IP Library Granted Patent US 12,619,797
Granted Patent B2
US 12,619,797 · App. 17/519,264 · Granted May 5, 2026

Topological message passing for three dimensional models in boundary representation format

Inventor: Joseph George Lambourne (London, GB)
Assignee: Autodesk, Inc.
G06F30/17G06F30/23G06F30/27G06F2119/18
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,619,797
App. No.
17/519,264
Granted
May 5, 2026
Kind
B2
Abstract

Methods, systems, and apparatus, including medium-encoded computer program products, for computer aided design of physical structures include: obtaining a B-Rep model including parametric surfaces and associated coedges; generating feature matrices from the coedges associated with the parametric surfaces; using the feature matrices in a convolution layer of a convolutional neural network of a machine learning algorithm to recognize a collection of faces or edges in the B-Rep model, including concatenating results of transforming the feature matrices using a topological walk matrix that represents topological information for the parametric surfaces based on adjacency relationships among the coedges (e.g., including ordering information); and preparing, based on the at least one collection of faces or edges recognized by the machine learning algorithm, (i) a display of the B-Rep model to facilitate user changes or (ii) a design of the B-Rep model to facilitate manufacturing a physical structure using the B-Rep model.

Claims (76)

1 . A method comprising:

obtaining, in a structural modelling program, a three dimensional model of a manufacturable object comprising one or more modelled manifolds defined by boundary representation data structure entities comprising (i) trimmed parametric surfaces and (ii) coedges associated with the trimmed parametric surfaces, wherein the coedges specify topological information for the trimmed parametric surfaces, and the topological information comprises adjacency relationships among the coedges including ordering information comprising next and previous coedges around a parent face of a given coedge;

generating, by the structural modelling program, feature matrices from the boundary representation data structure entities, wherein the feature matrices represent geometry information about the trimmed parametric surfaces;

using, by the structural modelling program, the feature matrices in at least one convolution layer of a convolutional neural network of a machine learning algorithm to recognize at least one collection of faces or edges in the one or more modelled manifolds, wherein using the feature matrices in the at least one convolution layer comprises concatenating results of transforming the feature matrices using at least one topological walk matrix built from data of the boundary representation data structure entities to represent the topological information for the trimmed parametric surfaces, wherein the data comprises the adjacency relationships among the coedges including the ordering information; and

preparing, by the structural modelling program and based on the at least one collection of faces or edges recognized by the machine learning algorithm, (i) a display of the three dimensional model of the manufacturable object to facilitate user input to change the three dimensional model or (ii) a design of the three dimensional model of the manufacturable object to facilitate manufacturing a physical structure using the three dimensional model.

2 . The method of claim 1 , wherein the one or more modelled manifolds comprise at least one closed manifold representing a modelled solid.

3 . The method of claim 1 , wherein the one or more modelled manifolds comprise at least one open manifold representing a modelled sheet body.

4 . The method of claim 1 , wherein the geometry information about the trimmed parametric surfaces comprises surface type information associated with faces of the trimmed parametric surfaces.

5 . The method of claim 1 , wherein the geometry information about the trimmed parametric surfaces comprises curve type information associated with edges of the trimmed parametric surfaces.

6 . The method of claim 1 , wherein the geometry information about the trimmed parametric surfaces comprises convexity information associated with edges of the trimmed parametric surfaces.

7 . The method of claim 1 , wherein the geometry information about the trimmed parametric surfaces comprises boundary representation flag information indicating an orientation of a face, an edge, a coedge, a surface, or a curve.

8 . The method of claim 7 , wherein the geometry information about the trimmed parametric surfaces comprises the boundary representation flag information indicating at least one of (i) whether a coedge has a same direction as a curve of its associated edge, (ii) whether a normal direction of a face is parallel to normals of an underlying surface, or (iii) whether a coedge is the coedge referenced by the parent loop.

9 . The method of claim 1 , wherein using the feature matrices in the at least one convolution layer of the convolutional neural network of the machine learning algorithm to recognize the at least one collection of faces or edges comprises identifying the at least one collection of faces or edges as being similar to at least one of multiple other collections of faces or edges in other three dimensional models, the other three dimensional models being in boundary representation format and having been previously processed by the machine learning algorithm in a self-supervised manner using adjacency relationships including ordering information for coedges in the other three dimensional models that are processed using at least one convolutional kernel defined with respect to coedges to find learnable parameters associated with both geometry and topology information within a region of a three dimensional model.

10 . The method of claim 9 , wherein the collections of faces or edges are represented using vectors of numbers for faces, edges and coedges in a multi-dimensional embedding space, and the identifying uses similarity of the vectors of numbers assessed using cosine similarity, Euclidean distance, or another measure of similarity in the multi-dimensional embedding space.

11 . The method of claim 10 , comprising running the machine learning algorithm in which the feature matrices are used in the at least one convolution layer, and running the machine learning algorithm comprises pooling information from coedges onto their parent faces and edges in each convolution unit of the convolutional neural network.

12 . The method of claim 1 , wherein the structural modelling program comprises a computer aided design program.

13 . The method of claim 1 , wherein the structural modelling program comprises a computer aided engineering program.

14 . The method of claim 1 , wherein the structural modelling program comprises a computer aided manufacturing program.

15 . The method of claim 1 , wherein the structural modelling program comprises a process planning program.

16 . The method of claim 1 , wherein the preparing comprises modifying the display of the three dimensional model by designating the at least one collection of faces or edges in the display of the three dimensional model.

17 . The method of claim 1 , wherein the preparing comprises modifying the display of the three dimensional model by designating a suggested completion of a user selection of the at least one collection of faces or edges in the display of the three dimensional model.

18 . The method of claim 1 , wherein the preparing comprises modifying the display of the three dimensional model by alerting a user about a suitability of the three dimensional model for at least one predefined downstream process.

19 . The method of claim 18 , wherein the at least one predefined downstream process comprises a manufacturing process or a structural performance process.

20 . The method of claim 1 , wherein the preparing comprises modifying the design of the three dimensional model by manipulating geometry of the at least one collection of faces or edges to automate a predefined workflow.

21 . The method of claim 1 , wherein the preparing comprises modifying the design of the three dimensional model by removing a feature in the three dimensional model, in accordance with the at least one collection of faces or edges, to prepare the three dimensional model for use in a finite element analysis simulation of physical properties of the physical structure to be manufactured.

22 . The method of claim 1 , wherein the preparing comprises preparing the design of the three dimensional model by producing one or more toolpath strategies to machine the physical structure during the manufacturing.

23 . A non-transitory computer-readable medium encoding instructions operable to cause data processing apparatus to perform operations comprising:

obtaining a three dimensional model of a manufacturable object comprising one or more modelled manifolds defined by boundary representation data structure entities comprising (i) trimmed parametric surfaces and (ii) coedges associated with the trimmed parametric surfaces, wherein the coedges specify topological information for the trimmed parametric surfaces, and the topological information comprises adjacency relationships among the coedges including ordering information comprising next and previous coedges around a parent face of a given coedge;

generating feature matrices from the boundary representation data structure entities, wherein the feature matrices represent geometry information about the trimmed parametric surfaces;

using the feature matrices in at least one convolution layer of a convolutional neural network of a machine learning algorithm to recognize at least one collection of faces or edges in the one or more modelled manifolds, wherein using the feature matrices in the at least one convolution layer comprises concatenating results of transforming the feature matrices using at least one topological walk matrix built from data of the boundary representation data structure entities to represent the topological information for the trimmed parametric surfaces, wherein the data comprises the adjacency relationships among the coedges including the ordering information; and

preparing, based on the at least one collection of faces or edges recognized by the machine learning algorithm, (i) a display of the three dimensional model of the manufacturable object to facilitate user input to change the three dimensional model or (ii) a design of the three dimensional model of the manufacturable object to facilitate manufacturing a physical structure using the three dimensional model.

24 . The non-transitory computer-readable medium of claim 23 , wherein the one or more modelled manifolds comprise at least one closed manifold representing a modelled solid.

25 . The non-transitory computer-readable medium of claim 23 , wherein the one or more modelled manifolds comprise at least one open manifold representing a modelled sheet body.

26 . The non-transitory computer-readable medium of claim 23 , wherein the geometry information about the trimmed parametric surfaces comprises surface type information associated with faces of the trimmed parametric surfaces.

27 . The non-transitory computer-readable medium of claim 23 , wherein the geometry information about the trimmed parametric surfaces comprises curve type information associated with edges of the trimmed parametric surfaces.

28 . The non-transitory computer-readable medium of claim 23 , wherein the geometry information about the trimmed parametric surfaces comprises convexity information associated with edges of the trimmed parametric surfaces.

29 . The non-transitory computer-readable medium of claim 23 , wherein the geometry information about the trimmed parametric surfaces comprises boundary representation flag information indicating an orientation of a face, an edge, a coedge, a surface, or a curve.

30 . The non-transitory computer-readable medium of claim 29 , wherein the geometry information about the trimmed parametric surfaces comprises the boundary representation flag information indicating at least one of (i) whether a coedge has a same direction as a curve of its associated edge, (ii) whether a normal direction of a face is parallel to normals of an underlying surface, or (iii) whether a coedge is the coedge referenced by the parent loop.

31 . The non-transitory computer-readable medium of claim 23 , wherein using the feature matrices in the at least one convolution layer of the convolutional neural network of the machine learning algorithm to recognize the at least one collection of faces or edges comprises identifying the at least one collection of faces or edges as being similar to at least one of multiple other collections of faces or edges in other three dimensional models, the other three dimensional models being in boundary representation format and having been previously processed by the machine learning algorithm in a self-supervised manner using adjacency relationships including ordering information for coedges in the other three dimensional models that are processed using at least one convolutional kernel defined with respect to coedges to find learnable parameters associated with both geometry and topology information within a region of a three dimensional model.

32 . The non-transitory computer-readable medium of claim 31 , wherein the collections of faces or edges are represented using vectors of numbers for faces, edges and coedges in a multi-dimensional embedding space, and the identifying uses similarity of the vectors of numbers assessed using cosine similarity, Euclidean distance, or another measure of similarity in the multi-dimensional embedding space.

33 . The non-transitory computer-readable medium of claim 32 , wherein the operations comprise running the machine learning algorithm in which the feature matrices are used in the at least one convolution layer, and running the machine learning algorithm comprises pooling information from coedges onto their parent faces and edges in each convolution unit of the convolutional neural network.

34 . The non-transitory computer-readable medium of claim 23 , wherein the preparing comprises modifying the display of the three dimensional model by designating the at least one collection of faces or edges in the display of the three dimensional model.

35 . The non-transitory computer-readable medium of claim 23 , wherein the preparing comprises modifying the display of the three dimensional model by designating a suggested completion of a user selection of the at least one collection of faces or edges in the display of the three dimensional model.

36 . The non-transitory computer-readable medium of claim 23 , wherein the preparing comprises modifying the display of the three dimensional model by alerting a user about a suitability of the three dimensional model for at least one predefined downstream process.

37 . The non-transitory computer-readable medium of claim 36 , wherein the at least one predefined downstream process comprises a manufacturing process or a structural performance process.

38 . The non-transitory computer-readable medium of claim 23 , wherein the preparing comprises modifying the design of the three dimensional model by manipulating geometry of the at least one collection of faces or edges to automate a predefined workflow.

39 . The non-transitory computer-readable medium of claim 23 , wherein the preparing comprises modifying the design of the three dimensional model by removing a feature in the three dimensional model, in accordance with the at least one collection of faces or edges, to prepare the three dimensional model for use in a finite element analysis simulation of physical properties of the physical structure to be manufactured.

40 . The non-transitory computer-readable medium of claim 23 , wherein the preparing comprises preparing the design of the three dimensional model by producing one or more toolpath strategies to machine the physical structure during the manufacturing.

41 . A system comprising:

a data processing apparatus including at least one hardware processor; and

a non-transitory computer-readable medium encoding instructions of a structural modelling program configured to cause the data processing apparatus to perform operations comprising:

obtaining a three dimensional model of a manufacturable object comprising one or more modelled manifolds defined by boundary representation data structure entities comprising (i) trimmed parametric surfaces and (ii) coedges associated with the trimmed parametric surfaces, wherein the coedges specify topological information for the trimmed parametric surfaces, and the topological information comprises adjacency relationships among the coedges including ordering information comprising next and previous coedges around a parent face of a given coedge;

generating feature matrices from the boundary representation data structure entities, wherein the feature matrices represent geometry information about the trimmed parametric surfaces;

using the feature matrices in at least one convolution layer of a convolutional neural network of a machine learning algorithm to recognize at least one collection of faces or edges in the one or more modelled manifolds, wherein using the feature matrices in the at least one convolution layer comprises concatenating results of transforming the feature matrices using at least one topological walk matrix built from data of the boundary representation data structure entities to represent the topological information for the trimmed parametric surfaces, wherein the data comprises the adjacency relationships among the coedges including the ordering information; and

preparing, based on the at least one collection of faces or edges recognized by the machine learning algorithm, (i) a display of the three dimensional model of the manufacturable object to facilitate user input to change the three dimensional model or (ii) a design of the three dimensional model of the manufacturable object to facilitate manufacturing a physical structure using the three dimensional model.

42 . The system of claim 41 , wherein the one or more modelled manifolds comprise at least one closed manifold representing a modelled solid.

43 . The system of claim 41 , wherein the one or more modelled manifolds comprise at least one open manifold representing a modelled sheet body.

44 . The system of claim 41 , wherein the geometry information about the trimmed parametric surfaces comprises surface type information associated with faces of the trimmed parametric surfaces.

45 . The system of claim 41 , wherein the geometry information about the trimmed parametric surfaces comprises curve type information associated with edges of the trimmed parametric surfaces.

46 . The system of claim 41 , wherein the geometry information about the trimmed parametric surfaces comprises convexity information associated with edges of the trimmed parametric surfaces.

47 . The system of claim 41 , wherein the geometry information about the trimmed parametric surfaces comprises boundary representation flag information indicating an orientation of a face, an edge, a coedge, a surface, or a curve.

48 . The system of claim 47 , wherein the geometry information about the trimmed parametric surfaces comprises the boundary representation flag information indicating at least one of (i) whether a coedge has a same direction as a curve of its associated edge, (ii) whether a normal direction of a face is parallel to normals of an underlying surface, or (iii) whether a coedge is the coedge referenced by the parent loop.

49 . The system of claim 41 , wherein using the feature matrices in the at least one convolution layer of the convolutional neural network of the machine learning algorithm to recognize the at least one collection of faces or edges comprises identifying the at least one collection of faces or edges as being similar to at least one of multiple other collections of faces or edges in other three dimensional models, the other three dimensional models being in boundary representation format and having been previously processed by the machine learning algorithm in a self-supervised manner using adjacency relationships including ordering information for coedges in the other three dimensional models that are processed using at least one convolutional kernel defined with respect to coedges to find learnable parameters associated with both geometry and topology information within a region of a three dimensional model.

50 . The system of claim 49 , wherein the collections of faces or edges are represented using vectors of numbers for faces, edges and coedges in a multi-dimensional embedding space, and the identifying uses similarity of the vectors of numbers assessed using cosine similarity, Euclidean distance, or another measure of similarity in the multi-dimensional embedding space.

51 . The system of claim 50 , wherein the operations comprise running the machine learning algorithm in which the feature matrices are used in the at least one convolution layer, and running the machine learning algorithm comprises pooling information from coedges onto their parent faces and edges in each convolution unit of the convolutional neural network.

52 . The system of claim 41 , wherein the structural modelling program comprises a computer aided design program.

53 . The system of claim 41 , wherein the structural modelling program comprises a computer aided engineering program.

54 . The system of claim 41 , wherein the structural modelling program comprises a computer aided manufacturing program.

55 . The system of claim 41 , wherein the structural modelling program comprises a process planning program.

56 . The system of claim 41 , wherein the preparing comprises modifying the display of the three dimensional model by designating the at least one collection of faces or edges in the display of the three dimensional model.

57 . The system of claim 41 , wherein the preparing comprises modifying the display of the three dimensional model by designating a suggested completion of a user selection of the at least one collection of faces or edges in the display of the three dimensional model.

58 . The system of claim 41 , wherein the preparing comprises modifying the display of the three dimensional model by alerting a user about a suitability of the three dimensional model for at least one predefined downstream process.

59 . The system of claim 58 , wherein the at least one predefined downstream process comprises a manufacturing process or a structural performance process.

60 . The system of claim 41 , wherein the preparing comprises modifying the design of the three dimensional model by manipulating geometry of the at least one collection of faces or edges to automate a predefined workflow.

61 . The system of claim 41 , wherein the preparing comprises modifying the design of the three dimensional model by removing a feature in the three dimensional model, in accordance with the at least one collection of faces or edges, to prepare the three dimensional model for use in a finite element analysis simulation of physical properties of the physical structure to be manufactured.

62 . The system of claim 41 , wherein the preparing comprises preparing the design of the three dimensional model by producing one or more toolpath strategies to machine the physical structure during the manufacturing.

Assignments (3)
CHANGE OF ADDRESS FOR ASSIGNEE Recorded Aug 19, 2022
From: AUTODESK, INC.
To: AUTODESK, INC.
Reel/Frame 061572/0061 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Nov 19, 2021
From: LAMBOURNE, JOSEPH GEORGE
To: AUTODESK LIMITED
Reel/Frame 058170/0326 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Nov 19, 2021
From: AUTODESK LIMITED
To: AUTODESK, INC.
Reel/Frame 058170/0354 →
Continuity (2)
Provisional Application 63113766 · Nov 13, 2020
Related Publication 20220156430A1 · May 19, 2022
References Cited (54)
US 12288013B2 · Jayaraman et al. · 2025 [cited by applicant]
US 20140184598A1 · Quilot · 2014 [cited by examiner]
US 20180012404A1 · Tanaka · 2018 [cited by examiner]
US 20200043231A1 · Zhang · 2020 [cited by examiner]
US 20200151286A1 · Willis et al. · 2020 [cited by applicant]
US 20220318636A1 · Jayaraman et al. · 2022 [cited by applicant]
US 20220318637A1 · Jayaraman et al. · 2022 [cited by applicant]
Balu et al., “A Deep 3D Convolutional Neural Network Based Design for Manufacturability Framework,” CoRR, abs/1612.02141,9 pages (Year: 2016). [cited by examiner]
Al-wswasi et al., “A Survey on Smart Automated Computer-Aided Process Planning (ACAPP) Techniques,” The International Journal of Advanced Manufacturing Technology, 2018, 97:809-832. [cited by applicant]
Ansaldi et al., “An Edge-Face Relational Scheme for Boundary Representations,” Computer Graphics Forum, 1985, 4(4):319-332. [cited by applicant]
Babic et al., “A Review of Automated Feature Recognition with Rule-Based Pattern Recognition,” Computers in Industry, 2008, 59:321-337. [cited by applicant]
Balu et al., “A Deep 3D Convolutional Neural Network Based Design for Manufacturability Framework,” CoRR, abs/1612.02141, 2016, 9 pages. [cited by applicant]
Baumgart et al., “Winged Edge Polyhedron Representation,” Technical Report, 1972, 44 pages. [cited by applicant]
Bharadwaj, “Inception of a Cyber-Infrastructure for Product Design Data and Evaluation of a Customized Multi-View Convolutional Neural Network for 3D Cad Model Classification,” Thesis in Industrial Engineering, 2020, 71… [cited by applicant]
Bouritas et al., “Neural 3D Morphable Models: Spiral Convolutional Networks for 3D Shape Representation Learning and Generation,” 2019 IEEE/CVF International Conference on Computer Vision (ICVV), 2019, 10 pages. [cited by applicant]
Cao et al., “Graph Representation of 3D CAD Models for Machining Feature Recognition with Deep Learning,” Proceedings of the ASME 2020 International Design Engineering Technical Conferences and Computers and Information… [cited by applicant]
Chen et al., “A Neural Network System Feature Recognition for Two-Dimensional,” International Journal of Computer Integrated Manufacturing, 1998, 11(2):111-117. [cited by applicant]
Ding et al., “Novel ANN-Based Feature Recognition Incorporating Design by Features,” Computers in Industry, 2004, 55:197-222. [cited by applicant]
Eastman et al., “Geometric Modeling Using the Euler Operators,” Institute of Physical Planning, Carnegie Mellon University, 1979, 12 pages. [cited by applicant]
Gilmer et al., “Neural Message Passing of Quantum Chemistry,” arXiv:1704.01212v2, Jun. 2017, 14 pages. [cited by applicant]
Guibas et al., “Primitives for the Manipulation of General Subdivisions and the Computation of Voronoi Diagrams,” 1983, 4:221-234. [cited by applicant]
Hanocka et al., “MeshCNN: A Network with an Edge,” ACM Transactions on Graphics (TOG), 2019, 38(4):1-12. [cited by applicant]
Henderson et al., “Boundary Representation-Based Feature Identification,” Advances in Feature Based Manufacturing, 1994, 20( C):15-38. [cited by applicant]
Jayaraman et al., “UV-Net: Learning from Curve-Networks and Solids,” arXiv:2006.10211v2, 2020, 15 pages. [cited by applicant]
Jayaraman et al., “UV-Net: Learning from Boundary Representations,” arXiv:2006.10211v2, 2021, 18 pages. [cited by applicant]
Jia et al., “Learning Semantic Image Representations at a Large Scale,” 2014, Dissertation in Computer Science in the Graduate Division of the university of California, 103 pages. [cited by applicant]
Jones et al., “AutoMate: A Dataset and Learning Approach for Automatic Mating of CAD Assemblies,” arXiv:2015.12238v2, Oct. 2021, 18 pages. [cited by applicant]
Joshi et al., “Graph-Based Heuristics for Recognition of Machined Features from a 3D Solid Model,” 1988, Computer Aided Design, 9 pages. [cited by applicant]
Koch et al., “ABC: A Big CAD Model Dataset for Geometric Deep Learning,” Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2019, 9601-9611. [cited by applicant]
Lavoie, “An Introduction to NURBS,” on-line tutorial https://linburbs.sourceforge.net/nurbsintro.pdf, 1999, 6 pages. [cited by applicant]
Le et al., “Going Deeper with Lean Point Networks,” IEEE Conference on Computer Vision and Pattern Recognition, 2020, 10 pages. [cited by applicant]
Lee et al., “Partial Entity Structure: A Compact Non-Manifold Boundary Representation Based on Partial Topological Entities,” 2001, 1:159-170. [cited by applicant]
Ma et al., “Automatic Discovery of Common Design Structures in CAD Models,” Computer Graphics, 2010, 34:545-555. [cited by applicant]
Marquez et al., “Application of Neural Networks in Feature Recognition of Mould Reinforced Plastic Parts,” Concurrent Engineering, 1999, 7(2):115-122. [cited by applicant]
Nezis et al., “Recognizing 2½D Shape Features Using a Neural Network and Heuristics,” Computer-Aided Design, 1997, 29(7):523-539. [cited by applicant]
Niepert et al., “Learning Convolutional Neural Networks for Graphs,” 2016, International Conference on Machine Learning, 10 pages. [cited by applicant]
Prabhakar et al., “Automatic Form-Feature Recognition Using Neural-Network-Based Techniques on Boundary Representations of Solid Models,” CAD Computer Aided Design, 1992, 24(7):381-393. [cited by applicant]
Qi et al., “Pointnet: Deep Learning On Point Sets for 3D Classification and Segmentation,” Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017, 652-660. [cited by applicant]
Qi et al., “Pointnet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space,” Advances in Neural Information Processing Systems, 2017, 5099-5108. [cited by applicant]
Sakurai et al., “Recognizing Shape Features in Solid Models,” IEEE Computer Graphics and Applications, 1990, 10:22-32. [cited by applicant]
Shi et al., “A Critical Review of Feature Recognition Techniques,” Computer-Aided Design and Applications, 2020, 17:861-899. [cited by applicant]
Simonovsky et al., “Dynamic Edge-Conditioned Filters in Convolutional Neural Networks on Graphs,” 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017, 10 pages. [cited by applicant]
Staley et al., “Using Syntactic Pattern Recognition to Extract Feature Information from Solid Geometric Database,” Computers in Mechanical Engineering, 1983, 6 pages. [cited by applicant]
Sunil et al., “Automatic Recognition of Machining Features using Artificial Neural Networks,” The International Journal of Advanced Manufacturing Technology, 2009, 41:932-947. [cited by applicant]
United States Patent Application for Machine Learning Techniques for Automating Tasks Based on Boundary Representations of 3D CAD Objects, filed on Jun. 15, 2021, assigned U.S. Appl. No. 17/348,338, 86 pages. [cited by applicant]
United States Patent Application for “Techniques for Generating UV-Net Representations of 3D CAD Objects for Machine Learning Models”, filed on Jun. 15, 2021, assigned U.S. Appl. No. 17/348,295, 86 pages. [cited by applicant]
United States Patent Application for “Techniques for Training Machine Learning Models to Automate Task Associated with 3D CAD Objects”, filed on Jun. 15, 2021, assigned U.S. Appl. No. 17/348,314, 87 pages. [cited by applicant]
Wang et al., “3D Shape Segmentation via Shape Fully Convolutional Networks,” Computers & Graphics, 2018, 76:182-192. [cited by applicant]
Wang et al., “Dynamic Graph CNN for Learning on Point Clouds,” CoRR, abs/1801.07829, 2018, 12 pages. [cited by applicant]
Weiler, “Topological Structures for Geometric Modelling,” Technical Report RPI, Center for Interactive Computer Graphica, University Microfilms, 1986, 346 pages. [cited by applicant]
Wikipedia.com [online]. “Shapemanagers,” published on or before Nov. 1, 2021, retrieved on Nov. 1, 2021, retrieved from URL<https://en.wikipedia.org/wiki/shapemanager>, 1 page. [cited by applicant]
Yue et al., “Study of Neural Network Techniques for Computer Integrated Manufacture,” Engineering Computations, 2002, 19:136-157. [cited by applicant]
Zhang et al., “Deep Learning on Graphs: A Survey,” CoRR, abs/1812.04202, 2018, 20 pages. [cited by applicant]
Zhang et al., “Featurenet: Machinings Feature Recognition Based on 3D Convolutional Neural Network,” Computer-Aided Design, 2018, 101:12-22. [cited by applicant]