An official website of the United States government
We search for new superhard B-N-O compounds with an iterative machine learning (ML) procedure, where ML models are trained using sample crystal structures from evolutionary algorithm. We first use cohesive energy to evaluate the thermodynamic stability of varying BxNyOz compositions, and then gradually focus on compositional regions with high cohesive energy and high hardness. The results converge quickly after a few iterations. Our resulting ML models show that Bx+2NxO3 compounds with x≥3 (like B5N3O3, B6N4O3, etc.) are potentially superhard and thermodynamically favorable. Our meta-GGA density functional theory calculations indicate that these materials are also wide bandgap (≥4.4 eV) insulators, with the valence band maximum related to the p-orbitals of nitrogen atoms near vacant sites. This study demonstrates that an iterative method combining ML and ab initio simulations provides a powerful tool for discovering novel materials.
more »
« less
Machine learning and evolutionary prediction of superhard B-C-N compounds
Abstract We build random forests models to predict elastic properties and mechanical hardness of a compound, using only its chemical formula as input. The model training uses over 10,000 target compounds and 60 features based on stoichiometric attributes, elemental properties, orbital occupations, and ionic bonding levels. Using the models, we construct triangular graphs for B-C-N compounds to map out their bulk and shear moduli, as well as hardness values. The graphs indicate that a 1:1 B-N ratio can lead to various superhard compositions. We also validate the machine learning results by evolutionary structure prediction and density functional theory. Our study shows that BC10N, B4C5N3, and B2C3N exhibit dynamically stable phases with hardness values >40 GPa, which are superhard materials that potentially could be synthesized by low-temperature plasma methods.
more »
« less
- Award ID(s):
- 1655280
- PAR ID:
- 10277973
- Publisher / Repository:
- Nature Publishing Group
- Date Published:
- Journal Name:
- npj Computational Materials
- Volume:
- 7
- Issue:
- 1
- ISSN:
- 2057-3960
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Discovering new materials with desired properties has been a dominant and crucial topic of interest in the field of materials science in the past few decades. In this work, novel carbon allotropes and ternary B–C–N structures were generated using the state-of-the-art RG 2 code. All structures were fully optimized using density functional theory with first-principles calculations. Several hundred carbon allotropes and ternary B–C–N structures were identified to be superhard materials. The thermodynamic stability of some randomly selected superhard materials was confirmed by evaluating the full phonon dispersions in the Brillouin zone. The new carbon allotropes and ternary B–C–N structures possess a wide range of mechanical properties generally and Vickers hardness specifically. Through 2D Pearson's correlation map, we first reproduced the well-accepted explanation and relationship of the Vickers hardness of the generated structures with other mechanical properties such as shear modulus, bulk modulus, Pugh's ratio, universal anisotropy, and Poisson's ratio. We then propose two fundamentally new descriptors from the electronic level, namely local potential and electron localization function averaged over a unit cell, both of which exhibit a strong correlation with Vickers hardness. More importantly, these descriptors are easy to access from first-principles calculations (at least two orders of magnitude faster than the traditional calculation of elastic constants), and thus can serve as a fast and accurate approach for screening superhard materials. We also combined these new descriptors with known composition and structural descriptors in the machine learning training process. The new descriptors significantly enhance the performance of the trained machine learning model in predicting the Vickers hardness of unknown materials, which provides strong evidence for local potential and electron localization function to be considered in future high-throughput computation. This work unravels more fundamental but previously unexplored knowledge about superhard materials and the newly proposed electronic level descriptors are expected to accelerate the discovery of new superhard materials.more » « less
-
We explored the B–C–O system at pressures in the range 0–50 GPa by ab initio variable-composition evolutionary simulations in the hope of discovering new stable superhard materials. A new tetragonal thermodynamically stable phase B 4 CO 4 , space group I 4̄, and two low-enthalpy metastable compounds (B 6 C 2 O 5 , B 2 CO 2 ) have been discovered. Computed phonons and elastic constants show that these structures are dynamically and mechanically stable both at high pressure and zero pressure. B 4 CO 4 is thermodynamically stable at pressures above 23 GPa, but should remain metastable under ambient conditions. Its computed hardness is about 38–41 GPa, which suggests that B 4 CO 4 is potentially superhard.more » « less
-
Abstract The low fracture toughness of strong covalent solids prevents them from wide engineering applications. Microalloying metal elements into covalent solids may lead to a significant improvement on mechanical properties and drastical changes on the chemical bonding. To illustrate these effects we employed density functional theory (DFT) to examine the bonding characteristic and mechanical failure of recently synthesized magnesium boride carbide (Mg3B50C8) that is formed by adding Mg into boron carbide (B4C). We found that Mg3B50C8has more metallic bonding charterer than B4C, but the atomic structure still satisfies Wade's rules. The metallic bonding significantly affects the failure mechanisms of Mg3B50C8compared with B4C. In Mg3B50C8, the B12icosahedral clusters are rotated in order to accommodate to the extensive shear strain without deconstruction. In addition, the critical failure strength of Mg3B50C8is slightly higher than that of B4C under indentation stress conditions. Our results suggested that the ductility of Mg3B50C8is drastically enhanced compared with B4C while the hardness is slightly higher than B4C.more » « less
-
Superhard boron-carbon materials are of prime interest due to their non-oxidizing properties at high temperatures compared to diamond-based materials and their non-reactivity with ferrous metals under extreme conditions. In this work, evolutionary algorithms combined with density functional theory have been utilized to predict stable structures and properties for the boron-carbon system, including the elusive superhard BC5 compound. We report on the microwave plasma chemical vapor deposition on a silicon substrate of a series of composite materials containing amorphous boron-doped graphitic carbon, boron-doped diamond, and a cubic hard-phase with a boron-content as high as 7.7 at%. The nanoindentation hardness of these composite materials can be tailored from 8 GPa to as high as 62 GPa depending on the growth conditions. These materials have been characterized by electron microscopy, X-ray photoelectron spectroscopy, Raman spectroscopy, X-ray diffraction, and nanoindentation hardness, and the experimental results are compared with theoretical predictions. Our studies show that a significant amount of boron up to 7.7 at% can be accommodated in the cubic phase of diamond and its phonon modes and mechanical properties can be accurately modeled by theory. This cubic hard-phase can be incorporated into amorphous boron-carbon matrices to yield superhard materials with tunable hardness values.more » « less
