About this Abstract |
Meeting |
MS&T22: Materials Science & Technology
|
Symposium
|
Materials Processing and Fundamental Understanding Based on Machine Learning and Data Informatics
|
Presentation Title |
B-5: Using Computer Vision and Machine Learning to Characterize Melt Pool Geometry in Additive Manufacturing |
Author(s) |
Han Chien, Bo Lei, Bryan Webler, Elizabeth Holm |
On-Site Speaker (Planned) |
Han Chien |
Abstract Scope |
The dimension of the melt pool determines the initial geometry of the material deposition in the process of laser powder bed fusion (LPBF). It is crucial for quality control to identify the microstructural features by using computer vision techniques. A model is built for deep learning on image segmentation which can recognize the boundaries between the heat affected zone and the unaffected base metal. The model is able to identify the shape and size of the heat affected zone and thus the dimension of the melt pool can be calculated. This study gives insight into the image segmentation of the melt pool geometry and contributes to the dimension measurement of it. |