Results and raw data of an adjustable similarity calculation for computer aided design (CAD) datahttps://doi.org/10.18419/darus-813Zink, DennisDaRUS2020-05-272022-06-03T21:15:08ZThe here shown data results from a methodology for calculating the similarity of CAD parts. CAD parts are analyzed using various algorithms to find geometric features and discrete point cloud representations.
The folder AnalyzedCADData contains a zip-file with the raw analyzed data of each part. All evaluated results can be found in folder EvaluationOfData in HDF5 formattet tables. An overview of the data set and the analyzed geometric features is given by an interactive HTML diagram in folder FeatureDiagram.Computer and Information ScienceEngineeringCAD (Computer-aided design)Similarity (Geometry)EnglishPhD thesis in progress: Methoden für die Bewertung des Leichtbaupotenzials sowie der Fertigbarkeit von Bauteilgeometrien bezüglich der Umsetzung in Faserverbundbauweisen2020-05-21Zink, Dennis2020-05-20The CAD data set is an excerpt of the ABC data set: <a href="https://deep-geometry.github.io/abc-dataset/">https://deep-geometry.github.io/abc-dataset/</a>. 5322 parts were used and disassembled to 42327 single bodies.
More information about the data set is published in S. Koch, A. Matveev, Z. Jiang, F. Williams, A. Artemov, E. Burnaev, M. Alexa, D. Zorin, D. Panozzo, Abc: A big cad model dataset for geometric deep learning, in: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019, pp. 9601-9611.CAD data in Siemens NX formatHDF5 dataInteractive HTML diagram3D PDFsText filesPicturesCC BY 4.0