About this Abstract |
| Meeting |
2025 Annual International Solid Freeform Fabrication Symposium (SFF Symp 2025)
|
| Symposium
|
2025 Annual International Solid Freeform Fabrication Symposium (SFF Symp 2025)
|
| Presentation Title |
Detecting Unstable Keyhole Fluctuations Through Acoustic Emissions in LPBF |
| Author(s) |
Rik Vaerenberg, Shivam Shukla, Bey Vrancken, Konstantinos Gryllias |
| On-Site Speaker (Planned) |
Rik Vaerenberg |
| Abstract Scope |
In-situ vibro-acoustic monitoring of LPBF is a promising solution to the issue of quality assurance of LPBF. However, due to the complexity of the recorded signals, the signals have so far been mainly interpreted based on machine learning approaches. While these models show impressive performance, the model performance is reliant on the availability of large scale, labelled datasets and are very sensitive to distribution shifts. Therefore, this work presents an analytical signal processing approach to the detection of unstable keyholes in LPBF.
The approach is based on the characteristic collapses of the unstable keyhole which are expected to show between 2.5kHz and 50kHz. However, the acoustic emission structure borne sensor is not sensitive in this frequency region. This work proposes instead to demodulate the higher frequency content of the signal and that through this envelope approach the oscillations can be found between 10-20kHz. |
| Proceedings Inclusion? |
Planned: Post-meeting proceedings |