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 |
Characterization of Microscopic Deformation of Materials Using Deep Learning Methods |
Author(s) |
Kavindu Wijesinghe, Janith Wanni, Natasha Kholgade Banerjee, Sean Banerjee, Ajit Achuthan |
On-Site Speaker (Planned) |
Kavindu Wijesinghe |
Abstract Scope |
A microstructure-informed design approach is expected to revolutionize the design of metals and alloy components for aerospace applications. In this approach, a designer utilizes the influence of individual microstructural features on microscopic deformation to yield desirable macroscopic properties. To realize this paradigm shift in practice, advanced experimental capabilities that enable detailed characterization of microscopic deformation of material test specimens are critical. In this study, we propose a data analysis framework based on instance segmentation and tracking of microstructural features using deep learning methods. The method consists of a Mask R-CNN model combined with a regional segmentation algorithm for the instance segmentation of features, an intersection over union (IoU) based multi-object tracking (MOT) algorithm to track segmented instances as they deform, and kinematics models to extract the material characteristics from the geometrical characteristics of the deforming instances. The method is successfully validated experimentally using an additively manufactured 316L stainless steel. |
Proceedings Inclusion? |
Definite: Post-meeting proceedings |