| About this Abstract |
| Meeting |
2023 Annual International Solid Freeform Fabrication Symposium (SFF Symp 2023)
|
| Symposium
|
2023 Annual International Solid Freeform Fabrication Symposium (SFF Symp 2023)
|
| Presentation Title |
Infrared Camera (IR) Feature Extraction for Defect Detection in Laser Powder Bed Fusion |
| Author(s) |
Shawn Hinnebusch, Berkay Bostan, David Anderson, Albert To |
| On-Site Speaker (Planned) |
Shawn Hinnebusch |
| Abstract Scope |
Part qualification is a critical step in advancing additive manufacturing. This work uses an infrared (IR) camera to construct features for a machine learning algorithm to predict defects with +90% accuracy. A custom heating module with thermocouples was employed to calibrate the IR camera with various scanning strategies from room temperature up to 500 ℃. Another custom plate enables angle perspective corrections accounting for distortion caused by the rotation or angle effects of the camera. After image correction, a voxel mesh is superimposed on top of the IR data to distinguish between the powder and the part. The images are separated by layer to analyze layerwise heat accumulation, cooling rates, heat intensities, melt pool spatter, spatter landing location, and scanning strategy. A machine learning algorithm uses the 3D reconstruction as the input to predict defects in a lack of fusion part. |
| Proceedings Inclusion? |
Definite: Post-meeting proceedings |