of an unsupervised method for defect detection and a multi-view deep learning model for defect classification, which can keep track of the features from both defective and non-defective regions. We prove that the proposed approach is invariant to different permutations and transformations. Two case studies are conducted for defect identification on the surfaces of synthetic aircraft fuselage and the real precast concrete specimen, respectively. The results show that our approach receives the best defect detection and classification accuracy compared with other benchmark methods.
Förderung
- National Science Foundation
- Office of Naval Research
Zitieren
APA
Wang, Y., Sun, W., Jin, J. J., Kong, Z. J., & Yue, X. (2023). MVGCN: Multi-View Graph Convolutional Neural Network for Surface Defect Identification Using Three-Dimensional Point Cloud. Journal of Manufacturing Science and Engineering, 145(3). https://doi.org/10.1115/1.4056005
Vancouver
Wang Y, Sun W, Jin JJ, Kong ZJ, Yue X. MVGCN: Multi-View Graph Convolutional Neural Network for Surface Defect Identification Using Three-Dimensional Point Cloud. Journal of Manufacturing Science and Engineering. 2023;145(3). doi:10.1115/1.4056005
BibTeX
@article{Wang2023,
author = {Wang, Yinan and Sun, Wenbo and Jin, Jionghua (Judy) and Kong, Zhenyu (James) and Yue, Xiaowei},
title = {MVGCN: Multi-View Graph Convolutional Neural Network for Surface Defect Identification Using Three-Dimensional Point Cloud},
journal = {Journal of Manufacturing Science and Engineering},
year = {2023},
volume = {145},
number = {3},
doi = {10.1115/1.4056005}
}
EUVIMED