|About this Abstract
||2018 TMS Annual Meeting & Exhibition
||Coupling Experiments and Modeling to Understand Plasticity and Failure
||E-17: Using Machine Learning Approaches towards Quantifying the Deformation History of Crystals: Examples from Discrete Dislocation Dynamics
||Michail Tzimas, Stefanos Papanikolaou, Hengxu Song, Andrew C.E. Reid, Stephen A. Langer
|On-Site Speaker (Planned)
Digital image correlation (DIC) is an established technique for tracking and quantifying the deformation of mechanical samples under strain. While it provides a way to observe displacement information, it seems likely that DIC data sets, which reflect the response of a microstructure to loading, contain richer information than previously observed. We demonstrate a machine learning (ML) approach to quantifying the prior deformation history of a crystalline sample based on its response to a DIC test. This prior deformation history is encoded in the microstructure through the inhomogeneity of the dislocation microstructure and in the spatial correlations of the dislocation patterns. Our playground consists of deformed crystalline thin films generated by a discrete dislocation plasticity simulation. We explore the range of applicability of ML as a function of size effects and stochasticity.
||Planned: Supplemental Proceedings volume