Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userMolecular simulation-derived features for machine learning predictions of metal glass forming ability
66
0
0.0
(
0
)
Added by
Benjamin Afflerbach
Publication date
2021
fields
Physics
and research's language is
English
Ask ChatGPT about the research
No Arabic abstract
We have developed models of metallic alloy glass forming ability based on newly computationally accessible features obtained from molecular dynamics simulations. In this work we showed that it is possible to increase the predictive value of GFA models by using input features obtained from molecular dynamics simulations. Such features require only relatively straightforward and scalable simulations, making them significantly easier and less expensive to obtain than experimental measurements. We generated a database of molecular dynamics critical cooling rates along with associated candidate features that are inspired from previous research on GFA. Out of the list of 9 proposed GFA features, we identify two as being the most important to performance through a LASSO model. Enthalpy of crystallization and icosahedral-like fraction at 100 K showed promise because they enable a significant improvement to model performance and because they are accessible to flexible ab initio quantum mechanical methods readily applicable to almost all systems. This advancement in computationally accessible features for machine learning predictions GFA will enable future models to more accurately predict new glass forming alloys.
rate research
Read More
Various combinations of characteristic temperatures, such as the glass transition temperature, liquidus temperature, and crystallization temperature, have been proposed as predictions of the glass forming ability of metal alloys. We have used statistical approaches from machine learning to systematically explore a wide range of possible characteristic temperature functions for predicting glass forming ability in the form of critical casting diameter, $D_{max}$. Both linear and non-linear models were used to learn on the largest database of $D_{max}$ values to date consisting of 747 compositions. We find that no combination of temperatures for features offers a better prediction of $D_{max}$ in a machine learning model than the temperatures themselves, and that regression models suffer from poor performance on standard machine learning metrics like root mean square error (minimum value of $3.3 pm 0.1$ $mm$ for data with a standard deviation of 4.8 $mm$). Examination of the errors vs. database size suggest that a larger database may improve results, although a database significantly larger than that used here would likely be required. Shifting a focus from regression to categorization models learning from characteristic temperatures can be used to weakly distinguish glasses likely to be above vs. below our databases median $D_{max}$ value of 4.0 $mm$, with a mean F1 score of $0.77 pm 0.02$ for this categorization. The overall weak results on predicting $D_{max}$ suggests that critical cooling rate might be a better target for machine learning model prediction.
The design of multi-functional BMGs is limited by the lack of a quantitative understanding of the variables that control the glass-forming ability (GFA) of alloys. Both geometric frustration (e.g. differences in atomic radii) and energetic frustration (e.g. differences in the cohesive energies of the atomic species) contribute to the GFA. We perform molecular dynamics simulations of binary Lennard-Jones mixtures with only energetic frustration. We show that there is little correlation between the heat of mixing and critical cooling rate $R_c$, below which the system crystallizes, except that $Delta H_{rm mix} < 0$. By removing the effects of geometric frustration, we show strong correlations between $R_c$ and the variables $epsilon_- = (epsilon_{BB}-epsilon_{AA})/(epsilon_{AA}+epsilon_{BB})$ and ${overline epsilon}_{AB} = 2epsilon_{AB}/(epsilon_{AA}+epsilon_{BB})$, where $epsilon_{AA}$ and $epsilon_{BB}$ are the cohesive energies of atoms $A$ and $B$ and $epsilon_{AB}$ is the pair interaction between $A$ and $B$ atoms. We identify a particular $f_B$-dependent combination of $epsilon_-$ and ${overline epsilon}_{AB}$ that collapses the data for $R_c$ over nearly $4$ orders of magnitude in cooling rate.
The effect of dopants on the metallic glass forming ability is usually considered based on analysis of changes in the liquid structure or thermodynamics. What is missing in such considerations is an analysis of how a dopant changes the properties of the crystal phases which can form instead of the glass. In order to illuminate this aspect we performed molecular dynamics simulations to study the effects of Mg and Sm dopants on the crystal nucleation in Al. The simulation data were found to be consistent with the experimental observations that addition of Mg to Al does not lead to vitrification but addition of only 8% Sm does. The significant effect of Sm doping was related to the intolerance of Al to this dopant. This leads to increase in the solid-liquid interfacial free energy, and therefore, to increase in the nucleation barrier and to dramatic decrease in the nucleation rate. The intolerance mechanism also significantly affects the growth kinetics.
We perform molecular dynamics simulations to compress binary hard spheres into jammed packings as a function of the compression rate $R$, size ratio $alpha$, and number fraction $x_S$ of small particles to determine the connection between the glass-forming ability (GFA) and packing efficiency in bulk metallic glasses (BMGs). We define the GFA by measuring the critical compression rate $R_c$, below which jammed hard-sphere packings begin to form random crystal structures with defects. We find that for systems with $alpha gtrsim 0.8$ that do not de-mix, $R_c$ decreases strongly with $Delta phi_J$, as $R_c sim exp(-1/Delta phi_J^2)$, where $Delta phi_J$ is the difference between the average packing fraction of the amorphous packings and random crystal structures at $R_c$. Systems with $alpha lesssim 0.8$ partially de-mix, which promotes crystallization, but we still find a strong correlation between $R_c$ and $Delta phi_J$. We show that known metal-metal BMGs occur in the regions of the $alpha$ and $x_S$ parameter space with the lowest values of $R_c$ for binary hard spheres. Our results emphasize that maximizing GFA in binary systems involves two competing effects: minimizing $alpha$ to increase packing efficiency, while maximizing $alpha$ to prevent de-mixing.
Machine learning approaches, enabled by the emergence of comprehensive databases of materials properties, are becoming a fruitful direction for materials analysis. As a result, a plethora of models have been constructed and trained on existing data to predict properties of new systems. These powerful methods allow researchers to target studies only at interesting materials $unicode{x2014}$ neglecting the non-synthesizable systems and those without the desired properties $unicode{x2014}$ thus reducing the amount of resources spent on expensive computations and/or time-consuming experimental synthesis. However, using these predictive models is not always straightforward. Often, they require a panoply of technical expertise, creating barriers for general users. AFLOW-ML (AFLOW $underline{mathrm{M}}$achine $underline{mathrm{L}}$earning) overcomes the problem by streamlining the use of the machine learning methods developed within the AFLOW consortium. The framework provides an open RESTful API to directly access the continuously updated algorithms, which can be transparently integrated into any workflow to retrieve predictions of electronic, thermal and mechanical properties. These types of interconnected cloud-based applications are envisioned to be capable of further accelerating the adoption of machine learning methods into materials development.
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
