Hostname: page-component-586b7cd67f-t8hqh Total loading time: 0 Render date: 2024-11-22T17:55:22.434Z Has data issue: false hasContentIssue false
  • English
  • Français

EXPLICIT ANNOTATED 3D-CNN DEEP LEARNING OF GEOMETRIC PRIMITIVES INSTANCES

Published online by Cambridge University Press:  19 June 2023

Arthur Hilbig ,
Stefan Holtzhausen  and
Kristin Paetzold-Byhain
Arthur Hilbig*
Affiliation:
Technische Universität Dresden, Chair of Virtual Product Development
Stefan Holtzhausen
Affiliation:
Technische Universität Dresden, Chair of Virtual Product Development
Kristin Paetzold-Byhain
Affiliation:
Technische Universität Dresden, Chair of Virtual Product Development
*
Hilbig, Arthur, Technische Universität Dresden, Germany, [email protected]

Abstract

Core share and HTML view are not available for this content. However, as you have access to this content, a full PDF is available via the ‘Save PDF’ action button.

In reengineering technical components, the robust automation of reverse engineering (RE) could overcome the need for human supervision in the surface reconstruction process. Therefore, an enhanced computer-based geometric reasoning to derive tolerable surface deviations for reconstructing optimal surface models would promote a deeper geometric understanding of RE downstream processes. This approach integrates advanced surface information into a deep learning-based recognition framework by explicitly labeling geometric outliers and subsurface boundaries. For this purpose, a synthetic dataset is created that morphs nominal surface models to resemble the macroscopic surface pattern of physical components. For the detection of regular geometry primitives, a 3D-CNN is used to analyze the voxelized components based on signed distance field data. This explicit labeling approach enables surface fitting to derive suitable shape features that fulfill the underlying surface constraints.

Keywords

Reverse EngineeringSurface ReconstructionMachine learningComputer Aided Design (CAD)Artificial intelligence
Type
Article
Information
Proceedings of the Design Society , Volume 3: ICED23 , July 2023 , pp. 1775 - 1784
Creative Commons
Creative Common License - CCCreative Common License - BYCreative Common License - NCCreative Common License - ND
This is an Open Access article, distributed under the terms of the Creative Commons Attribution-NonCommercial-NoDerivatives licence (http://creativecommons.org/licenses/by-nc-nd/4.0/), which permits non-commercial re-use, distribution, and reproduction in any medium, provided the original work is unaltered and is properly cited. The written permission of Cambridge University Press must be obtained for commercial re-use or in order to create a derivative work.
Copyright
The Author(s), 2023. Published by Cambridge University Press

References

Agathos, A., Pratikakis, I., Perantonis, S., Sapidis, N. and Azariadis, P. (2007), “3D Mesh Segmentation Methodologies for CAD applications”, Computer-Aided Design and Applications, Vol. 4 No. 6, pp. 827–841. http://doi.org/10.1080/16864360.2007.10738515.CrossRefGoogle Scholar
Ali, S., Durupt, A. and Adragna, P.A. (2013), “Reverse Engineering for Manufacturing Approach: Based on the Combination of 3D and Knowledge Information”, Smart Product Engineering, Lecture Notes in Production Engineering, pp. 137–146. http://doi.org/10.1007/978-3-642-30817-8_14.CrossRefGoogle Scholar
Attene, M., Falcidieno, B. and Spagnuolo, M. (2006), “Hierarchical mesh segmentation based on fitting primitives”, The Visual Computer, Vol. 22 No. 3, pp. 181–193. http://doi.org/10.1007/s00371-006-0375-x.CrossRefGoogle Scholar
Aydin, O.U., Taha, A.A., Hilbert, A., Khalil, A.A., Galinovic, I., Fiebach, J.B., Frey, D. and Madai, V.I. (2021), “On the usage of average Hausdorff distance for segmentation performance assessment: hidden error when used for ranking”, European radiology experimental, Vol. 5 No. 1, p. 4. http://doi.org/10.1186/s41747-020-00200-2.CrossRefGoogle ScholarPubMed
Bici, M., Mohammadi, S.S. and Campana, F. (2020), “A Compared Approach on How Deep Learning May Support Reverse Engineering for Tolerance Inspection”, Proceedings of the ASME International Mechanical Engineering Congress and Exposition - 2019, November 8-14, 2019, Salt Lake City, Utah, USA. http://doi.org/10.1115/IMECE2019-11325.CrossRefGoogle Scholar
Buonamici, F., Carfagni, M., Furferi, R., Governi, L., Lapini, A. and Volpe, Y. (2018), “Reverse engineering modeling methods and tools: a survey”, Computer-Aided Design and Applications, Vol. 15 No. 3, pp. 443–464. http://doi.org/10.1080/16864360.2017.1397894.CrossRefGoogle Scholar
Chikofsky, E.J. and Cross, J.H. II (1990), “Reverse engineering and design recovery: a taxonomy”, IEEE Software, Vol. 7 No. 1, pp. 13–17. http://doi.org/10.1109/52.43044.CrossRefGoogle Scholar
DIN 2769: Toleranzen für Längen - und Winkelgrößenmaße ohne individuelle Toleranzangaben No. 2769, Beuth Verlag GmbH, Berlin.Google Scholar
Fayolle, P.-A. and Pasko, A. (2016), “An evolutionary approach to the extraction of object construction trees from 3D point clouds”, Computer-Aided Design, Vol. 74, pp. 1–17. http://doi.org/10.1016/j.cad.2016.01.001.CrossRefGoogle Scholar
Geng, Z., Sabbaghi, A. and Bidanda, B. (2022), “A framework of tolerance specification for freeform point clouds and capability analysis for reverse engineering processes”, International Journal of Production Research, Vol. 60 No. 24, pp. 7475–7491. http://doi.org/10.1080/00207543.2022.2086083.CrossRefGoogle Scholar
Guo, Y., Wang, H., Hu, Q., Liu, H., Liu, L. and Bennamoun, M. (2021), “Deep Learning for 3D Point Clouds: A Survey”, IEEE transactions on pattern analysis and machine intelligence, Vol. 43 No. 12, pp. 4338–4364. http://doi.org/10.1109/TPAMI.2020.3005434.CrossRefGoogle ScholarPubMed
Hong-Seok, P. and Mani, T.U. (2014), “Development of an Inspection System for Defect Detection in Pressed Parts Using Laser Scanned Data”, Procedia Engineering, Vol. 69, pp. 931–936. http://doi.org/10.1016/j.proeng.2014.03.072.CrossRefGoogle Scholar
Kaisarlis, G.J., Diplaris, S.C. and Sfantsikopoulos, M.M. (2008), “Geometrical position tolerance assignment in reverse engineering”, International Journal of Computer Integrated Manufacturing, Vol. 21 No. 1, pp. 89–96. http://doi.org/10.1080/09511920601164140.CrossRefGoogle Scholar
Kaiser, A., Ybanez Zepeda, J.A. and Boubekeur, T. (2019), “A Survey of Simple Geometric Primitives Detection Methods for Captured 3D Data”, Computer Graphics Forum, Vol. 38 No. 1, pp. 167–196. http://doi.org/10.1111/cgf.13451.CrossRefGoogle Scholar
Li, L., Sung, M., Dubrovina, A., Yi, L. and Guibas, L. (2019), “Supervised Fitting of Geometric Primitives to 3D Point Clouds”, pp. 2647–2655. http://doi.org/10.1109/CVPR.2019.00276.CrossRefGoogle Scholar
Ping, G., Esfahani, M.A. and Wang, H. (2020), “Unsupervised 3D Primitive Shape Detection using Mathematical Models”, 2020 16th International Conference on Control, Automation, Robotics and Vision (ICARCV), pp. 178–183. http://doi.org/10.1109/ICARCV50220.2020.9305494.CrossRefGoogle Scholar
Qie, Y., Bickel, S., Wartzack, S., Schleich, B. and Anwer, N. (2021), “A function-oriented surface reconstruction framework for reverse engineering”, CIRP Annals, Vol. 70 No. 1, pp. 135–138. http://doi.org/10.1016/j.cirp.2021.04.016.CrossRefGoogle Scholar
Schnabel, R., Wahl, R. and Klein, R. (2007), “Efficient RANSAC for Point-Cloud Shape Detection”, Computer Graphics Forum, Volume 26, Issue 2, pp. 214–226. http://doi.org/10.1111/j.1467-8659.2007.01016.x.CrossRefGoogle Scholar
Schöne, C. (2009), “Reverse Engineering für Freiformflächen in Prozessketten der Produktionstechnik”, Habilitation, Technische Universität Dresden, Dresden, 2009.Google Scholar
Shah, G.A., Polette, A., Pernot, J.-P., Giannini, F. and Monti, M. (2022), “User-Driven Computer-Assisted Reverse Engineering of Editable CAD Assembly Models”, Journal of Computing and Information Science in Engineering, Vol. 22 No. 2. http://doi.org/10.1115/1.4053150.CrossRefGoogle Scholar
Sharma, G., Liu, D., Maji, S., Kalogerakis, E., Chaudhuri, S. and Měch, R. (2020), “ParSeNet: A Parametric Surface Fitting Network for 3D Point Clouds”, Computer Vision – ECCV 2020, Lecture Notes in Computer Science, Vol. 12352, pp. 261–276. http://doi.org/10.1007/978-3-030-58571-6_16.CrossRefGoogle Scholar
Shi, P., Qi, Q., Qin, Y., Scott, P.J. and Jiang, X. (2022), “Highly interacting machining feature recognition via small sample learning”, Robotics and Computer-Integrated Manufacturing, Vol. 73, p. 102260. http://doi.org/10.1016/j.rcim.2021.102260.CrossRefGoogle Scholar
Takashima, H. and Kanai, S. (2021), “Recognition of Free-form Features for Finite Element Meshing using Deep Learning”, Computer-Aided Design and Applications, Vol. 19 No. 4, pp. 677–693. http://doi.org/10.14733/cadaps.2022.677-693.CrossRefGoogle Scholar
Várady, T., Martin, R.R. and Cox, J. (1997), “Reverse engineering of geometric models—an introduction”, Computer-Aided Design, Vol. 29 No. 4, pp. 255–268. http://doi.org/10.1016/S0010-4485(96)00054-1.CrossRefGoogle Scholar
Wang, Z. and Lu, F. (2018), VoxSegNet: Volumetric CNNs for Semantic Part Segmentation of 3D Shapes, available at: http://arxiv.org/pdf/1809.00226v1.Google Scholar
Wong, V.W.H., Ferguson, M., Law, K.H., Lee, Y.-T.T. and Witherell, P. (2020), “Automatic Volumetric Segmentation of Additive Manufacturing Defects with 3D U-Net”, AAAI 2020 Spring Symposia. http://doi.org/.Google Scholar
Woodford, O.J., Pham, M.-T., Maki, A., Perbet, F. and Stenger, B. (2014), “Demisting the Hough Transform for 3D Shape Recognition and Registration”, International Journal of Computer Vision, Vol. 106 No. 3, pp. 332–341. http://doi.org/10.1007/s11263-013-0623-2.CrossRefGoogle Scholar
Xie, Y., Tian, J. and Zhu, X.X. (2020), “Linking Points With Labels in 3D: A Review of Point Cloud Semantic Segmentation”, IEEE Geoscience and Remote Sensing Magazine, Vol. 8 No. 4, pp. 38–59. http://doi.org/10.1109/MGRS.2019.2937630.CrossRefGoogle Scholar
Yan, S., Yang, Z., Ma, C., Huang, H., Vouga, E. and Huang, Q. (2021), HPNet: Deep Primitive Segmentation Using Hybrid Representations, available at: http://arxiv.org/pdf/2105.10620v3.CrossRefGoogle Scholar
Zhang, Z., Jaiswal, P. and Rai, R. (2018), “FeatureNet: Machining feature recognition based on 3D Convolution Neural Network”, Computer-Aided Design, Vol. 101, pp. 12–22. http://doi.org/10.1016/j.cad.2018.03.006.CrossRefGoogle Scholar