A machine learning approach for engineering bulk metallic glass alloys

Ward, Logan; O'Keeffe, Stephanie C.; Stevick, Joseph; Jelbert, G.; Aykol, Muratahan; Wolverton, Chris

doi:10.1016/j.actamat.2018.08.002

Cited by 191 publications

(128 citation statements)

References 95 publications

Supporting

Mentioning

119

Contrasting

Unclassified

Order By: Relevance

“…An atomic-position independent descriptor was able to reach a MAE of 70 meV/atom for formation energy predictions of a diverse dataset of more than 85 000 materials [415]. Recently, the synergistic combination of ML techniques and HT experiments resulted in the accelerated discovery of novel bulk metallic glasses [416,417].…”

Section: Discovery Energies and Stabilitymentioning

confidence: 99%

From DFT to machine learning: recent approaches to materials science–a review

et al. 2019

View full text Add to dashboard Cite

Recent advances in experimental and computational methods are increasing the quantity and complexity of generated data. This massive amount of raw data needs to be stored and interpreted in order to advance the materials science field. Identifying correlations and patterns from large amounts of complex data is being performed by machine learning algorithms for decades. Recently, the materials science community started to invest in these methodologies to extract knowledge and insights from the accumulated data. This review follows a logical sequence starting from density functional theory as the representative instance of electronic structure methods, to the subsequent high-throughput approach, used to generate large amounts of data. Ultimately, data-driven strategies which include data mining, screening, and machine learning techniques, employ the data generated. We show how these approaches to modern computational materials science are being used to uncover complexities and design novel materials with enhanced properties. Finally, we point to the present research problems, challenges, and potential future perspectives of this new exciting field. characterized by its diverse and huge volume, usually ranging from terabytes to petabytes of data, being created in or near real-time. Such data is found either structured and unstructured in nature, and is exhaustive, usually aiming to capture entire populations in a scalable manner [7]. Simple tasks represent challenges in this scale: capture, curation, storage, search, sharing, analysis, and visualization of the data cannot be accomplished without the proper tools. Thus, it can be effectively summarized by the popular 'five V's': volume, velocity, variety, veracity, and value, shown in figure 3(right). A related sixth V is visualization, although not exclusive to Big Data, which requires different techniques to handle data with various characteristics.Striving to tackle the challenges imposed by Big Data, the field of Data Science has arisen. It is largely interdisciplinary being a combination of mathematics and statistics, computer science and programming, and domain knowledge for problem definition and solving, as shown in figure 3(left). Its objective is, roughly speaking, to deal with the whole process of data production, cleaning, preparation, and finally, analysis. Data science encompasses areas such as Big Data, which deals with large volumes of data, and data mining, which relates to analysis processes to discover patterns and extract knowledge from data, part of the so-called Knowledge Discovery in Databases (KDD).The analysis process within Data Science is challenging, as the techniques are very different from traditional static and rigid datasets, generated and analyzed under a predetermined hypothesis. The distinction from traditional data is based on the larger abundance, exhaustivity, and variety of Big Data. It is also much more dynamic, messy and uncertain, being highly relational [7]. Recently, the possibility of overcoming such a challenge slowly sta...

show abstract

Section: Discovery Energies and Stabilitymentioning

confidence: 99%

From DFT to machine learning: recent approaches to materials science–a review

et al. 2019

View full text Add to dashboard Cite

show abstract

“…Trained on available materials data either from experimental observations or DFT datasets (like the OQMD (1, 2), Materials Project (3), and AFLOWlib (4)), most of these ML models aim at predicting promising chemical subspaces for materials with favorable properties (8). Examples include models for melting temperatures (9), materials thermodynamics (10)(11)(12)(13)(14)(15)(16)(17), mechanical properties of alloy systems (18)(19)(20), superconductivity (21), formation of metallic glasses (22), and electronic properties of semiconductors and insulating materials (23)(24)(25)(26)(27).…”

Section: Introductionmentioning

confidence: 99%

Ternary mixed-anion semiconductors with tunable band gaps from machine-learning and crystal structure prediction

Amsler

Ward

Hegde

et al. 2019

Phys. Rev. Materials

Self Cite

View full text Add to dashboard Cite

We report the computational investigation of a series of ternary X4Y2Z and X5Y2Z2 compounds with X={Mg, Ca, Sr, Ba}, Y={P, As, Sb, Bi}, and Z={S, Se, Te}. The compositions for these materials were predicted through a search guided by machine learning, while the structures were resolved using the minima hopping crystal structure prediction method. Based on ab initio calculations, we predict that many of these compounds are thermodynamically stable. In particular, 21 of the X4Y2Z compounds crystallize in a tetragonal structure with I-42d symmetry, and exhibit band gaps in the range of 0.3 and 1.8 eV, well suited for various energy applications. We show that several candidate compounds (in particular X4Y2Te and X4Sb2Se) exhibit good photo absorption in the visible range, while others (e.g., Ba4Sb2Se) show excellent thermoelectric performance due to a high power factor and extremely low lattice thermal conductivities.

show abstract

“…AFA alloys have been designed to use MC, M23C6, Laves and/or L12 strengthening precipitates in an austenite single-phase matrix. Over the past decade more than 100 lab-scale arc-cast (0.1 to 0.5 kg) and pilot scale industrial vacuum cast (15 kg, with several compositions at 200 kg and 4000 kg) AFA alloys were manufactured and evaluated for creep (and oxidation) resistance, with nominal composition range of Fe-(12-32)Ni- (12)(13)(14)(15)(16)(17)(18)(19)(20) [14][15][16][17][18][19][20].…”

Section: Experimental Alloy Datamentioning

confidence: 99%

“…Fe (Bal. ), Ni , Cr (12)(13)(14)(15)(16)(17)(18)(19)(20), (12) 31 T2_FCC_CX_B 13 92 T2_NbC_CX_AL 13 14 T2_NbC_CX_AL 14 13 T2_SIGMA_X_CR (14) 115 T2_NbC_X_NI 15 30 T2_M2B_CB_X_MO (15) 35 T2_NbC_CX_B 16 120 T2_NbC_X_MO 16 50 T2_NbC_X_B 17 128 T2_M2B_CB_X_FE (17) 33 T2_NIAL_ACR_B2_FE 18 47 T2_NbC_CX_MO 18 39 T2_NIAL_B2_X_CR 19 358 T2_M3B...…”

Section: Elementsmentioning

confidence: 99%

“…On the other hand, analytical surrogate models are better suited for alloy design as they can better handle multi-component systems with much less computing power [2][3][4][5][6]. There are a number of legacy (mainly based on neural networks) [7][8][9] and recent efforts (based on machine learning) [10][11][12][13] to apply data analytics approaches for developing predictive capabilities toward multi-component/multi-phase alloy design. These approaches usually require a large volume of experimental data to ensure the fidelity of trained models.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Modern data analytics approach to predict creep of high-temperature alloys

et al. 2019

View full text Add to dashboard Cite

A breakthrough in alloy design often requires comprehensive understanding in complex multicomponent/multi-phase systems to generate novel material hypotheses. We introduce a modern data analytics workflow that leverages high-quality experimental data augmented with advanced features obtained from high-fidelity models. Herein, we use an example of a consistently-measured creep dataset of developmental high-temperature alloy combined with scientific alloy features populated from a high-throughput computational thermodynamic approach. Extensive correlation analyses provide ranking insights for most impactful alloy features for creep resistance, evaluated from a large set of candidate features suggested by domain experts. We also show that we can accurately train machine learning models by integrating high-ranking features obtained from correlation analyses. The demonstrated approach can be extended beyond incorporating thermodynamic features, with input from domain experts used to compile lists of features from other alloy physics, such as diffusion kinetics and microstructure evolution.

show abstract

A machine learning approach for engineering bulk metallic glass alloys

Cited by 191 publications

References 95 publications

From DFT to machine learning: recent approaches to materials science–a review

From DFT to machine learning: recent approaches to materials science–a review

Ternary mixed-anion semiconductors with tunable band gaps from machine-learning and crystal structure prediction

Modern data analytics approach to predict creep of high-temperature alloys

Contact Info

Product

Resources

About