Hostname: page-component-cd9895bd7-dk4vv Total loading time: 0 Render date: 2024-12-26T20:34:09.312Z Has data issue: false hasContentIssue false
  • English
  • Français

A New Projection Based Method for the Classification of Mechanical Components Using Convolutional Neural Networks

Published online by Cambridge University Press:  26 May 2022

S. Bickel ,
B. Schleich  and
S. Wartzack
S. Bickel*
Affiliation:
Friedrich-Alexander-Universität Erlangen-Nürnberg, Germany
B. Schleich
Affiliation:
Friedrich-Alexander-Universität Erlangen-Nürnberg, Germany
S. Wartzack
Affiliation:
Friedrich-Alexander-Universität Erlangen-Nürnberg, 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.

Digital engineering is increasingly established in the industrial routine. Especially the application of machine learning on geometry data is a growing research issue. Driven by this, the paper presents a new method for the classification of mechanical components, which utilizes the projection of points onto a spherical detector surfaces to transfer the geometries into matrices. These matrices are then classified using deep learning networks. Different types of projection are examined, as are several deep learning models. Finally, a benchmark dataset is used to demonstrate the competitiveness.

Keywords

data-driven designartificial intelligence (AI)data miningdeep learningpart classification
Type
Article
Information
Proceedings of the Design Society , Volume 2: DESIGN2022 , May 2022 , pp. 1501 - 1510
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), 2022.

References

Bickel, S., Sauer, C., Schleich, B. and Wartzack, S. (2020). Comparing CAD part models for geometrical similarity: A concept using machine learning algorithms. In Procedia CIRP (Eds.), Proceedings of the CIRPe 2020 - 8th CIRP Global Web Conference - (pp. 133–138).Google Scholar
Bickel, S., Schleich, B. and Wartzack, S. (2021). Detection and Classification of Symbols in Principle Sketches using Deep Learning. In Cambridge University Press (Eds.), Proceedings of the International Conference on Engineering Design (ICED21) (pp. 1183 - 1192). Gothenburg, SE: Cambridge University Press. doi: 10.1017/pds.2021.118CrossRefGoogle Scholar
Bickel, S., Spruegel, T., Schleich, B. and Wartzack, S. (2019). How Do Digital Engineering and Included AI Based Assistance Tools Change the Product Development Process and the Involved Engineers. Proceedings of the Design Society: International Conference on Engineering Design, 1(1), 2567–2576. 10.1017/dsi.2019.263Google Scholar
Brock, A., Lim, T., Ritchie, J. and Weston, N. (2016). Generative and Discriminative Voxel Modeling with Convolutional Neural Networks.Google Scholar
Deng, J. et al. ., 2009. ImageNet: A large-scale hierarchical image database. In 2009 IEEE conference on computer vision and pattern recognition. pp. 248–255. doi: 10.1109/CVPR.2009.5206848CrossRefGoogle Scholar
Fawcett, T. (2006). An introduction to ROC analysis. Pattern Recognition Letters, 27(8), 861–874. 10.1016/j.patrec.2005.10.010.Google Scholar
Furuya, T. and Ohbuchi, R. (2016). Deep Aggregation of Local 3D Geometric Features for 3D Model Retrieval. In Wilson, Richard C., Hancock, Edwin R. and Smith, William A. P., editors, Proceedings of the British Machine Vision Conference (BMVC), pages 121.1–121.12. BMVA Press, doi: 10.5244/C.30.121CrossRefGoogle Scholar
He, K., Zhang, X., Ren, S. and Sun, J. (2015), Deep Residual Learning for Image Recognition, CoRR, abs/1512.03385. 10.1109/CVPR.2016.90Google Scholar
Huang, G., Liu, Z. and Weinberger, K. (2016), Densely Connected Convolutional Networks, CoRR, abs/1608.06993. 10.1109/CVPR.2017.243Google Scholar
Kanezaki, A., Matsushita, Y. and Nishida, Y. (2018). RotationNet: Joint Object Categorization and Pose Estimation Using Multiviews from Unsupervised Viewpoints. CVPR, pp.5010–5019, 10.1109/CVPR.2018.00526Google Scholar
Kestel, P., Kügler, P., Zirngibl, C., Schleich, B. and Wartzack, S. (2019). Ontology-based approach for the provision of simulation knowledge acquired by Data and Text Mining processes. Advanced Engineering Informatics, 39, 292–305.10.1016/j.aei.2019.02.001Google Scholar
Kim, Sangpil, Chi, Hyung-gun, Hu, Xiao, Huang, Qixing, Ramani, Karthik (2020): A Large-scale Annotated Mechanical Components Benchmark for Classification and Retrieval Tasks with Deep Neural Networks. In: Proceedings of 16th European Conference on Computer Vision (ECCV).Google Scholar
Krizhevsky, A., Sutskever, I. and Hinton, G. (2012). Imagenet classification with deep convolutional neural networks. In NIPS. 10.1145/3065386Google Scholar
Simonyan, K., Zissermann, A. (2014). Very deep convolutional networks for large-scale image recognition, arXiv:1409.1556, 2014.Google Scholar
Spruegel, T., Bickel, S., Schleich, B. and Wartzack, S. (2021). Approach and application to transfer heterogeneous simulation data from finite element analysis to neural networks. Journal of Computational Design and Engineering, Volume 8(1), 298–315. 10.1093/jcde/qwaa079Google Scholar
Spruegel, T. and Wartzack, S. (2015). Concept and application of automatic part-recognition with artificial neural networks for FE simulations. In Weber, C.; Husung, S.; Cantamessa, M.; Cascini, G.; Marjanovic, D.; Graziosi, S. (Eds.), Proceedings of the 20th International Conference on Engineering Design (ICED15) (pp. 183-193). Mailand, IT.Google Scholar
Su, H., Maji, S., Kalogerakis, E. and Learned-Miller, E. (2015). Multi-view convolutional neural networks for 3d shape recognition. 10.1109/ICCV.2015.114CrossRefGoogle Scholar
Szegedy, C., Ioffe, S. and Vanhoucke, V. (2016), Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning, CoRR, abs/1602.07261.Google Scholar
Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J. and Wojna, Z. (2015), Rethinking the Inception Architecture for Computer Vision, CoRR, abs/1512.00567. 10.1109/CVPR.2016.308Google Scholar
Qi, C. R., Su, H., Mo, K., and Guibas, L. J. (2016) Pointnet: Deep learning on point sets for 3d classification and segmentation. arXiv preprint arXiv:1612.00593. 10.1109/CVPR.2017.16Google Scholar
Qi, C. R., Yi, L., Su, H., and Guibas, L. J. (2017) Pointnet++: Deep hierarchical feature learning on point sets in a metric space. arXiv preprint arXiv:1706.02413Google Scholar
Qie, Y., Bickel, S., Wartzack, S., Schleich, B. and Anwer, N. (2021). A function-oriented surface reconstruction framework for reverse engineering. CIRP Annals - Manufacturing Technology, 70(1), 135–138. 10.1016/j.cirp.2021.04.016CrossRefGoogle Scholar
Wu, Z., Song, S., Khosla, A., Yu, F., Zhang, L., Tang, X. and Xiao, J. (2015). 3D ShapeNets: A Deep Representation for Volumetric Shapes, Proceedings of 28th IEEE Conference on Computer Vision and Pattern Recognition (CVPR2015), doi: 10.1109/CVPR.2015.7298801CrossRefGoogle Scholar
Xu, Y., Fan, T., Xu, M., Zeng, L. and Qiao, Y. (2018). SpiderCNN: Deep Learning on Point Sets with Parameterized Convolutional Filters.Google Scholar