Graph Representation of 3D CAD Models for Machining Feature Recognition With Deep Learning
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.
Field roles
Rank sensitivity
Stability: volatile; rank range: 110.
Keyword Scores
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.