Conference paper Open Access

CAD Defeaturing Using Machine Learning

Owen, Steven; Shead, Timothy M.; Martin, Shawn

We describe new machine-learning-based methods to defeature CAD models for tetrahedral meshing. Using machine learning predictions of mesh quality for geometric features of a CAD model prior to meshing we can identify potential problem areas and improve meshing outcomes by presenting a prioritized list of suggested geometric operations to users. Our machine learning models are trained using a combination of geometric and topological features from the CAD model and local quality metrics for ground truth. We demonstrate a proof-of-concept implementation of the resulting workflow using Sandia’s Cubit Geometry and Meshing Toolkit.

Files (3.3 MB)
Name Size
3.3 MB Download
All versions This version
Views 187187
Downloads 135135
Data volume 451.6 MB451.6 MB
Unique views 168168
Unique downloads 125125


Cite as