Data Science for Additive Manufacturing

Advancing AM Through Data Science

The extensive amounts of data generated during design-to-product transformation provide a valuable resource on which new insights can be gained into and about parts and processes. The application of data science to AM, ranging from information modeling to machine learning to process and simulation to digital twins, has become an integral aspect of advancing AM technologies and their adoption. Our team develops valuable data resources to support these advancements in the AM community, like the NIST Additive Manufacturing Material Database, pictured below. 

Select the magnifying glass to enlarge the image.

Sharing Measurement Results Using Data Science

The immense amount of measurement data generated by the Additive Manufacturing Benchmark Series (AM Bench) has necessitated the development and deployment of multiple systems and pathways for users to access, download, search, and analyze AM Bench data and metadata. The diagram below shows the overall structure of our internal and outward-facing data systems. Descriptions and links to the outward-facing systems can be accessed at the "AM Bench Data Management Systems" website. 

Select the magnifying glass to enlarge the image.

Back to Top

Advanced Informatics and Artificial Intelligence for Additive Manufacturing

Advancements in additive manufacturing are progressively driven by digital technologies, with advanced sensors and measurements informing increasingly complex modeling and simulation paradigms and playing an important role in part design, production, and qualification. Advanced informatics are providing new opportunities to harness trusted data and information to acquire knowledge and develop actionable assessments in complex AM systems and environments. Read more.

Project Leader: Paul Witherell

Additive Manufacturing Benchmark Test Series

Additive Manufacturing Benchmark Test Series (AM Bench) provides a continuing series of AM benchmark measurements, challenge problems, and conferences with the primary goal of enabling modelers to test their simulations against rigorous, highly controlled additive manufacturing benchmark measurement data. Read more. 

Points of Contact: Lyle Levine & Jordan Weaver

Data Management and Fusion for AM Industrialization

The maturation of additive manufacturing into an industrialization (wide-scale production) technology requires an expanded notion of integration of both heterogenous systems and data in a production environment. Data fusion combines integrated data from various sources and uses advanced data analytics to achieve inferences and decision making that cannot be obtained from a single source. Methods and standards for AM data integration and fusion need to scale up as well to streamline production workflows and improve decision-making across the AM supply chain. Read more.

Project Leader: Yan Lu

Back to Top

Updated Standard Provides Fundamental 3D-Printing Design Guidance to Streamline

The American Society of Mechanical Engineers (ASME) published an updated standard, based in large part on research by NIST, that includes language specifically for 3D printing. Read more.

Back to Top