|About this Abstract
||2022 TMS Annual Meeting & Exhibition
||Late News Poster Session
||J-49: Data-driven Quality Control of Laser Directed Energy Deposition (DED)
||Michael Juhasz, Melanie Lang, Jeff Riemann
|On-Site Speaker (Planned)
Defects are a leading cause for rejection of additively manufactured parts. Typically, defect measurements are gathered post-production with little to no remedy in the case where defects are found. In-situ monitoring of Additive Manufacturing (AM) produced parts was employed to collect real-time data during a Directed Energy Deposition (DED) build. The in-situ signatures were linked to post-build defects using Machine Learning (ML)-based, layer classification. A threshold was applied to detect porosity sizes and quantities that render individual layers as acceptable or unacceptable. We demonstrate these ML techniques for the purpose of defect monitoring are shown to be highly effective at classifying acceptable/unacceptable layers real-time during build process.
||Additive Manufacturing, Machine Learning, Characterization