More Web Proxy on the site http://driver.im/

research-article

Hierarchical CADNet: : Learning from B-Reps for Machining Feature Recognition

Authors:

Andrew R. Colligan,

Trevor T. Robinson,

Declan C. Nolan,

Weijuan CaoAuthors Info & Claims

Volume 147, Issue C

https://doi.org/10.1016/j.cad.2022.103226

Published: 01 June 2022 Publication History

Abstract

Deep learning approaches have been shown to be capable of recognizing shape features (e.g. machining features) in Computer-Aided Design (CAD) models in certain circumstances, yet still have issues when the features intersect, and in exploiting the geometric and topological information which comprises the boundary representation (B-Rep) of the typical CAD model. This paper presents a novel hierarchical B-Rep graph shape representation which encodes information about the surface geometry and face topology of the B-Rep. To learn from this new shape representation, a novel hierarchical graph convolutional network called Hierarchical CADNet has been created, which has been shown to outperform other state-of-the-art neural architectures on feature identification, including machining features that intersect, with improvements in accuracy for some more complex CAD models.

Highlights

•

A novel representation and deep learning framework for learning from B-Rep CAD models.

•

A complex CAD model dataset with labeled machining features is proposed.

•

Improvements over current state-of-the-art deep learning frameworks for machining feature recognition.

References

[1]

CATIATM 3Dexperience® - dassault systèmes® 3D software n.d, 2019, https://www.3ds.com/products-services/catia/. [Accessed 11 May 2019].

[2]

NX n.d, 2021, https://www.plm.automation.siemens.com/global/en/products/nx/. [Accessed 9 January 2020].

[3]

Al-wswasi M., Ivanov A., Makatsoris H., A survey on smart automated computer-aided process planning (ACAPP) techniques, Int J Adv Manuf Technol 97 (2018) 809–832,.

[4]

Babic B., Nesic N., Miljkovic Z., A review of automated feature recognition with rule-based pattern recognition, Comput Ind 59 (2008) 321–337,.

[5]

Babić B.R., Nešić N., Miljković Z., Automatic feature recognition using artificial neural networks to integrate design and manufacturing: Review of automatic feature recognition systems, Artif Intell Eng Des Anal Manuf AIEDAM 25 (2011) 289–304,.

[6]

Krizhevsky A., Sutskever I., Hinton G.E., ImageNet classification with deep convolutional neural networks, Adv Neural Inf Process Syst 25 (NIPS 2012) (2012) 1097–1105.

[7]

Qi C.R., Su H., NieBner M., Dai A., Yan M., Guibas L.J., Volumetric and multi-view CNNs for object classification on 3D data, in: 2016 IEEE Conf. Comput. Vis. Pattern Recognit, IEEE, 2016, pp. 5648–5656,.

[8]

Shi B., Bai S., Zhou Z., Bai X., DeepPano: Deep panoramic representation for 3-D shape recognition, IEEE Signal Process Lett 22 (2015) 2339–2343,.

[9]

Wu Zhirong, Song S., Khosla A., Yu Fisher, Zhang Linguang, Tang Xiaoou, et al., 3D ShapeNets: A deep representation for volumetric shapes, in: 2015 IEEE Conf. Comput. Vis. Pattern Recognit, IEEE, 2015, pp. 1912–1920,.

[10]

Maturana D., Scherer S., Voxnet: A 3D convolutional neural network for real-time object recognition, in: 2015 IEEE/RSJ Int. Conf. Intell. Robot. Syst, IEEE, 2015, pp. 922–928,.

Digital Library

[11]

Sedaghat N., Zolfaghari M., Amiri E., Brox T., Orientation-boosted Voxel nets for 3D object recognition, 2016.

[12]

Kim S., gun Chi H, Ramani K., Object synthesis by learning part geometry with surface and volumetric representations, Comput Des 130 (2021),.

[13]

Riegler G., Ulusoy A.O., Geiger A., OctNet: Learning deep 3D representations at high resolutions, in: 2017 IEEE Conf. Comput. Vis. Pattern Recognit, IEEE, 2017, pp. 6620–6629,.

[14]

Wang P.-S., Liu Y., Guo Y.-X., Sun C.-Y., Tong X., O-CNN: Octree-based convolutional neural networks for 3D shape analysis, ACM Trans Graph 36 (2017) 1–11,.

Digital Library

[15]

Wang P., Sun C., Liu Y., Tong X., Wang P.-S., Sun C.-Y., et al., Adaptive O-CNN: A patch-based deep representation of 3D shapes ACM reference format, ACM Trans Graph (2018) 37,.

Digital Library

[16]

Charles R.Q., Su H., Kaichun M., Guibas L.J., PointNet: Deep learning on point sets for 3D classification and segmentation, in: 2017 IEEE Conf. Comput. Vis. Pattern Recognit, IEEE, 2017, pp. 77–85,.

[17]

Li CRQ, Hao Y, Leonidas S, Guibas J. PointNet++: Deep hierarchical feature learning on point sets in a metric space. In: Conf. Neural Inf. Process. Syst. 2017, 2017.

[18]

Wang Y., Sun Y., Liu Z., Sarma S.E., Bronstein M.M., Solomon J.M., Dynamic graph CNN for learning on point clouds, ACM Trans Graph 38 (2018).

Digital Library

[19]

Hanocka R., Hertz A., Fish N., Giryes R., Fleishman S., Cohen-Or D., MeshCNN: A network with an edge, 2018,.

Digital Library

[20]

Feng Y., Feng Y., You H., Zhao X., Gao Y., MeshNet: Mesh neural network for 3D shape representation, Proc AAAI Conf Artif Intell 33 (2019) 8279–8286,.

Digital Library

[21]

Yang J., Mo K., Lai Y.-K., Guibas L.J., Gao L., DSG-net: Learning disentangled structure and geometry for 3D shape generation, 2021.

[22]

Masci J, Boscaini D, Bronstein MM, Vandergheynst P. Geodesic convolutional neural networks on Riemannian manifolds. In: Proc IEEE Int Conf Comput Vis, 2015-February. 2015, p. 832–40.

[23]

Boscaini D., Masci J., Rodolà E., Bronstein M.M., Learning shape correspondence with anisotropic convolutional neural networks, Adv Neural Inf Process Syst (2016) 3197–3205.

[24]

Boscaini D., Masci J., Rodolà E., Bronstein M.M., Cremers D., Anisotropic diffusion descriptors, Comput Graph Forum 35 (2016) 431–441,.

[25]

Sunil V.B., Pande S.S., Automatic recognition of machining features using artificial neural networks, Int J Adv Manuf Technol 41 (2009) 932–947,.

[26]

Onwubolu G.C., Manufacturing features recognition using backpropagation neural networks, J Intell Manuf 10 (1999) 289–299,.

[27]

Zhang Z., Jaiswal P., Rai R., FeatureNet: Machining feature recognition based on 3D convolution neural network, Comput Des 101 (2018) 12–22,.

[28]

Peddireddy D., Fu X., Wang H., Joung B.G., Aggarwal V., Sutherl J.W., et al., Deep learning based approach for identifying conventional machining processes from CAD data, Procedia Manuf 48 (2020) 915–925,.

[29]

Ning F., Shi Y., Cai M., Xu W., Part machining feature recognition based on a deep learning method, J Intell Manuf (2021),.

Digital Library

[30]

Ma Y., Zhang Y., Luo X., Automatic recognition of machining features based on point cloud data using convolution neural networks, in: ACM Int. Conf. Proceeding Ser, Association for Computing Machinery, 2019, pp. 229–235,.

Digital Library

[31]

Shi P., Qi Q., Qin Y., Scott P.J., Jiang X., A novel learning-based feature recognition method using multiple sectional view representation, J Intell Manuf 31 (2020) 1291–1309,.

Digital Library

[32]

Cao W., Robinson T., Hua Y., Boussuge F., Colligan A.R., Pan W., Graph representation of 3D CAD models for machining feature recognition with deep learning, in: 11A 46th Des. Autom. Conf, American Society of Mechanical Engineers, 2020,.

[33]

Jayaraman PK, Sanghi A, Lambourne J, Davies T, Shayani H, Morris N. UV-Net: Learning from curve-networks and solids. In: IEEE Conf. Comput. Vis. Pattern Recognit. 2021, p. 11703–12, arXiv.

[34]

Lambourne Autodesk Research Karl DD, Willis JG, Kumar Jayaraman P, Sanghi A, Meltzer P, Shayani H. BRepNet: A topological message passing system for solid models. In: Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. 2021, p. 12773–82.

[35]

Jones B., Hildreth D., Chen D., Baran I., Kim V.G., Schulz A., Automate: A dataset and learning approach for automatic mating of CAD assemblies, 2021.

[36]

STL (sTereoLithography) file format, binary n.d, 2021, https://www.loc.gov/preservation/digital/formats/fdd/fdd000505.shtml. [Accessed 8 January 2021].

[37]

Rahman M.S., Basic graph theory, Springer International Publishing, Cham, 2017,.

[38]

Wu Z., Pan S., Chen F., Long G., Zhang C., Yu P.S., A comprehensive survey on graph neural networks, IEEE Trans Neural Netw Learn Syst 32 (2019) 4–24,.

[39]

Such F.P., Sah S., Dominguez M., Pillai S., Zhang C., Michael A., et al., Robust spatial filtering with graph convolutional neural networks, IEEE J Sel Top Signal Process 11 (2017) 884–896,.

[40]

Li M., Perrier E., Xu C., Deep hierarchical graph convolution for election prediction from geospatial census data, in: 33rd AAAI Conf. Artif. Intell. Vol. 33, AAAI Press, 2019, pp. 647–654,.

Digital Library

[41]

Li Q, Han Z, Wu X-M. Deeper insights into graph convolutional networks for semi-supervised learning. In: 32nd AAAI Conf Artif Intell AAAI 2018. 2018, p. 3538–45.

[42]

Li G., Muller M., Thabet A., Ghanem B., DeepGCNs: Can GCNs go as deep as CNNs?, in: Proc. IEEE Int. Conf. Comput. Vis., 2019- October, Institute of Electrical and Electronics Engineers Inc., 2019, pp. 9266–9275,.

[43]

Koch S., Matveev A., Jiang Z., Williams F., Artemov A., Burnaev E., et al., ABC: A big CAD model dataset for geometric deep learning, 2018.

[44]

Kim S, gun Chi H, Hu X, Huang Q, Ramani K. A large-scale annotated mechanical components benchmark for classification and retrieval tasks with deep neural networks. In: Proc. 16th Eur. Conf. Comput. Vis. 2020.

[45]

MFCAD: A dataset of 3D CAD models with machining feature labels. n.d, 2021, https://github.com/hducg/MFCAD. [Accessed 14 June 2021].

[46]

PythonOCC: Python package for 3D CAD/BIM/PLM/CAM n.d, 2021, https://github.com/tpaviot/pythonocc-core. [Accessed 18 June 2021].

[47]

Numba: A high performance python compiler n.d, 2021, http://numba.pydata.org/. [Accessed 18 June 2021].

[48]

Tensorflow n.d, 2020, https://www.tensorflow.org/. [Accessed 18 December 2020].

[49]

Glorot X, Bengio Y. Understanding the difficulty of training deep feedforward neural networks. In: JMLR Workshop and Conference Proceedings. 2010, p. 249–56, J. Mach. Learn. Res., 9.

[50]

Ioffe S., Szegedy C., Batch normalization: Accelerating deep network training by reducing internal covariate shift, in: 32nd Int. Conf. Mach. Learn. ICML 2015, 1, International Machine Learning Society (IMLS), 2015, pp. 448–456.

[51]

Srivastava N., Hinton G., Krizhevsky A., Salakhutdinov R., Dropout: A simple way to prevent neural networks from overfitting, J Mach Learn Res 15 (2014) 1929–1958.

[52]

Kingma D.P., Ba J.L., Adam: A method for stochastic optimization, in: 3rd Int. Conf. Learn. Represent. ICLR 2015 - Conf. Track Proc, International Conference on Learning Representations, ICLR, 2015.

[53]

Categorical cross entropy n.d, 2021, https://www.tensorflow.org/api_docs/python/tf/keras/losses/CategoricalCrossentropy. [Accessed 18 June 2021].

[54]

Lin M., Chen Q., Yan S., Network in network, in: 2nd Int. Conf. Learn. Represent. ICLR 2014 - Conf. Track Proc. International Conference on Learning Representations, ICLR, 2014.

[55]

Imagenet n.d, 2019, http://www.image-net.org/. [Accessed 16 May 2019].

[56]

Precision-recall — scikit-learn 0.24.2 documentation n.d, 2021, https://scikit-learn.org/stable/auto_examples/model_selection/plot_precision_recall.html. [Accessed 28 June 2021].

[57]

Colligan AR, Robinson TT, Nolan DC, Hua Y, Cao W. MFCAD++ Dataset n.d, https://doi.org/10.17034/d1fec5a0-8c10-4630-b02e-b92dc81df823.

Cited By

Wang YChen YLu YWang JHuang KHan BZhang Q(2025)Multi-layer cutting path planning for composite enclosed cavity in additive and subtractive hybrid manufacturingRobotics and Computer-Integrated Manufacturing10.1016/j.rcim.2024.10282391:COnline publication date: 1-Feb-2025
https://dl.acm.org/doi/10.1016/j.rcim.2024.102823
Wu HLei RPeng YGao L(2024)AAGNetRobotics and Computer-Integrated Manufacturing10.1016/j.rcim.2023.10266186:COnline publication date: 1-Apr-2024
https://dl.acm.org/doi/10.1016/j.rcim.2023.102661
Zhang SGuan ZJiang HWang XTan P(2024)BrepMFRComputer Aided Geometric Design10.1016/j.cagd.2024.102318111:COnline publication date: 1-Jun-2024
https://dl.acm.org/doi/10.1016/j.cagd.2024.102318
Show More Cited By

Index Terms

Hierarchical CADNet: Learning from B-Reps for Machining Feature Recognition
1. Applied computing
  1. Physical sciences and engineering
    1. Engineering
2. Computing methodologies

Index terms have been assigned to the content through auto-classification.

Recommendations

Trimming of free-form objects for a B-Rep solid modeller

This paper describes a technique for trimming solid objects in a B-Rep solid modelling system. A B-Rep scheme based on the split-edge structure, which is suitable for the representation of trimmed surfaces, is first discussed. Algorithms for graph ...
BrepMFR: Enhancing machining feature recognition in B-rep models through deep learning and domain adaptation
Abstract
Feature Recognition (FR) plays a crucial role in modern digital manufacturing, serving as a key technology for integrating Computer-Aided Design (CAD), Computer-Aided Process Planning (CAPP) and Computer-Aided Manufacturing (CAM) systems. The ...
Highlights
- A learning-based method for machining feature recognition from B-rep models.
- The network BrepMFR directly takes boundary representations of CAD models as input.
- A new large-scale synthetic CAD dataset comprising labeled machining ...
A novel method for intersecting machining feature segmentation via deep reinforcement learning
Abstract
Machining feature segmentation is a primary task in machining feature recognition, as it directly impacts downstream activities such as feature type identification and process planning. However, the intersecting and overlapping of multiple ...

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

cover image Computer-Aided Design

Computer-Aided Design Volume 147, Issue C

Jun 2022

55 pages

ISSN:0010-4485

Issue’s Table of Contents

The Authors.

Publisher

Butterworth-Heinemann

United States

Publication History

Published: 01 June 2022

Author Tags

Qualifiers

Research-article

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

6
Total Citations
View Citations
0
Total Downloads

Downloads (Last 12 months)0
Downloads (Last 6 weeks)0

Reflects downloads up to 30 Dec 2024

Other Metrics

View Author Metrics

Citations

Cited By

Wang YChen YLu YWang JHuang KHan BZhang Q(2025)Multi-layer cutting path planning for composite enclosed cavity in additive and subtractive hybrid manufacturingRobotics and Computer-Integrated Manufacturing10.1016/j.rcim.2024.10282391:COnline publication date: 1-Feb-2025
https://dl.acm.org/doi/10.1016/j.rcim.2024.102823
Wu HLei RPeng YGao L(2024)AAGNetRobotics and Computer-Integrated Manufacturing10.1016/j.rcim.2023.10266186:COnline publication date: 1-Apr-2024
https://dl.acm.org/doi/10.1016/j.rcim.2023.102661
Zhang SGuan ZJiang HWang XTan P(2024)BrepMFRComputer Aided Geometric Design10.1016/j.cagd.2024.102318111:COnline publication date: 1-Jun-2024
https://dl.acm.org/doi/10.1016/j.cagd.2024.102318
Zhang HWang WZhang SZhang YZhou JWang ZHuang BHuang R(2024)A novel method for intersecting machining feature segmentation via deep reinforcement learningAdvanced Engineering Informatics10.1016/j.aei.2023.10225659:COnline publication date: 1-Jan-2024
https://dl.acm.org/doi/10.1016/j.aei.2023.102256
Lou YLi XChen HZhou XFrommholz IHopfgartner FLee MOakes MLalmas MZhang MSantos R(2023)BRep-BERT: Pre-training Boundary Representation BERT with Sub-graph Node Contrastive LearningProceedings of the 32nd ACM International Conference on Information and Knowledge Management10.1145/3583780.3614795(1657-1666)Online publication date: 21-Oct-2023
https://dl.acm.org/doi/10.1145/3583780.3614795
Wang PLiu WYou Y(2023)A hybrid framework for manufacturing feature recognition from CAD models of 3-axis milling partsAdvanced Engineering Informatics10.1016/j.aei.2023.10207357:COnline publication date: 1-Aug-2023
https://dl.acm.org/doi/10.1016/j.aei.2023.102073

View Options

View options

Media

Figures

Other

Tables

View Issue’s Table of Contents