Spatial prediction of crystalline defects observed in molecular dynamic simulations of plastic damage

Peterson, Geoffrey Colin Lee; Liu, Dong; Reich, Brian J.; Brenner, Donald W.

doi:10.1080/02664763.2016.1221915

Cited by 1 publication

(2 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[17,18] In two recent studies, statistical and image analysis approaches were used to characterize plastic damage from MD simulations. [22,23] Both studies used coarse-grained matrices of central symmetry parameters (CSPs) [13] generated from a training set of plastic damage in strained bi-crystals containing two complementary symmetric grain boundaries with different tilt angles prepared as described in Section II below. The first study used three spatial regression approaches, a conditional autoregressive model, discrete wavelets, and principle component analysis, in an attempt to predict plastic damage at different tilt angles based on the training set.…”

Section: Introductionmentioning

confidence: 99%

“…The first study used three spatial regression approaches, a conditional autoregressive model, discrete wavelets, and principle component analysis, in an attempt to predict plastic damage at different tilt angles based on the training set. [22] Although the statistical models varied in their predictive capabilities, none was able to predict spatially-resolved plastic damage at an acceptable level to replace an MD simulation. In the second study, normalized spatial autocorrelation matrices were created from the CSP matrix of each MD simulation, and then cross-correlation (CC) matrices were generated from each of the auto-correlation matrices.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Statistical and image analysis for characterizing simulated atomic-scale damage in crystals

Reich

Brenner

2017

Computational Materials Science

View full text Add to dashboard Cite

While molecular dynamics simulations have been used for decades to study structure and formation mechanisms of plastic damage in crystals, the analytical tools needed to characterize collections of plastic defects have been limited. Here we demonstrate the use of two methods, spatial cross-correlations (CC) and Linear Discriminate Analysis (LDA), to analyze and compare plastic damage profiles among molecular dynamics simulations in which damage was created by straining bi-crystals containing symmetric tilt grain boundaries with different tilt angles. Two potentials were used, one representing Cu and one representing Ag, and two coarse-grained descriptors for different types of crystal damage were used, averaged central symmetry parameters (CSP) and atomic hydrostatic stress (HS). We find that in general the CSP is a more accurate descriptor than HS for both analysis methods, and for data base sizes of about 30 or more simulations per tilt angle, the LDA does considerably better in predicting angle and material than the CC method. For example, at the largest data base size of 50 simulations per tilt angle and using the average CSP values, the LDA predicts the exact initial tilt angle and material type for 92% of the simulations, while the CC approach drops to 58%. If the average HS is used instead of the average CSP, the LDA and CC predictions drop to 63% and 32%, respectively. These results point to a number of possible applications of this method, for example in quantifying how the range of damage for a set of strained systems may depend on strain rate or temperature, or quantifying similarities between complex damage from processes such as indentation and energetic ion bombardment.

show abstract