Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userDeep Learning and Crystal Plasticity: A Preconditioning Approach for Accurate Orientation Evolution Prediction
95
0
0.0
(
0
)
Ask ChatGPT about the research
No Arabic abstract
Efficient and precise prediction of plasticity by data-driven models relies on appropriate data preparation and a well-designed model. Here we introduce an unsupervised machine learning-based data preparation method to maximize the trainability of crystal orientation evolution data during deformation. For Taylor model crystal plasticity data, the preconditioning procedure improves the test score of an artificial neural network from 0.831 to 0.999, while decreasing the training iterations by an order of magnitude. The efficacy of the approach was further improved with a recurrent neural network. Electron backscattered (EBSD) lab measurements of crystal rotation during rolling were compared with the results of the surrogate model, and despite error introduced by Taylor model simplifying assumptions, very reasonable agreement between the surrogate model and experiment was observed. Our method is foundational for further data-driven studies, enabling the efficient and precise prediction of texture evolution from experimental and simulated crystal plasticity results.
rate research
Read More
Crystal structure prediction is one of the major unsolved problems in materials science. Traditionally, this problem is formulated as a global optimization problem for which global search algorithms are combined with first principle free energy calculations to predict the ground-state crystal structure given only a material composition or a chemical system. These ab initio algorithms usually cannot exploit a large amount of implicit physicochemical rules or geometric constraints (deep knowledge) of atom configurations embodied in a large number of known crystal structures. Inspired by the deep learning enabled breakthrough in protein structure prediction, herein we propose AlphaCrystal, a crystal structure prediction algorithm that combines a deep residual neural network model that learns deep knowledge to guide predicting the atomic contact map of a target crystal material followed by reconstructing its 3D crystal structure using genetic algorithms. Based on the experiments of a selected set of benchmark crystal materials, we show that our AlphaCrystal algorithm can predict structures close to the ground truth structures. It can also speed up the crystal structure prediction process by predicting and exploiting the predicted contact map so that it has the potential to handle relatively large systems. We believe that our deep learning based ab initio crystal structure prediction method that learns from existing material structures can be used to scale up current crystal structure prediction practice. To our knowledge, AlphaCrystal is the first neural network based algorithm for crystal structure contact map prediction and the first method for directly reconstructing crystal structures from materials composition, which can be further optimized by DFT calculations.
The use of machine learning methods for accelerating the design of crystalline materials usually requires manually constructed feature vectors or complex transformation of atom coordinates to input the crystal structure, which either constrains the model to certain crystal types or makes it difficult to provide chemical insights. Here, we develop a crystal graph convolutional neural networks framework to directly learn material properties from the connection of atoms in the crystal, providing a universal and interpretable representation of crystalline materials. Our method provides a highly accurate prediction of density functional theory calculated properties for eight different properties of crystals with various structure types and compositions after being trained with $10^4$ data points. Further, our framework is interpretable because one can extract the contributions from local chemical environments to global properties. Using an example of perovskites, we show how this information can be utilized to discover empirical rules for materials design.
In their Letter, Haziot et al. [Phys. Rev. Lett. 110 (2013) 035301] report a novel phenomenon of giant plasticity for hcp Helium-4 quantum crystals. They assert that Helium-4 exhibits mechanical properties not found in classical plasticity theory. Specifically, they examine high-quality crystals as a function of temperature and applied strain, where the shear modulus reaches a plateau and dissipation becomes close to zero; both quantities are reported to be independent of stress and strain, implying a reversible dissipation process and quantum tunneling. In this Comment, we show that these signatures can be explained with a classical model of thermally activated dislocation glide without the need to invoke quantum tunneling or dissipationless motion. Recently, we proposed a dislocation glide model in solid Helium-4 containing the dissipation contribution in the presence of other dislocations with qualitatively similar behavior [Zhou et al., Philos. Mag. Lett. 92 (2012) 608].
The critical dynamics of dislocation avalanches in plastic flow is examined using a phase field crystal (PFC) model. In the model, dislocations are naturally created, without any textit{ad hoc} creation rules, by applying a shearing force to the perfectly periodic ground state. These dislocations diffuse, interact and annihilate with one another, forming avalanche events. By data collapsing the event energy probability density function for different shearing rates, a connection to interface depinning dynamics is confirmed. The relevant critical exponents agree with mean field theory predictions.
Plastic deformation in polycrystals is governed by the interplay between intra-granular slip and grain boundary-mediated plasticity. However, while the role played by bulk dislocations is relatively well-understood, the contribution of grain boundaries (GBs) has only recently begun to be studied. GB plasticity is known to play a key role along with bulk plasticity under a wide range of conditions, such as dynamic recovery, superplasticity, severe plastic deformation , etc., and developing models capable of simultaneously capturing GB and bulk plasticity has become a topic of high relevance. In this paper we develop a thermodynamically-consistent polycrystal plasticity model capable of simulating a variety of grain boundary-mediated plastic processes in conjunction with bulk dislocation slip. The model starts from the description of a single crystal and creates lattice strain-free polycrystalline configurations by using a specially-designed multiplicative decomposition developed by the authors. This leads to the introduction of a particular class of geometrically necessary dislocations (GND) that define fundamental GB features such as misorientation and inclination. The evolution of the system is based on an energy functional that uses a non-standard function of the GND tensor to account for the grain boundary energy, as well as for the standard elastic energy. Our implementation builds on smooth descriptions of GBs inspired on diffuse-interface models of grain evolution for numerical convenience. We demonstrate the generality and potential of the methodology by simulating a wide variety of phenomena such as shear-induced GB sliding, coupled GB motion, curvature-induced grain rotation and shrinkage, and polygonization via dislocation sub-grain formation.
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
