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.
Product Design based Knowledge graphs (KG) aid the representation of product assemblies through heterogeneous relationships that link entities obtained from multiple structured and unstructured sources. This study describes an approach to constructing a multi-relational and multi-hierarchical knowledge graph that extracts information contained within the 3D product model data to construct Assembly-Subassembly-Part and Shape Similarity relationships. This approach builds on a combination of utilizing 3D model meta-data and structuring the graph using the Assembly-Part hierarchy alongside 3D Shape-based Clustering. To demonstrate our approach, from a dataset consisting of 110,770 CAD models, 92,715 models were organized into 7,651 groups of varying sizes containing highly similar shapes, demonstrating the varied nature of design repositories, but inevitably also containing a significant number of repetitive and unique designs. Using the Product Design Knowledge Graph, we demonstrate the effectiveness of 3D shape retrieval using Approximate Nearest Neighbor search. Finally, we illustrate the use of the KG for Design Reuse of co-occurring components, Rule-Based Inference for Assembly Similarity and Collaborative Filtering for Multi-Modal Search of manufacturing process conditions. Future work aims to expand the KG to include downstream data within product manufacturing and towards improved reasoning methods to provide actionable suggestions for design bot assistants and manufacturing automation.
ResearchGate has not been able to resolve any references for this publication.