Options
Enhancing Machining Feature Recognition in CAD Models through Transfer Learning on BRepNet
Citation Link: https://doi.org/10.15480/882.13539
Publikationstyp
Conference Paper
Date Issued
2024-09-18
Sprache
English
Author(s)
TORE-DOI
Start Page
42
End Page
49
Citation
35. Forum Bauinformatik, fbi 2024: 42-49
Contribution to Conference
Publisher
Technische Universität Hamburg, Institut für Digitales und Autonomes Bauen
Peer Reviewed
true
Industrial products are initially designed using Computer-Aided Design (CAD) systems, which employ Boundary Representation (B-Rep) models for precision and efficiency. During the manufacturing process it is important to identify machining features in CAD models, as this enhances the ability to analyze, process and manufacture them.
This study proposes a deep learning approach that employs transfer learning to enhance the identification and segmentation of these features. BRepNet, a novel neural network designed to operate directly on B-Reps, is adapted by integrating pre-trained weights and adding a modified segmentation head to refine feature identification. By freezing the backbone network and training only the segmentation head, the approach minimizes computational demands and accelerates training times. This makes deep learning more feasible for real-world applications requiring rapid deployment and high accuracy. Tested on the MFCAD dataset, the proposed architecture achieves near state-of-the-art accuracy, with 0.998 accuracy in feature identification for the version with the freezed backbone and 0.999 for the fully fine-tuned version. The study highlights the effectiveness of transfer learning in achieving high accuracy with fewer resources, demonstrating the potential for more efficient and robust CAD model analysis.
This study proposes a deep learning approach that employs transfer learning to enhance the identification and segmentation of these features. BRepNet, a novel neural network designed to operate directly on B-Reps, is adapted by integrating pre-trained weights and adding a modified segmentation head to refine feature identification. By freezing the backbone network and training only the segmentation head, the approach minimizes computational demands and accelerates training times. This makes deep learning more feasible for real-world applications requiring rapid deployment and high accuracy. Tested on the MFCAD dataset, the proposed architecture achieves near state-of-the-art accuracy, with 0.998 accuracy in feature identification for the version with the freezed backbone and 0.999 for the fully fine-tuned version. The study highlights the effectiveness of transfer learning in achieving high accuracy with fewer resources, demonstrating the potential for more efficient and robust CAD model analysis.
Subjects
B-Rep
CAD learning
CAD segmentation
Geometric Deep Learning
Machining features
DDC Class
006.3: Artificial Intelligence
620: Engineering
004: Computer Sciences
005: Computer Programming, Programs, Data and Security
Publication version
publishedVersion
Loading...
Name
Enhancing Machining Feature Recognition in CAD Models through Transfer Learning on BRepNet.pdf
Type
Main Article
Size
310.41 KB
Format
Adobe PDF