Papers
Topics
Authors
Recent
Search
2000 character limit reached

Machine learning accelerated discovery of corrosion-resistant high-entropy alloys

Published 12 Jul 2023 in cond-mat.mtrl-sci | (2307.06384v3)

Abstract: Corrosion has a wide impact on society, causing catastrophic damage to structurally engineered components. An emerging class of corrosion-resistant materials are high-entropy alloys. However, high-entropy alloys live in high-dimensional composition and configuration space, making materials designs via experimental trial-and-error or brute-force ab initio calculations almost impossible. Here we develop a physics-informed machine-learning framework to identify corrosion-resistant high-entropy alloys. Three metrics are used to evaluate the corrosion resistance, including single-phase formability, surface energy and Pilling-Bedworth ratios. We used random forest models to predict the single-phase formability, trained on an experimental dataset. Machine learning inter-atomic potentials were employed to calculate surface energies and Pilling-Bedworth ratios, which are trained on first-principles data fast sampled using embedded atom models. A combination of random forest models and high-fidelity machine learning potentials represents the first of its kind to relate chemical compositions to corrosion resistance of high-entropy alloys, paving the way for automatic design of materials with superior corrosion protection. This framework was demonstrated on AlCrFeCoNi high-entropy alloys and we identified composition regions with high corrosion resistance. Machine learning predicted lattice constants and surface energies are consistent with values by first-principles calculations. The predicted single-phase formability and corrosion-resistant compositions of AlCrFeCoNi agree well with experiments. This framework is general in its application and applicable to other materials, enabling high-throughput screening of material candidates and potentially reducing the turnaround time for integrated computational materials engineering.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (71)
  1. Microstructural development in equiatomic multicomponent alloys. Materials Science and Engineering: A 2004; 375-377, 213–218.
  2. Nanostructured High-Entropy Alloys with Multiple Principal Elements: Novel Alloy Design Concepts and Outcomes. Advanced Engineering Materials 2004; 6, 299–303.
  3. A fracture-resistant high-entropy alloy for cryogenic applications. Science 2014; 345, 1153–1158.
  4. Multicomponent intermetallic nanoparticles and superb mechanical behaviors of complex alloys. Science 2018; 362, 933–937.
  5. Metastable high-entropy dual-phase alloys overcome the strength–ductility trade-off. Nature 2016; 534, 227–230.
  6. Synergistic effects of Al and Ti on the oxidation behaviour and mechanical properties of L12-strengthened FeCoCrNi high-entropy alloys. Corrosion Science 2021; 184, 109365.
  7. Effects of Al addition on the microstructure and mechanical property of AlxCoCrFeNi high-entropy alloys. Intermetallics 2012; 26, 44–51.
  8. Microstructural stability and mechanical behavior of FeNiMnCr high entropy alloy under ion irradiation. Acta Materialia 2016; 113, 230–244.
  9. A promising new class of irradiation tolerant materials: Ti2ZrHfV0.5Mo0.2 high-entropy alloy. Journal of Materials Science & Technology 2019; 35, 369–373.
  10. Homogenization of AlxCoCrFeNi high-entropy alloys with improved corrosion resistance. Corrosion Science 2018; 133, 120–131.
  11. Corrosion characteristics of high entropy alloys. Materials Science and Technology 2015; 31, 1235–1243.
  12. Recent advances on environmental corrosion behavior and mechanism of high-entropy alloys. Journal of Materials Science & Technology 2021; 80, 217–233.
  13. Steurer, W. Single-phase high-entropy alloys – A critical update. Materials Characterization 2020; 162, 110179.
  14. A hexagonal close-packed high-entropy alloy: The effect of entropy. Materials & Design 2016; 96, 10–15.
  15. Integrated computational materials engineering of corrosion resistant alloys. npj Mater Degrad 2018; 2, 1–10.
  16. Electrochemical metrics for corrosion resistant alloys. Sci Data 2021; 8, 58.
  17. Phase field modeling for the morphological and microstructural evolution of metallic materials under environmental attack. npj Comput Mater 2021; 7, 1–21.
  18. Improvement of the machine learning-based corrosion rate prediction model through the optimization of input features. Materials & Design 2021; 198, 109326.
  19. Machine-learning-guided descriptor selection for predicting corrosion resistance in multi-principal element alloys. npj Mater Degrad 2022; 6, 1–10.
  20. Density Functional Theory: An Essential Partner in the Integrated Computational Materials Engineering Approach to Corrosion. Corrosion 2019; 75, 708–726.
  21. A coupled mechano-chemical peridynamic model for pit-to-crack transition in stress-corrosion cracking. Journal of the Mechanics and Physics of Solids 2021; 146, 104203.
  22. Probing the randomness of the local current distributions of 316 L stainless steel corrosion in NaCl solution. Corrosion Science 2023; 217, 111104.
  23. Cooperative Stochastic Behavior in Localized Corrosion: I. Model. J. Electrochem. Soc. 1997; 144, 1614. Publisher: IOP Publishing.
  24. Localized corrosion: Passive film breakdown vs. Pit growth stability, Part VI: Pit dissolution kinetics of different alloys and a model for pitting and repassivation potentials. Corrosion Science 2021; 182, 109277.
  25. Pilling-Bedworth ratio for oxidation of alloys. Materials Research Innovations 2000; 3, 231–235.
  26. Oxidation of magnesium alloys at elevated temperatures in air: A review. Corrosion Science 2016; 112, 734–759.
  27. Crystallographic orientation and electrochemical activity of AZ31 Mg alloy. Electrochemistry Communications 2010; 12, 1009–1012.
  28. Ab initio modelling of localized corrosion: Study of the role of surface steps in the interaction of chlorides with passivated nickel surfaces. Corrosion Science 2009; 51, 2174–2182.
  29. A Point Defect Model for Anodic Passive Films: II . Chemical Breakdown and Pit Initiation. J. Electrochem. Soc. 1981; 128, 1194. Publisher: IOP Publishing.
  30. Unmasking chloride attack on the passive film of metals. Nat Commun 2018; 9, 2559.
  31. Strong yet ductile nanolamellar high-entropy alloys by additive manufacturing. Nature 2022; 608, 62–68.
  32. 𝒪𝒪\mathcal{O}caligraphic_O(N𝑁{N}italic_N) methods in electronic structure calculations. Reports on Progress in Physics 2012; 75, 036503.
  33. Kohn, W. Density Functional and Density Matrix Method Scaling Linearly with the Number of Atoms. Physical Review Letters 1996; 76, 3168–3171.
  34. Generalized Neural-Network Representation of High-Dimensional Potential-Energy Surfaces. Physical Review Letters 2007; 98, 146401.
  35. A nearsighted force-training approach to systematically generate training data for the machine learning of large atomic structures. The Journal of Chemical Physics 2022; 156, 064104.
  36. Crystal Graph Convolutional Neural Networks for an Accurate and Interpretable Prediction of Material Properties. Physical Review Letters 2018; 120, 145301. Publisher: American Physical Society.
  37. Gaussian Approximation Potentials: the accuracy of quantum mechanics, without the electrons. Physical Review Letters 2010; 104, 136403.
  38. Fast and Accurate Modeling of Molecular Atomization Energies with Machine Learning. Physical Review Letters 2012; 108, 058301.
  39. E(3)-equivariant graph neural networks for data-efficient and accurate interatomic potentials. Nat Commun 2022; 13, 2453.
  40. The phase stability of large-size nanoparticle alloy catalysts at ab initio quality using a nearsighted force-training approach 2023.
  41. Machine learning potentials for extended systems: a perspective. Eur. Phys. J. B 2021; 94, 142.
  42. Performance and Cost Assessment of Machine Learning Interatomic Potentials. J. Phys. Chem. A 2020; 124, 731–745.
  43. Shapeev, A.V. Moment Tensor Potentials: A Class of Systematically Improvable Interatomic Potentials. Multiscale Model. Simul. 2016; 14, 1153–1173.
  44. The MLIP package: moment tensor potentials with MPI and active learning. Mach. Learn.: Sci. Technol. 2020; 2, 025002. Publisher: IOP Publishing.
  45. Model interatomic potentials for Fe–Ni–Cr–Co–Al high-entropy alloys. Journal of Materials Research 2020; 35, 3031–3040.
  46. Grid-Based Projector Augmented Wave (GPAW) Implementation of Quantum Mechanics/Molecular Mechanics (QM/MM) Electrostatic Embedding and Application to a Solvated Diplatinum Complex. Journal of Chemical Theory and Computation 2017; 13, 6010–6022.
  47. Special quasirandom structures. Phys. Rev. Lett. 1990; 65, 353–356.
  48. Efficient stochastic generation of special quasirandom structures. Calphad 2013; 42, 13–18.
  49. The atomic simulation environment—a Python library for working with atoms. Journal of Physics: Condensed Matter 2017; 29, 273002.
  50. LAMMPS - a flexible simulation tool for particle-based materials modeling at the atomic, meso, and continuum scales. Computer Physics Communications 2022; 271, 108171.
  51. TCHEA1: A Thermodynamic Database Not Limited for “High Entropy” Alloys. J. Phase Equilib. Diffus. 2017; 38, 353–368.
  52. Accelerated discovery of single-phase refractory high entropy alloys assisted by machine learning. Computational Materials Science 2021; 199, 110723.
  53. Hydrogen permeation characteristic of nanoscale passive films formed on different zirconium alloys. International Journal of Hydrogen Energy 2016; 41, 7676–7690.
  54. Hydrogen interaction characteristic of nanoscale oxide films grown on iron–nickel based stainless steel by selective thermal oxidation. International Journal of Hydrogen Energy 2017; 42, 20910–20921.
  55. Diffusion of iron in Cr2O3: polycrystals and thin films. Materials Science and Engineering: A 2005; 392, 254–261.
  56. Sluggish diffusion in Co–Cr–Fe–Mn–Ni high-entropy alloys. Acta Materialia 2013; 61, 4887–4897.
  57. High-throughput synthesis and corrosion behavior of sputter-deposited nanocrystalline Alx(CoCrFeNi)100-x combinatorial high-entropy alloys. Materials & Design 2020; 195, 109018.
  58. Coupling of surface energy with electric potential makes superhydrophobic surfaces corrosion-resistant. Phys. Chem. Chem. Phys. 2015; 17, 24988–24997.
  59. A Percolation Model for Passivation in Stainless Steels. J. Electrochem. Soc. 1986; 133, 1979.
  60. Exploring the potential of transfer learning in extrapolating accelerated corrosion test data for long-term atmospheric corrosion forecasting. Corrosion Science 2023; 225, 111619.
  61. The Explanation Game: Explaining Machine Learning Models Using Shapley Values. In A. Holzinger; P. Kieseberg; A.M. Tjoa; E. Weippl, eds., Machine Learning and Knowledge Extraction, Lecture Notes in Computer Science. Springer International Publishing, Cham. ISBN 978-3-030-57321-8, pp. 17–38.
  62. Compatibility and microstructure evolution of Al-Cr-Fe-Ni high entropy model alloys exposed to oxygen-containing molten lead. Corrosion Science 2021; 189, 109593.
  63. Effect of thermally induced B2 phase on the corrosion behavior of an Al0.3CoCrFeNi high entropy alloy. Journal of Alloys and Compounds 2022; 903, 163886.
  64. Uncovering the eutectics design by machine learning in the Al–Co–Cr–Fe–Ni high entropy system. Acta Materialia 2020; 182, 278–286.
  65. Bernstein, H.L. A model for the oxide growth stress and its effect on the creep of metals. Metall Trans A 1987; 18, 975–986.
  66. Huntz, A.M. Stresses in NiO, Cr2O3 and Al2O3 oxide scales. Materials Science and Engineering: A 1995; 201, 211–228.
  67. Screening of generalized stacking fault energies, surface energies and intrinsic ductile potency of refractory multicomponent alloys. Acta Materialia 2021; 210, 116800.
  68. A machine learning-based alloy design system to facilitate the rational design of high entropy alloys with enhanced hardness. Acta Materialia 2022; 222, 117431.
  69. A Universal Framework for Featurization of Atomistic Systems. J. Phys. Chem. Lett. 2022; 13, 7911–7919.
  70. A universal graph deep learning interatomic potential for the periodic table. Nat Comput Sci 2022; 2, 718–728.
  71. Automatic selection of atomic fingerprints and reference configurations for machine-learning potentials. The Journal of Chemical Physics 2018; 148, 241730.
Citations (14)
View on Semantic Scholar

Summary

No one has generated a summary of this paper yet.

Sign Up to Summarize

Paper to Video (Beta)

No one has generated a video about this paper yet.

Sign Up to Generate All Videos Subscribe on YouTube

Whiteboard

No one has generated a whiteboard explanation for this paper yet.

Sign Up to Generate

Open Problems

We haven't generated a list of open problems mentioned in this paper yet.

Generate Now

Continue Learning

We haven't generated follow-up questions for this paper yet.

Generate Now

Collections

Sign up for free to add this paper to one or more collections.

Sign Up

Tweets

Sign up for free to view the 1 tweet with 4 likes about this paper.

Sign Up for Free