Deep learning for synthetic microstructure generation in a materials-by-design framework for heterogeneous energetic materials

• Published in: Scientific reports Vol. 10; no. 1; p. 13307
• Main Authors: Chun, Sehyun, Roy, Sidhartha, Nguyen, Yen Thi, Choi, Joseph B., Udaykumar, H. S., Baek, Stephen S.
• Format: Journal Article
• Language: English
• Published: London Nature Publishing Group UK 06.08.2020; Nature Publishing Group
• Subjects: 639/166/988; 639/301/1034/1037; 639/301/930/1032; Chemical reactions; Deep learning; Design; Humanities and Social Sciences; Localization; Microstructure; multidisciplinary; Physics; Porosity; Prediction models; Science; Science (multidisciplinary)

The sensitivity of heterogeneous energetic (HE) materials (propellants, explosives, and pyrotechnics) is critically dependent on their microstructure. Initiation of chemical reactions occurs at hot spots due to energy localization at sites of porosities and other defects. Emerging multi-scale predic...