Enhancing 3D-CNN-based Geometric Feature Recognition for Adaptive Additive Manufacturing: A SDF Data Approach

Publikation: Beitrag in FachzeitschriftForschungsartikelBeigetragenBegutachtung



In the context of additive manufacturing, the adjustment of process data to individual geometric features offers the potential to further increase manufacturing speed and quality, while being widely underestimated in recent research. Unfortunately, the current non-uniform data handling in the CAD-CAM-Link results in a downstream data loss, that prevents the availability of geometric knowledge from being present at any time to apply the more advanced approaches of adaptive slicing and toolpath generation. Automatic detection of various geometric entities would be beneficial for classifying partial surfaces and volumetric ranges to gain customized informational insights of geometric parameterization. In this work, an enhanced approach of geometric deep learning for the analysis of voxelized engineering parts will be presented to align the inference representations to modeling paradigms for complex design models like architected materials. Although the baseline voxel representation offers distinct advantages in detection accuracy, it comes with an adversely large memory footprint. The geometry discretization leads to high resolutions needed to capture various detail levels that prevent the analysis of fine-grained objects. To achieve efficient usage of 3D deep learning techniques, we propose a 3D-CNN-based feature recognition approach using signed distance field data to limit the needed resolution. This implicit geometric data leverages the advantages of volumetric convolution while alleviating their disadvantages through the use of the continuous signed distance function. When analyzing CAD data for geometric primitive features, a common application task in surface reconstruction of reverse engineering, the proposed methodology achieves a detection accuracy that is in line with the accuracy values achieved by comparable algorithms. This enables the recognition of fine-grained surface instances. The unambiguous shape information extracted could be used in subsequent adaptive slicing algorithms to achieve individual geometry-based hatch generation.


Seiten (von - bis)992-1009
FachzeitschriftJournal of Computational Design and Engineering
PublikationsstatusVeröffentlicht - 4 Apr. 2023

Externe IDs

WOS 000985982200003
dblp journals/jcde/HilbigVHP23
Mendeley 8455d04e-655b-3c76-a642-b6aa28479537
unpaywall 10.1093/jcde/qwad027
Scopus 85163017861
ORCID /0000-0003-3368-4130/work/142253602


DFG-Fachsystematik nach Fachkollegium

Fächergruppen, Lehr- und Forschungsbereiche, Fachgebiete nach Destatis

Ziele für nachhaltige Entwicklung


  • Adaptive slicing, Additive manufacturing, Deep learning, Feature recognition, Signed-distance field, Voxel data, deep learning, voxel data, additive manufacturing, signed-distance field, adaptive slicing, feature recognition