DataPDF Available


This is Part 1/3 of the 3D Engineering CAD data in Part 1 - Classes 1 through 15. The classes are standardized components - Bearings, Bolts, Brackets, Bushing, Bushing Liners, Collets, Gaskets, Grommets, Headless Screws, Hex-Head Screws, Keyway Shaft, Machine key, Nuts, O-rings, Thumb-Screws. The data comes in .STL and .STEP formats. Each model also comes with an accompanying .JPEG image capture of the 3D part for view purposes. New formats can be obtained from converting each CAD file to other appropriate formats. If dataset is used, please cite Starly, Binil; Bharadwaj, Akshay; Angrish, Atin. (2019). FabWave CAD Repository Categorized Part Classes. doi:10.5061/dryad.vmcvdncqp? Alternate Full Dataset download link:

File (1)

Content uploaded by Binil Starly
Author content
... FFS contains various thresholds and configurable parameters (shown in Table 1) that affect the timing and storage overheads, as well as the accuracy of our framework. Table 2 summarizes performance and top-3 accuracy for our exact match experiments using the FabWave dataset [22]. In this case, top-3 accuracy measures if one of the first three retrieved answers correctly identifies the input query model; in general, top-K accuracy measures if the expected answer is among the first K retrieved results. ...
... We implemented FFS using Python 3.6.8 and LevelDB 1. 22, an open-source VOLUME 4, 2020 key-value storage library provided by Google. 3 Finally, the host system is running Ubuntu 18.04 with the 4.15.0 ...
An ever-increasing number of industries are adopting additive manufacturing (AM), also known as 3D printing, to their production lifecycles for manufacturing parts. A computer aided design (CAD) model is used to manufacture the part. The capability for efficient search and retrieval of the CAD models from the database has become an essential need for designers and users. However, traditional search techniques perform poorly in the context of searching CAD designs. In this paper, we propose Fourier Fingerprint Search (FFS), a retrieval framework for 3D models that deduces and leverages critical shape characteristics for search. FFS introduces a novel search methodology that incorporates these characteristics and uses two advanced matching techniques that operate at different granularities and take into account unique patterns associated with each design. In addition, FFS supports both exact and partial matching in order to provide helpful and robust search results for any scenario. We investigate a diverse set of features and enhancements for search that allows for high adaptability in all situations, such as dividing shapes into smaller parts, surface interpolation, and two different types of rotation. We evaluate FFS using the FabWave CAD dataset with approximately 3000 manufacturing models with different configurations. Our experimental results demonstrate the efficiency and high accuracy of our approach for both exact and partial matching, rendering FFS a powerful framework for CAD model search.
ResearchGate has not been able to resolve any references for this publication.