| About this Abstract |
| Meeting |
2023 TMS Annual Meeting & Exhibition
|
| Symposium
|
Advances in Multi-Principal Element Alloys II
|
| Presentation Title |
Defect Detection and Characterization of Additively Manufactured Al0.1CoCrFeNi High Entropy Alloy |
| Author(s) |
Kwangtae Son, Andy Fan, Baldur Steingrimsson, Peter Liaw, Soon-Jik Hong, Ji-Woon Lee |
| On-Site Speaker (Planned) |
Kwangtae Son |
| Abstract Scope |
Laser powder bed fusion (LPBF) has been investigated in both industrial and academic areas due to its potential to process poor-machinability alloys, such as Al0.1CoCrFeNi high entropy alloy (HEA). One important requisite for LPBF processing of a new alloy like Al0.1CoCrFeNi is to optimize the LPBF process parameters to reduce defect formation. As a fundamental approach to parameter optimization, in-situ monitoring of the Al0.1CoCrFeNi process was conducted, using a multi-sensor system consisting of an infrared camera, acoustic sensor, and spectrometer. Those obtained in-situ sensor data were correlated with the ground truth information from the computational tomography (CT) data. The comparison of sensor data to the ground truth information helped realize the direct defect detection from in-situ sensor signals. Artificial intelligence/machine learning-based software tools are being developed to improve the reliability of the defect identification from sensor data, which is based on the ground truth information of CT data. |
| Proceedings Inclusion? |
Planned: |
| Keywords |
Additive Manufacturing, High-Entropy Alloys, Machine Learning |