MeshCNN-based BREP to CSG conversion algorithm for 3D CAD models and its application

Yue-Tong Luo; Hua Du; Yi-Man Yan

doi:10.1007/s41365-022-01063-5

Your Location：

Home >

Browse articles >

MeshCNN-based BREP to CSG conversion algorithm for 3D CAD models and its application

NUCLEAR ENERGY SCIENCE AND ENGINEERING | Updated：2022-07-27

- MeshCNN-based BREP to CSG conversion algorithm for 3D CAD models and its application
- MeshCNN-based BREP to CSG conversion algorithm for 3D CAD models and its application
- Nuclear Science and Techniques 2022年33卷第6期文章编号：74
- Affiliations：
  
  1.Hefei University of Technology, Hefei 230009, China
  2.University of Science and Technology of China, Hefei 230027, China
  3.Institute of Plasma Physics, Hefei Institutes of Physical Science, Chinese Academy of Sciences, Hefei 230031, China
  4.State Power Investment Corporation Research Institute, National Energy Key Laboratory of Nuclear Power Software, Beijing 102209, China
- Author bio：
  
  ytluo@hfut.edu.cn
- Funds：
  
  National Key R&D Program of China(2019YFE03110000;2017YFE0300501);Chinese National Natural Science Foundation(11775256)
- DOI：10.1007/s41365-022-01063-5
  中图分类号：
Scan for full text
Yue-Tong Luo, Hua Du, Yi-Man Yan. MeshCNN-based BREP to CSG conversion algorithm for 3D CAD models and its application[J]. Nuclear Science and Techniques, 2022,33(6):74

Yue-Tong Luo, Hua Du, Yi-Man Yan. MeshCNN-based BREP to CSG conversion algorithm for 3D CAD models and its application[J]. Nuclear Science and Techniques, 2022,33(6):74
Yue-Tong Luo, Hua Du, Yi-Man Yan. MeshCNN-based BREP to CSG conversion algorithm for 3D CAD models and its application[J]. Nuclear Science and Techniques, 2022,33(6):74 DOI： 10.1007/s41365-022-01063-5.

Yue-Tong Luo, Hua Du, Yi-Man Yan. MeshCNN-based BREP to CSG conversion algorithm for 3D CAD models and its application[J]. Nuclear Science and Techniques, 2022,33(6):74 DOI： 10.1007/s41365-022-01063-5.

摘要

Abstract

In the field of neutronics analysis, it is imperative to develop computer-aided modeling technology for Monte Carlo (MC) codes to address the increasing complexity of reactor core components by converting 3D CAD model (boundary representation, BREP) to MC model (constructive solid geometry, CSG). Separation-based conversion from BREP to CSG is widely used in computer-aided modeling MC codes because of its high efficiency, reliability, and easy implementation. However, the current separation-based BREP-CSG conversion is poor for processing complex CAD models, and it is necessary to divide a complex model into several simple models before applying the separation-based conversion algorithm, which is time-consuming and tedious. To avoid manual segmentation, this study proposed a MeshCNN-based 3D-shape segmentation algorithm to automatically separate a complex model. The proposed 3D-shape segmentation algorithm was combined with separation-based BREP-CSG conversion algorithms to directly convert complex models. The proposed algorithm was integrated into the computer-aided modeling software cosVMPT and validated using the Chinese fusion engineering testing reactor model. The results demonstrate that the MeshCNN-based BREP-CSG conversion algorithm has a better performance and higher efficiency, particularly in terms of CPU time, and the conversion result is more intuitive and consistent with the intention of the modeler.

关键词

Keywords

BREP to CSG conversionComputer-aided modelingcosVMPTIntelligent pre-segmentationMeshCNN

references

K. Tang, T. Woo, Algorithmic aspects of alternating sum of volumes. Part 2: Nonvergence and its remedy. Comput. Aided Design 23, 435-443 (1991). doi: 10.1016/0010-4485(91)90011-Khttp://doi.org/10.1016/0010-4485(91)90011-K

V. Shapiro, D.L. Vossler, Separation for boundary to CSG conversion. ACM T. Graphic 12, 35-55 (1993). doi: 10.1145/169728.169723http://doi.org/10.1145/169728.169723

V. Shapiro, D.L. Vossler, Construction and optimization of CSG representations. Comput. Aided Design 23, 4-20 (1991). doi: 10.1016/0010-4485(91)90077-Ahttp://doi.org/10.1016/0010-4485(91)90077-A

S.F. Buchele, R.H. Crawford, Three-dimensional half-space constructive solid geometry tree construction from implicit boundary representations. Comput. Aided Design 36, 1063-1073 (2004). doi: 10.1016/j.cad.2004.01.006http://doi.org/10.1016/j.cad.2004.01.006

B.L. Kirk, Overview of Monte Carlo radiation transport codes. Radiat. Meas. 45, 1318-1322 (2010). doi: 10.1016/j.radmeas.2010.05.037http://doi.org/10.1016/j.radmeas.2010.05.037

Y.-T. Luo, Research on models conversion and its application in MCNP modeling. (Hefei University of Technology, 2005) (in Chinese).

L. Lu, Y. Li, A.-P. Ding et al., Application of MCAM in generating Monte Carlo model for ITER port limiter. Chinese Journal of Nuclear Science and Engineering 27, 3 (2007). doi: 10.3321/j.issn:0258-0918.2007.03.015http://doi.org/10.3321/j.issn:0258-0918.2007.03.015 (in Chinese)

Y. Li, L. Lu, A. Ding et al., Benchmarking of MCAM 4.0 with the ITER 3D model. Fusion Eng. Des. 82, 15-24 (2007). doi: 10.1016/j.fusengdes.2007.02.022http://doi.org/10.1016/j.fusengdes.2007.02.022

J. Xiong, G.-Z. Wang, D.-X. Wang et al., Applications of MCAM for ITER TRIPOLI 3D neutronics modeling. Chinese Journal of Nuclear Science and Engineering, 31, 162-168 (2011).

F. Moro, U. Fischer, L. Lei et al., Applications of McCad for the automatic generation of MCNP 3D models in fusion neutronics. Paper presented at 2013 IEEE 25th Symposium on Fusion Engineering(San Francisco, CA, USA 10-14, July. 2013). doi: 10.1109/SOFE.2013.6635377http://doi.org/10.1109/SOFE.2013.6635377

F. Moro, U. Fischer, L. Lu et al., The McCad code for the automatic generation of MCNP 3-D models: Applications in fusion neutronics. IEEE T. Plasma Sci. 42, 1036-1041 (2014). doi: 10.1109/TPS.2014.2308957http://doi.org/10.1109/TPS.2014.2308957

L. Lu, Y.F. Qiu, U. Fischer, Improved solid decomposition algorithms for the CAD-to-MC conversion tool McCad. Fusion Eng. Des. 124, 1269-1272 (2017). doi: 10.1016/j.fusengdes.2017.02.040http://doi.org/10.1016/j.fusengdes.2017.02.040

Y.-T. Luo, J. Sun, Y. Xue, Three-dimensional CSG tree construction from BREP model based on conversion feature. Modern Electronic Technology, 20 (2007). (in Chinese).

S.L. Liu, Y. Pu, X.M. Cheng et al., Conceptual design of a water cooled breeder blanket for CFETR. Fusion Eng. Des. 89, 1380-1385 (2014). doi: 10.1016/j.fusengdes.2014.01.065http://doi.org/10.1016/j.fusengdes.2014.01.065

S. Liu, X. Ma, K. Jiang et al., Conceptual design of the water cooled ceramic breeder blanket for CFETR based on pressurized water cooled reactor technology. Fusion Eng. Des. 124, 865-870 (2017). doi: 10.1016/j.fusengdes.2017.02.065http://doi.org/10.1016/j.fusengdes.2017.02.065

Y.T. Feng, Y.F. Feng, H.X. You et al., MeshNet: Mesh neural network for 3D shape representation. Paper presented at 2019 Thirty-third AAAI Conference on Artificial Intelligence(Hawaii, USA. J27 Jan. – 1 Feb. 2019). doi: 10.1609/aaai.v33i01.33018279http://doi.org/10.1609/aaai.v33i01.33018279

R. Hanocka, A. Hertz, N. Fish et al., MeshCNN: A network with an edge. ACM. T. Graphics 38, 90 (2019). doi: 10.1145/3306346.3322959http://doi.org/10.1145/3306346.3322959

Z.R. Wu, S.R. Song, A. Khosla et al., 3D ShapeNets: A deep representation for volumetric shapes. Paper presented at 2015 IEEE Conference on Computer Vision and Pattern Recognition (USA, Jun. 08 - 10, 2015). doi: 10.1109/CVPR.2015.7298801http://doi.org/10.1109/CVPR.2015.7298801

A. Angrish, A. Bharadwaj, B. Starly, MVCNN++: Computer-aided design model shape classification and retrieval using multi-view convolutional neural networks. J. Comput. Inf. Sci. Eng. 21, 011001 (2021). doi: 10.1115/1.4047486http://doi.org/10.1115/1.4047486

R. Qi Charles, H. Su, M. Kaichun et al., PointNet: Deep learning on point sets for 3D classification and segmentation. Paper presented at 2017 IEEE Conference on Computer Vision and Pattern Recognition (Hawaii, USA. 21-26 July, 2017). doi: 10.1109/CVPR.2017.16http://doi.org/10.1109/CVPR.2017.16

H. Du, Y.T. Luo, C.C. Han et al., Development of an assistant program for CAD-to-cosRMC modelling. Fusion Eng. Des. 157, 111662 (2020). doi: 10.1016/j.fusengdes.2020.111662http://doi.org/10.1016/j.fusengdes.2020.111662

H. Du, Q.R. Wu, P. Lu et al., Development of cosVMPT and application of creating 3D neutronics model for 360-degree CFETR. J. Fusion Energ. 40, 2 (2021). doi: 10.1007/s10894-021-00299-0http://doi.org/10.1007/s10894-021-00299-0

E. Kalogerakis, A. Hertzmann, K. Singh, Learning 3D mesh segmentation and labeling. ACM T. Graphic. 29, 102 (2010). doi: 10.1145/1778765.1778839http://doi.org/10.1145/1778765.1778839

Z.G. Xie, K. Xu, L.G. Liu et al., 3D shape segmentation and labeling via extreme learning machine. Comput. Graph. Forum. 33, 5 (2014). doi: 10.1111/cgf.12434http://doi.org/10.1111/cgf.12434

C.R. Qi, L. Yi, H. Su et al., PointNet++: Deep hierarchical feature learning on point sets in a metric space. Adv. Neur. In. 30 (2017). doi: 10.48550/arXiv.1706.02413http://doi.org/10.48550/arXiv.1706.02413

Y.Y. Li, R. Bu, M.C. Sun et al., PointCNN: Convolution on X-transformed points. Adv. Neur. In. 31 (2018). doi: 10.48550/arXiv.1801.07791http://doi.org/10.48550/arXiv.1801.07791

Y.T. Feng, Y.F. Feng, H.X. You et al., MeshNet: Mesh neural network for 3D shape representation. Paper presented at 2018 AAAI 32nd Conference on Artificial Intelligence (Louisiana, USA 2–7, Feb. 2018) doi: 10.1609/aaai.v33i01.33018279http://doi.org/10.1609/aaai.v33i01.33018279

浏览量

Downloads

CSCD

文章被引用时，请邮件提醒。

Submit

工具集

关联资源

暂无数据