Advanced manufacturing research is dependent on access to large datasets of product models to enable product designers to learn from past errors, and to discover and develop new solutions. However, such datasets are typically archived in inaccessible repositories and may be poorly described and difficult to use by others. Current manufacturing research must shift from siloed repositories of product manufacturing data to a federated, decentralized, open and inter-operable approach. This transformation can be achieved by embedding cyber-capability in every physical end-point, be it on a desktop used by a product designer or within the control systems of a manufacturing machine. The goal of this project is to develop a pilot manufacturing-focused cyberinfrastructure called FabWave. FabWave will gather together digital data on product and manufacturing processes from diverse sources, in particular, three-dimensional (3D) computer aided design (CAD) models generated by academia and public community users, into a new rich dataset that, in turn, will be fully accessible to manufacturing researchers and others. FabWave's system design will be driven by the needs of the manufacturing research community, and the project will encourage its adoption by academic users, government labs and the public. FabWave will aim to lower the barriers for users to upload, share and download 3D product model data; it will also enable manufacturing science researchers to gain access to an information rich dataset for testing and evaluation of algorithms to advance manufacturing research and offer the capability for the community to build custom apps that provide services to the community. This infrastructure development project aligns with the NSF Harnessing Data for 21st Century Science and Engineering Big Ideas vision and can serve to improve US competitiveness in advanced manufacturing.
The de novo cyberinfrastructure tools to be built in the FabWave project include: 1) Direct plugins within design software to allow easier capture of metadata and upload of 3D product models to the FabWave repository with limited human interaction; 2) a data-store with application programming interface (API) tools to allow users to write scripts to search through the repository for content specific to their research questions. Innovative use of the Inter-Planetary File System (IPFS) protocols along with next generation unstructured databases will serve to index and enable search services for Fabwave's users. the project will demonstrate use of FabWave for development of community facing third-party apps and libraries. Ultimately, the research community will have access to a rich source of product datasets created within research laboratories, within classes and through other open sourced projects. This data network, if expanded across universities, would accelerate advancements in cybermanufacturing, engineering systems design, and cyber-physical systems in manufacturing. In addition, FabWave will enable new areas of research in manufacturing information integration and informatics combined with reducing the barriers to exploring the science of manufacturing machine intelligence. This award is supported by the Division of Civil, Mechanical and Manufacturing Innovation and the Office of Advanced Cyberinfrastructure.
This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.