About this Abstract |
Meeting |
MS&T22: Materials Science & Technology
|
Symposium
|
2022 Undergraduate Student Poster Contest
|
Presentation Title |
Automated Quantification of Microstructure & Damage in Large SiC-SiC CMC Computed Tomography Datasets via Machine Learning |
Author(s) |
Tyriek Craigs, Ashley Hilmas, Craig Przybyla |
On-Site Speaker (Planned) |
Tyriek Craigs |
Abstract Scope |
X-ray CT imaging is a 3D imaging technique used to obtain detailed internal images within a material. This technique is valuable because it allows for the ability to both visualize and quantify the entire volume of complex 3D microstructures. While such valuable information can be obtained through these techniques, the ability to accurately and efficiently quantify these datasets manually has proven to be difficult. With the development of machine learning algorithms it’s now feasible to automate the segmentation process, in-turn reducing the R&D time for these materials. This work focuses a machine learning algorithm that was developed to quantify the initial microstructure of a SiC-SiC ceramic matrix composite (CMC) and the algorithms currently being developed to track damage evolution throughout the CMC. The objective is to develop an algorithm that can discern the microstructure while tracking the formation of damage before and after in-situ mechanical testing. |