Project Introduction
Title: An Effective Quality Assurance Method for Additively Manufactured Gas Turbine Metallic Components via Machine Learning from In-Situ Monitoring, Part-scale Modeling, and Ex-Situ Characterization Data
Sponsor: Department of Energy (DoE), National Energy Technology Laboratory (NETL)
Period of Performance: Oct-01-2019 to Sept-30-2022
Total DoE Award: $802,400
Total Project Cost: $1,003,000
Role: PI
Collaborators: Georgia Tech, ANSYS, a USA Turbine Manufacturer
(other info: News Link)
Lab-designed in-situ monitoring system of LPBF based AM (EOS M290 DMLS)
Overall System: In-situ Multi-sensor Comprehensive Monitoring for
-
Melt Pool (MP) Temperature Profile and Morphology
-
Powder Bed and Printed Layer Surface Topography
-
Off-axis Camera Imaging for MP registration and spatter tracking
Subsystem: In-situ Coaxial Two-wavelength Single-camera Imaging Pyrometry (Patent Pending)