TY - JOUR
T1 - Learning to Predict Crystal Plasticity at the Nanoscale
T2 - Deep Residual Networks and Size Effects in Uniaxial Compression Discrete Dislocation Simulations
AU - Yang, Zijiang
AU - Papanikolaou, Stefanos
AU - Reid, Andrew C.E.
AU - Liao, Wei keng
AU - Choudhary, Alok Nidhi
AU - Campbell, Carelyn
AU - Agrawal, Ankit
PY - 2020/12/1
Y1 - 2020/12/1
N2 - The density and configurational changes of crystal dislocations during plastic deformation influence the mechanical properties of materials. These influences have become clearest in nanoscale experiments, in terms of strength, hardness and work hardening size effects in small volumes. The mechanical characterization of a model crystal may be cast as an inverse problem of deducing the defect population characteristics (density, correlations) in small volumes from the mechanical behavior. In this work, we demonstrate how a deep residual network can be used to deduce the dislocation characteristics of a sample of interest using only its surface strain profiles at small deformations, and then statistically predict the mechanical response of size-affected samples at larger deformations. As a testbed of our approach, we utilize high-throughput discrete dislocation simulations for systems of widths that range from nano- to micro- meters. We show that the proposed deep learning model significantly outperforms a traditional machine learning model, as well as accurately produces statistical predictions of the size effects in samples of various widths. By visualizing the filters in convolutional layers and saliency maps, we find that the proposed model is able to learn the significant features of sample strain profiles.
AB - The density and configurational changes of crystal dislocations during plastic deformation influence the mechanical properties of materials. These influences have become clearest in nanoscale experiments, in terms of strength, hardness and work hardening size effects in small volumes. The mechanical characterization of a model crystal may be cast as an inverse problem of deducing the defect population characteristics (density, correlations) in small volumes from the mechanical behavior. In this work, we demonstrate how a deep residual network can be used to deduce the dislocation characteristics of a sample of interest using only its surface strain profiles at small deformations, and then statistically predict the mechanical response of size-affected samples at larger deformations. As a testbed of our approach, we utilize high-throughput discrete dislocation simulations for systems of widths that range from nano- to micro- meters. We show that the proposed deep learning model significantly outperforms a traditional machine learning model, as well as accurately produces statistical predictions of the size effects in samples of various widths. By visualizing the filters in convolutional layers and saliency maps, we find that the proposed model is able to learn the significant features of sample strain profiles.
UR - http://www.scopus.com/inward/record.url?scp=85084964798&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85084964798&partnerID=8YFLogxK
U2 - 10.1038/s41598-020-65157-z
DO - 10.1038/s41598-020-65157-z
M3 - Article
C2 - 32427971
AN - SCOPUS:85084964798
VL - 10
JO - Scientific Reports
JF - Scientific Reports
SN - 2045-2322
IS - 1
M1 - 8262
ER -