With product customization an emerging business opportunity, organizations must find ways to collaborate and enable sharing of information in an inherently trust-less network. In this paper, we propose -"FabRec": a decentralized approach to handle manufacturing information generated by various organizations using blockchain technology. We propose a system in which a decentralized network of manufacturing machines and computing nodes can enable automated transparency of an organization's capability, third party verification of such capability through a trail of past historic events and automated mechanisms to drive paperless contracts between participants using 'smart contracts'. Our system decentralizes critical information about the manufacturer and makes it available on a peer-topeer network composed of fiduciary nodes to ensure transparency and data provenance through a verifiable audit trail. We present a testbed platform through a combination of manufacturing machines, system-on-chip platforms and computing nodes to demonstrate mechanisms through which a consortium of disparate organizations can communicate through a decentralized network. Our prototype testbed demonstrates the value of computer code residing on a decentralized network for verification of information on the blockchain and ways in which actions can be autonomously initiated in the physical world. This paper intends to expose system elements in preparation for much larger field tests through the working prototype and discusses the future potential of blockchain for manufacturing IT.
Deep neural networks have shown promising success towards the classification and retrieval tasks for images and text data. While there have been several implementations of deep networks in the area of computer graphics, these algorithms do not translate easily across different datasets, especially for shapes used in product design and manufacturing domain. Unlike datasets used in the 3D shape classification and retrieval in the computer graphics domain, engineering level description of 3D models do not yield themselves to neat distinct classes. The current study looks at an improved form of the 3D shape deep learning algorithm for classification and retrieval through the use of techniques such as relaxed classification, use of prime angled camera angles for capturing feature detail and transfer learning for reducing the amount of data and processing time needed to train shape recognition algorithms. The proposed algorithm (MVCNN++) builds on top of multi-view convolutional neural network (MVCNN) algorithm, improving its efficacy for manufacturing part classification by enabling use of part metadata, yielding an improvement of almost 6% over the original version. With the explosive growth of 3D product models available in publicly available repositories, search and discovery of relevant models is critical to democratizing access to design models.
In this paper, we present "FabSearch", a prototype search engine for sourcing manufacturer service providers, by making use of the product manufacturing information contained within a 3D digital file of a product. FabSearch is designed to take in a query 3D model, such as the .STEP file of a part model which then produces a ranked list of job shop service providers who are best suited to fabricate the part. Service providers may have potentially built hundreds to thousands of parts with associated part 3D models over time. FabSearch assumes that these service providers have shared shape signatures of the part models built previously to enable the algorithm to most effectively rank the service providers who have the most experience to build the query part model. FabSearch has two
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.