About this Abstract |
Meeting |
2020 TMS Annual Meeting & Exhibition
|
Symposium
|
Additive Manufacturing: Advanced Characterization with Synchrotron, Neutron, and In Situ Laboratory-scale Techniques
|
Presentation Title |
A-21: Building a Novel Heat Exchanger with Haynes 230 Alloy and Using Data Science to Characterize Rheological and Microstructural Properties in Additive Manufacturing |
Author(s) |
Srujana Rao Yarasi, Andrew Kitahara, Ziheng Wu, Anthony Rollett, Elizabeth Holm |
On-Site Speaker (Planned) |
Srujana Rao Yarasi |
Abstract Scope |
Additive Manufacturing has enabled novel designs, without restrictions in their complexity, to be produced using superalloys such as Haynes 230. Laser Powder Bed Fusion method is used to fabricate a novel Heat Exchanger using the Haynes 230 superalloy, after optimizing build parameters to minimize defects. There is immense potential in the use of computer vision and machine learning tools in the additive manufacturing domain. This ranges from the quantitative investigation of qualitative factors like powder morphology, which affects the flowability in powder bed fusion processes, to the characterization and analysis of microstructures. Flowability is measured through rheological experiments conducted with the FT4 rheometer and the GranuDrum. The use of Convolutional Neural Networks (CNN) to generate hypercolumn descriptors is proposed as part of a framework that describe characteristics of the powder feedstock such as particle size distribution, sphericity, surface defects, and other morphological features as well as microstructural features. |
Proceedings Inclusion? |
Planned: Supplemental Proceedings volume |