Learning crystal plasticity using digital image correlation: Examples from discrete dislocation dynamics

Digital image correlation (DIC) is a well-established, non-invasive technique for tracking and quantifying the deformation of mechanical samples under strain. While it provides an obvious way to observe incremental and aggregate displacement information, it seems likely that DIC data sets, which after all reflect the spatially-resolved response of a microstructure to loads, contain much richer information than has generally been extracted from them. In this paper, we demonstrate a machine-learning approach to quantifying the prior deformation history of a crystalline sample based on its response to a subsequent 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, which mediate the system's response to the DIC test load. Our domain consists of deformed crystalline thin films generated by a discrete dislocation plasticity simulation. We explore the range of applicability of machine learning (ML) for typical experimental protocols, and as a function of possible size effects and stochasticity. Plasticity size effects may directly influence the data, rendering unsupervised techniques unable to distinguish different plasticity regimes.

[1]  Andrew M Minor,et al.  Mechanical annealing and source-limited deformation in submicrometre-diameter Ni crystals. , 2008, Nature materials.

[2]  van der Erik Giessen,et al.  Discrete dislocation plasticity: a simple planar model , 1995 .

[3]  Anthony Nathan Fast Developing Higher-Order Materials Knowledge Systems , 2011 .

[4]  William H. Press,et al.  Numerical Recipes 3rd Edition: The Art of Scientific Computing , 2007 .

[5]  Robert J. Asaro,et al.  Mechanics of Solids and Materials , 2006 .

[6]  Vikram Deshpande,et al.  Tensile response of passivated films with climb-assisted dislocation glide , 2012 .

[7]  Surya R. Kalidindi,et al.  Application of data science tools to quantify and distinguish between structures and models in molecular dynamics datasets , 2015, Nanotechnology.

[8]  Trevor Hastie,et al.  An Introduction to Statistical Learning , 2013, Springer Texts in Statistics.

[9]  John Lambros,et al.  High resolution digital image correlation measurements of strain accumulation in fatigue crack growth , 2013 .

[10]  Stefanos Papanikolaou,et al.  Obstacles and sources in dislocation dynamics: Strengthening and statistics of abrupt plastic events in nanopillar compression , 2015, 1511.04613.

[11]  Peter Norvig,et al.  Artificial Intelligence: A Modern Approach , 1995 .

[12]  C. Boehlert,et al.  Evaluating the Plastic Anisotropy of AZ31 Using Microscopy Techniques , 2013, JOM.

[13]  Satoru Yoneyama,et al.  DIGITAL IMAGE CORRELATION , 2011 .

[14]  Carl E. Rasmussen,et al.  Gaussian Processes for Machine Learning (GPML) Toolbox , 2010, J. Mach. Learn. Res..

[15]  Zhiqiang Wang,et al.  A parallel algorithm for 3D dislocation dynamics , 2006, J. Comput. Phys..

[16]  Zhe Chen A STUDY OF THE EFFECTS OF PROCESSING AND ALLOYING ON THE MICROSTRUCTURE AND DEFORMATION BEHAVIOR OF WROUGHT MAGNESIUM ALLOYS , 2012 .

[17]  William E. Frazier,et al.  Metal Additive Manufacturing: A Review , 2014, Journal of Materials Engineering and Performance.

[18]  Tyrus Berry,et al.  Consistent manifold representation for topological data analysis , 2016, Foundations of Data Science.

[19]  Peter Norvig,et al.  Artificial intelligence - a modern approach, 2nd Edition , 2003, Prentice Hall series in artificial intelligence.