|About this Abstract
||2016 TMS Annual Meeting & Exhibition
||Additive Manufacturing: Building the Pathway towards Process and Material Qualification
||Automated In-situ Defect Detection and Geometry Validation on the ARCAM Q10 System
||Ryan Dehoff, Vincent Paquit, , Edwin Schwalbach, Michael Groeber, Michael Goin, Michael Pearce
|On-Site Speaker (Planned)
The Manufacturing Demonstration Facility (MDF) at the Oak Ridge National Laboratory (ORNL) is conducting extensive data analytics research on in situ-monitoring of metal printing processes. We are interested in quantifying, monitoring and understanding the strong correlation between printed layers quality and the inerrant printing process parameters are essentials to control additive manufacturing techniques. Ultimately, we aim to conduct inline process monitoring, alteration, and correction using real time sensing and data processing techniques. To this end, we are actively developing image processing techniques coupled to machine learning techniques allowing (1) to detect the presence of porosity and defects, (2) to map geometric inaccuracies and surface roughness, (3) to compare CAD models and printed objects for significant variations, and (4) to perform real time quality control of the parts for validation. This presentation will provide some of the advances and results we have accomplished to date.
||Planned: A print-only volume