Skip to main content
U.S. flag

An official website of the United States government

Official websites use .gov
A .gov website belongs to an official government organization in the United States.

Secure .gov websites use HTTPS
A lock ( ) or https:// means you’ve safely connected to the .gov website. Share sensitive information only on official, secure websites.

Statistical and Spatio-temporal Data Features in Melt Pool Monitoring of Additive Manufacturing

Published

Author(s)

Brandon Lane, Ho Yeung, Zhuo Yang

Abstract

Co-axial melt pool monitoring is an in-situ method applied in laser-powder bed fusion (LPBF) processes which uses a high-speed camera optically aligned with the scanning laser to continuously observe and measure the melt pool. This results in a large volume of image data, which subsequently needs to be processed into data features that aim to be statistically correlated to processing or part quality metrics. One such processing method uses the laser position information to superimpose melt pool images onto the part coordinates, creating a stitched image or mosaic resembling part geometry. While superposition reduces the overall data volume and provides registration and visualization of melt pool image data to 3D part geometry, initial algorithms have demonstrated only a handful of static image features. This paper demonstrates an updated, generalized algorithm using dynamic arrays to efficiently store and process the image data and corresponding temporal information. Using this generalized algorithm, multiple physics-based data features are demonstrated using real data from a LPBF build. Each feature is then discussed in terms of their physical relevance to fabrication quality, and potential for predictive process control.
Proceedings Title
Proceedings of the 2022 IISE Annual Conference
Conference Dates
May 21-24, 2022
Conference Location
Seattle, WA, US
Conference Title
IISE Annual Conference and Expo 2022

Keywords

Laser powder bed fusion, melt pool monitoring, digital twin, superposition

Citation

Lane, B. , Yeung, H. and Yang, Z. (2022), Statistical and Spatio-temporal Data Features in Melt Pool Monitoring of Additive Manufacturing, Proceedings of the 2022 IISE Annual Conference, Seattle, WA, US, [online], https://tsapps.nist.gov/publication/get_pdf.cfm?pub_id=934033 (Accessed March 28, 2024)
Created May 23, 2022, Updated November 29, 2022