Quantification of morphological change in materials based on image data utilizing machine learning techniques
- Sandia National Laboratories (SNL), Albuquerque, NM, and Livermore, CA (United States)
Computed tomography (CT) resolution has become high enough to monitor morphological changes due to aging in materials in long-term applications. We explored the utility of the critic of a generative adversarial network (GAN) to automatically detect such changes. The GAN was trained with images of pristine Pharmatose, which is used as a surrogate energetic material. It is important to note that images of the material with altered morphology were only used during the test phase. The GAN-generated images visually reproduced the microstructure of Pharmatose well, although some unrealistic particle fusion was seen. Calculated morphological metrics (volume fraction, interfacial line length, and local thickness) for the synthetic images also showed good agreement with the training data, albeit with signs of mode collapse in the interfacial line length. While the critic exposed changes in particle size, it showed limited ability to distinguish images by particle shape. The detection of shape differences was also a more challenging task for the selected morphological metrics that related to energetic material performance. We further tested the critic with images of aged Pharmatose. Subtle changes due to aging are difficult for the human analyst to detect. Both critic and morphological metrics analysis showed image differentiation.
- Research Organization:
- Sandia National Laboratories (SNL-NM), Albuquerque, NM (United States)
- Sponsoring Organization:
- USDOE National Nuclear Security Administration (NNSA)
- DOE Contract Number:
- NA0003525
- OSTI ID:
- 1885639
- Report Number(s):
- SAND2022-11788R; 709495
- Country of Publication:
- United States
- Language:
- English
Similar Records
Utilization of the Critic Subnetwork of a Generative Adversarial Network as Detector of Morphological Material Change in Image Data
Journal Article
·
Sun Dec 11 19:00:00 EST 2022
· Propellants, Explosives, Pyrotechnics
·
OSTI ID:2311783