| 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 |
A Data Driven-based Geometric Compensation Method for Laser Powder Bed Fusion |
| Author(s) |
Wen Dong, Basil J. Paudel, Albert C. To |
| On-Site Speaker (Planned) |
Wen Dong |
| Abstract Scope |
The residual stress and deformation induced during the laser powder bed fusion (L-PBF) process can degrade the performance and quality of the products and increase the difficulty of post-processing like machining and cutting. The present work develops a data driven-based geometric compensation method to reduce the part distortion in L-PBF processes. The method includes four steps: (1) collect distortion data based on both numerical simulations and experimental measurement; (2) implement principal component analysis to reduce the data size and extract features that account for 99.99% of the total energy; (3) train the Gaussian process model for each feature to establish relationships between the initial and as-built shape of a part; (4) apply the trained model to generate the compensated geometry so that the as-built shape is the desired one. The experimental validation shows that the proposed approach is able to effectively improve the geometric accuracy of the as-built part. |
| Proceedings Inclusion? |
Definite: Post-meeting proceedings |