Awesome AI4CAD Hub Papers · Datasets · Projects
← Back to papers

Graph Representation of 3D CAD Models for Machining Feature Recognition With Deep Learning

arXiv 2020 34.1 method

TLDR

Proposes a graph representation for 3D CAD models to enable deep learning-based machining feature recognition, outperforming voxel representations.

Reasoning

The paper introduces a novel graph representation and automatic dataset generation for machining feature recognition, with experimental comparison to voxels. Strengths include addressing interacting features and efficiency; weaknesses include reliance on synthetic data and lack of real-world validation.

Read-first score

Read-first score 34.1, weighted from topical fit, citation, graph, method, reproducibility, and recency signals. Original total remains 33.

Methodology quality 25%
80

Screens visible abstract and analysis fields for experiment, dataset, baseline, metric, and limitation evidence. markers=dataset,evaluation,experiment,result

Recency 8%
42.4

Uses a gentle age decay so recent papers surface without erasing older foundations. 2020

Topical relevance 42%
20.6

Uses existing LLM keyword relevance scores normalized to 0-100. AI for CAD,computer-aided design,neural CAD,generative CAD,parametric CAD,B-Rep,boundary representation,constructive solid geometry,CSG,sketch extrusion,CAD generation,CAD reconstruction,text-to-CAD,image-to-CAD,point cloud to CAD,CAD program

Reproducibility 25%
8

Screens links and visible text for paper, code, dataset, artifact, and repository signals. pdf=False; code=False; dataset=False; markers=dataset

Field roles

Methodology anchor

Rank sensitivity

Stability: volatile; rank range: 110.

Keyword Scores

computer-aided design
9
AI for CAD
7
neural CAD
6
generative CAD
2
parametric CAD
1
B-Rep
1
boundary representation
1
constructive solid geometry
1
CSG
1
sketch extrusion
1
CAD generation
1
CAD reconstruction
1
CAD program
1
text-to-CAD
0
image-to-CAD
0
point cloud to CAD
0

Deep Analysis

Innovations

  • Automatic method to generate large datasets of 3D CAD models with multiple machining features and face labels
  • Concise and informative graph representation for 3D CAD models applicable to graph neural networks
  • Comparison of graph representation with voxels for training deep neural networks to segment 3D CAD models
  • Evaluation of graph-based deep learning for interacting feature recognition

Methodology

The paper proposes an automatic dataset generation method for 3D CAD models containing multiple machining features with face labels. A graph representation of CAD models is introduced and fed into graph neural networks. Performance is compared against voxel-based representations for segmentation, and the approach is tested on interacting feature recognition.

Key Results

The graph representation is more efficient than voxels for deep learning on 3D CAD models. Graph neural networks successfully recognize individual machining features and identify complex interacting features.

Tags