Modelling and prediction of hardness in multi-component alloys: A combined machine learning, first principles and experimental study

Abstract In present study, the relations between hardness and elemental descriptors in the multi-component alloys (MACs) are particularly uncovered via machine learning (ML) and first-principles calculations. The RBF neural network is utilized to efficiently train a large database which allows an acceptable accuracy for identifying the overall role of elemental features for target properties. Detailed information from ML predictions indicates the critical element of Al and its significant advantages for the hardness in a model Al–Cr–Fe–Ni system. Investigations on elastic properties using first-principles calculations provide relations between physical quantities and match well with ML model. Furthermore, the Al 1.2 CrFeNi alloy was selected as an example, experimentally synthesized and properties-identified, to provide a strong validation in this case. Combined with some other reported alloys in this system, the prediction of the developed model can achieve above 90%. Further experimental analysis found that a dual phase microstructure presents in the Al 1.2 CrFeNi alloy, leading to a superior work hardening ability compared with the reported high performance alloys. This study offers reliable composition-properties features and encourages more researches using this integrated approach to guide for tuning novel MACs.

[1]  Yong Deng,et al.  A Comparative Study on Arrhenius Equations and BP Neural Network Models to Predict Hot Deformation Behaviors of a Hypereutectoid Steel , 2020, IEEE Access.

[2]  B. S. Murty,et al.  Decomposition in multi-component AlCoCrCuFeNi high-entropy alloy , 2011 .

[3]  J. Pi,et al.  Microstructure and wear behavior of the AlCrFeCoNi high-entropy alloy fabricated by additive manufacturing , 2020 .

[4]  Y. Liu,et al.  Alloying effect on phase stability, elastic and thermodynamic properties of Nb-Ti-V-Zr high entropy alloy , 2018, Intermetallics.

[5]  Dianzhong Li,et al.  Modeling hardness of polycrystalline materials and bulk metallic glasses , 2011 .

[6]  B. Han,et al.  Investigation on microstructure and properties of AlxCoCrFeMnNi high entropy alloys by ultrasonic impact treatment , 2020 .

[7]  Z. Jiao,et al.  Superior high-temperature properties and deformation-induced planar faults in a novel L12-strengthened high-entropy alloy , 2020 .

[8]  Yuan Wang,et al.  Model free adaptive fault-tolerant tracking control for a class of discrete-time systems , 2020, Neurocomputing.

[9]  Jonghyun Kim,et al.  Effects of Mn addition on the microstructures, mechanical properties and work-hardening of Mg-1Sn alloy , 2019, Materials Science and Engineering: A.

[10]  Ling Qiao,et al.  Modelling and prediction of thermal deformation behaviors in a pearlitic steel , 2020 .

[11]  W. Gan,et al.  Work hardening and softening behavior of pure Mg influenced by Zn addition investigated via in-situ neutron diffraction , 2020 .

[12]  W. Kohn,et al.  Self-Consistent Equations Including Exchange and Correlation Effects , 1965 .

[13]  G. Kresse,et al.  From ultrasoft pseudopotentials to the projector augmented-wave method , 1999 .

[14]  P. Liaw,et al.  Deviation from high-entropy configurations in the atomic distributions of a multi-principal-element alloy , 2015, Nature Communications.

[15]  L. Vitos,et al.  Empirical design of single phase high-entropy alloys with high hardness , 2015 .

[16]  Jorge O. Sofo,et al.  First-principles study of binary bcc alloys using special quasirandom structures , 2004 .

[17]  M. Peng,et al.  The interstitial diffusion behaviors and mechanisms of boron in α-Ti and β-Ti: A first-principles calculation , 2020 .

[18]  Yufeng Zheng,et al.  Phase inversion in a two-phase, BCC+B2, refractory high entropy alloy , 2020 .

[19]  Matt Probert,et al.  First-principles simulation: ideas, illustrations and the CASTEP code , 2002 .

[20]  Longke Bao,et al.  The mechanical and thermodynamic properties of ZrTM (TM=Fe, Ru and Os) intermetallics under pressure and temperature: A first-principles predictions , 2020 .

[21]  Ferreira,et al.  Special quasirandom structures. , 1990, Physical review letters.

[22]  Zhou-hua Jiang,et al.  Enhancing the strength and ductility of CoCrFeMnNi high-entropy alloy by nitrogen addition , 2020 .

[23]  Bo Xu,et al.  Microscopic theory of hardness and design of novel superhard crystals , 2012 .

[24]  M. Ren,et al.  Microstructure and properties of AlCrFeNi intermetallic for electronic packaging shell , 2017, 2017 18th International Conference on Electronic Packaging Technology (ICEPT).

[25]  M. Born,et al.  Dynamical Theory of Crystal Lattices , 1954 .

[26]  D. Vojtěch,et al.  High-strength ultrafine-grained CoCrFeNiNb high-entropy alloy prepared by mechanical alloying: Properties and strengthening mechanism , 2020 .

[27]  Turab Lookman,et al.  Machine learning assisted design of high entropy alloys with desired property , 2019, Acta Materialia.

[28]  T. Shun,et al.  Nanostructured High‐Entropy Alloys with Multiple Principal Elements: Novel Alloy Design Concepts and Outcomes , 2004 .

[29]  E. George,et al.  Reasons for the superior mechanical properties of medium-entropy CrCoNi compared to high-entropy CrMnFeCoNi , 2017 .

[30]  K. Dahmen,et al.  Microstructures and properties of high-entropy alloys , 2014 .

[31]  Ya Liu,et al.  Microstructure and microhardness of as-cast and 800 °C annealed Al x Cr 0.2 Fe 0.2 Ni 0.6-x and Al 0.2 Cr 0.2 Fe y Ni 0.6-y alloys , 2018, Vacuum.

[32]  Longke Bao,et al.  Revealing the elastic properties and anisotropies of Mg2X(X = Si, Ge and Sn) with different structures from a first-principles calculation , 2020 .

[33]  Tongmin Wang,et al.  Effect of aluminium content of AlxCrFe1·5Ni0·5 multiprincipal alloys on microstructure and alloy hardness , 2011 .

[34]  Jiqiu Qi,et al.  Effects of aluminum on microstructure and compressive properties of Al-Cr-Fe-Ni eutectic multi-component alloys , 2017 .

[35]  D. Broomhead,et al.  Radial Basis Functions, Multi-Variable Functional Interpolation and Adaptive Networks , 1988 .

[36]  F. Pan,et al.  Effect of Sn content on strain hardening behavior of as-extruded Mg-Sn alloys , 2018 .

[37]  David S. Broomhead,et al.  Multivariable Functional Interpolation and Adaptive Networks , 1988, Complex Syst..

[38]  S. Seils,et al.  Origins of strength and plasticity in the precious metal based high-entropy alloy AuCuNiPdPt , 2020 .

[39]  M. Gao,et al.  High-Entropy Alloys: Fundamentals and Applications , 2016 .

[40]  Junqi Yin,et al.  Robust data-driven approach for predicting the configurational energy of high entropy alloys , 2019, Materials & Design.

[41]  X. Yang,et al.  Alloy Design and Properties Optimization of High-Entropy Alloys , 2012 .

[42]  K. An,et al.  First-principles and machine learning predictions of elasticity in severely lattice-distorted high-entropy alloys with experimental validation , 2019, Acta Materialia.

[43]  Wang,et al.  Generalized gradient approximation for the exchange-correlation hole of a many-electron system. , 1996, Physical review. B, Condensed matter.

[44]  Yong Liu,et al.  Application of generalized regression neural network optimized by fruit fly optimization algorithm for fracture toughness in a pearlitic steel , 2020 .

[45]  Peter K. Liaw,et al.  Science and technology in high-entropy alloys , 2018, Science China Materials.

[46]  O. Nikan,et al.  Modeling high temperature deformation characteristics of AA7020 aluminum alloy using substructure-based constitutive equations and mesh-free approximation method , 2019, Mechanics of Materials.

[47]  Yan-qing Yang,et al.  Co-free non-equilibrium medium-entropy alloy with outstanding tensile properties , 2020 .