About this Abstract |
| Meeting |
MS&T25: Materials Science & Technology
|
| Symposium
|
Additive Manufacturing: Development of Powders
|
| Presentation Title |
Developing Figure of Merit for Feedstock Powders for Printable Inks Through AI-Based SEM Image Processing |
| Author(s) |
Simay Ozsoysal, Jonathan L McNanna, Mysha Momtaz, Mirko Schoenitz, Edward L Dreizin |
| On-Site Speaker (Planned) |
Simay Ozsoysal |
| Abstract Scope |
Spherical powders with controlled particle sizes offer significant advantages for printable inks, enabling higher solids loadings and enhanced resolution in additively manufactured (AM) items. One material-agnostic method to produce such powders is emulsion-assisted milling. The morphology of the produced powders, which is important for AM applications, is affected by the milling process parameters. Understanding these effects is challenging because of the multiple morphology descriptors and the many process parameters. Here, this challenge is addressed by employing AI-based analysis and subsequent processing of large sets of SEM powder images. StarDist, a deep-learning model trained with Python, served to extract diverse shape, size, and structure descriptors for individual powder particles. Powders produced with variable process parameters were prepared and analyzed. Integrated descriptors of the powder quality (figures of merit) were developed. These figures of merit will guide the predictive design and manufacturing of feedstock powders for the printable inks for AM. |