About this Abstract |
| Meeting |
2027 TMS Annual Meeting & Exhibition
|
| Symposium
|
AI-Enabled Materials Processing: Integrating Accelerated Experimental Workflows and Processing-Aware Machine Learning
|
| Presentation Title |
Asynchronous, Autonomous Materials Aging Characterization |
| Author(s) |
Ryan Katona, Kenneth Plackowski, Spencer Newman, Matthew Roop, Jason Taylor, Matthew Kottwitz, Erik Linde, Justin Hall, John Curry |
| On-Site Speaker (Planned) |
Ryan Katona |
| Abstract Scope |
Materials aging influences the long-term performance, reliability, and safety of components, yet conventional laboratory workflows are often too slow, siloed, and inflexible to efficiently evaluate degradation across broad material sets and exposure conditions. A high-throughput materials science laboratory was developed to accelerate the study of aging mechanisms through an integrated, adaptable experimental framework that combines imaging, tribology, and compression testing. To support rapid experimentation and scalable operation, the laboratory is designed on a NATS server architecture, enabling modular instrument integration, real-time communication, and streamlined asynchronous automation of experimental workflows. Continuous data streaming supports centralized storage, remote access, scalable analysis, and the development of data-driven models linking aging conditions to material response. This high-throughput laboratory will generate robust datasets, improve lifetime assessment through machine learning, and accelerate the development and qualification of durable materials for critical applications.
SNL is managed and operated by NTESS under DOE NNSA contract DE-NA0003525. SAND2026-23041A. |
| Proceedings Inclusion? |
Planned: |
| Keywords |
Characterization, Machine Learning, Other |