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 |
Physics-Informed Learning of Real-time Residual Stress in Laser Powder Bed Fusion |
Author(s) |
Xinyi Xiao |
On-Site Speaker (Planned) |
Xinyi Xiao |
Abstract Scope |
Metal additive manufacturing (AM) process recently predominately gained attention by providing flexibility in design and manufacturability, but its rapid heating and cooling lead to deviations in the as-built properties far from the desired. Residual stress is prone to cause build failure and further affect the part functionality performing. However, in-situ residual stress cannot be easily measured and examined for controlling as-built properties in real-time. The recent development of the in-situ monitoring sensors can contribute to carefully examining the process anomalies, such as porosity and cracking issues. However, the quantitative consequences between the observed physical phenomena and the residual stress have not yet been developed. To solve the aforementioned issues, we propose a quantitative method that integrates process-related physical phenomena and a novel neural networks framework to predict and control the in-situ residual stress during the real-time fabrication process. |
Proceedings Inclusion? |
Definite: Post-meeting proceedings |