About this Abstract |
Meeting |
2022 Annual International Solid Freeform Fabrication Symposium (SFF Symp 2022)
|
Symposium
|
2022 Annual International Solid Freeform Fabrication Symposium (SFF Symp 2022)
|
Presentation Title |
Porosity Prediction for Multiple Processing Regimes in Laser Powder Bed Fusion via Machine Learning of In-situ Multi-modal Monitoring Data |
Author(s) |
Haolin Zhang, Chaitanya Prasad Vallabh, Alexander N Caputo, Richard W. Neu, Xiayun Zhao |
On-Site Speaker (Planned) |
Haolin Zhang |
Abstract Scope |
In metal additive manufacturing (AM) processes, such as Laser Powder Bed Fusion (LPBF), complex laser-powder interactions make the process difficult to monitor and qualify. One such major challenge is the quantification of process-induced porosity. Porosity is detrimental to the mechanical properties and the life-cycle of the manufactured part. In this work, we develop a machine learning aided porosity prediction framework utilizing the in-situ monitored, multi-modal, melt pool (MP) and powder bed signatures as input to predict the process-induced porosity in the final printed part. The proposed input signatures are our in-house 1) single camera two wavelength imaging pyrometry (STWIP) measured MP temperature and MP area, and 2) Fringe Projection profilometry (FPP) measured surface topography. A machine learning based porosity correlation framework will be developed to derive quantitative metrics of the porosity from the multiple in-situ MP signatures. Further, this framework has the potential to be implemented for online defect detection. |
Proceedings Inclusion? |
Definite: Post-meeting proceedings |