| About this Abstract |
| Meeting |
MS&T24: Materials Science & Technology
|
| Symposium
|
Standards for Data Science in Additive Manufacturing
|
| Presentation Title |
Challenges in Producing, Curating, and Sharing Large Multimodal, Multi-Institutional Data Sets for Additive Manufacturing |
| Author(s) |
Lyle E. Levine, Brandon Lane, Gerard Lemson, Jai Won Kim, Shengyen Li, Gretchen Greene |
| On-Site Speaker (Planned) |
Lyle E. Levine |
| Abstract Scope |
The additive manufacturing benchmark series (AM Bench) provides the AM community with rigorous measurement datasets for model validation. Through a collaboration that includes more than a hundred scientists from 11 divisions within the National Institute of Standards and Technology (NIST) and 20 external organizations, AM Bench recently released eight comprehensive sets of metal and polymer AM benchmark data. Developing effective data management and data sharing solutions is critical for providing these validation measurement data to the AM community. Challenges include ensuring measurement and sample provenance, capturing and sharing data and metadata for all measurements, producing numerous formal datasets with data descriptor documents and registered DOI’s, data transportation and storage, data searching, data security, and providing server-side compute capabilities for users to explore large congruent and multimodal datasets. For harmonization with other AM data efforts, adherence to AM data standards and participation in the corresponding data standards activities is required. |