4.8 Article

A neural network model for high entropy alloy design

Related references

Note: Only part of the references are listed.
Article Materials Science, Multidisciplinary

A thermodynamic description for the Co-Cr-Fe-Mn-Ni system

Hyeon-Seok Do et al.

Summary: Research on representative Co-Cr-Fe-Mn-Ni high-entropy alloys has been conducted to develop new HEAs with improved strength, utilizing computational thermodynamic prediction to efficiently design the new HEAs. The phase equilibria in HEAs can be effectively predicted by CALPHAD type techniques, but challenges still exist due to incompleteness in thermodynamic descriptions for constituent ternary systems. Developing a self-consistent thermodynamic description for the quinary system involved completing descriptions for constituent ternary sub-systems and carrying out new assessments, with the reliability confirmed by comparing calculated vertical sections of the quinary phase diagram with experimental information.

JOURNAL OF MATERIALS SCIENCE (2022)

Article Chemistry, Physical

Molecular dynamics study on the strengthening mechanisms of Cr-Fe-Co-Ni high-entropy alloys based on the generalized stacking fault energy

Asker Jarlov et al.

Summary: The correlation between the generalized stacking fault energy and the strengthening mechanisms of Cr-Fe-Co-Ni high-entropy alloys during uniaxial tensile deformation is investigated. The results show that the increase in Cr and Fe content decreases the generalized stacking fault energy while the Co and Ni content has the opposite effect. A linear correlation is identified between the unstable stacking fault energy and the yield stress. The composition of the alloy plays a crucial role in enhancing the yield strength and the efficiency of strengthening mechanisms.

JOURNAL OF ALLOYS AND COMPOUNDS (2022)

Article Materials Science, Multidisciplinary

Quantitative analysis of mechanical properties associated with aging treatment and microstructure in Mg-Al-Zn alloys through machine learning

Joung Sik Suh et al.

Summary: The present study proposes a methodology to predict the mechanical properties of AZ61 and AZ91 alloys by considering microstructure, texture, and aging parameters. Machine learning techniques were used to analyze the correlations between microstructure, texture, and mechanical properties of aged rods. Artificial neural networks achieved high accuracy in predicting tensile and compressive yield strengths using 11 predictors, and decision tree learning assessed the importance of predictors in determining the mechanical properties of aged rods.

JOURNAL OF MATERIALS SCIENCE & TECHNOLOGY (2022)

Article Chemistry, Physical

Machine-learning-based intelligent framework for discovering refractory high-entropy alloys with improved high-temperature yield strength

Stephen A. Giles et al.

Summary: This study demonstrates a method of intelligently exploring the compositional space of refractory high-entropy alloys (RHEAs) through a machine learning framework and optimization methods, successfully discovering RHEA alloys with superior high-temperature yield strengths.

NPJ COMPUTATIONAL MATERIALS (2022)

Article Chemistry, Multidisciplinary

Performance-oriented multistage design for multi-principal element alloys with low cost yet high efficiency

Jia Li et al.

Summary: Multi-principal element alloys (MPEAs) have great potential as structural, functional, and smart materials with remarkable performances. However, designing MPEAs with efficient performance in a wide range of compositions and types is challenging. This study proposes a multistage-design approach that integrates machine learning, physical laws, and a mathematical model to develop desired-property MPEAs in a time-efficient way, achieving better efficiency and accuracy compared to existing methods.

MATERIALS HORIZONS (2022)

Article Materials Science, Multidisciplinary

Tailoring nanoprecipitates for ultra-strong high-entropy alloys via machine learning and prestrain aging

Tao Zheng et al.

Summary: The concept of multi-principal-component high-entropy alloys has led to the creation of numerous new alloys, including nanoscale precipitated HEAs with exceptional mechanical properties for structural applications. Finding the optimal alloy remains a challenge, with current approaches relying on trial-and-error methods and phase diagram calculations. This study proposes a novel method to accelerate the development of ultra-strong nanoprecipitated HEAs by utilizing machine learning and kinetic control for designing nanoscale precipitates.

JOURNAL OF MATERIALS SCIENCE & TECHNOLOGY (2021)

Article Materials Science, Multidisciplinary

Online prediction of mechanical properties of hot rolled steel plate using machine learning

Qian Xie et al.

Summary: In industrial steel plate production, a deep learning model was developed to predict mechanical properties based on process parameters and steel grade composition. Comparative analysis showed that the accuracy of the deep neural network model was higher than other classic machine learning algorithms. The tuned model was deployed in a real steel plant for online monitoring and control of steel mechanical properties.

MATERIALS & DESIGN (2021)

Article Materials Science, Multidisciplinary

Discovery of marageing steels: machine learning vs. physical metallurgical modelling

Chunguang Shen et al.

Summary: Physical metallurgical (PM) and data-driven approaches can be independently applied to alloy design. PM approaches provide a clearer picture of the overall composition-microstructure-properties relationship but are highly sensitive to the alloy system and lack exploration ability of new domains. On the other hand, machine learning (ML) offers stronger prediction accuracy but provides little explicit physical insight. Hybrid PM/ML approaches maximize accuracy while leading to a clearer physical picture and desired properties.

JOURNAL OF MATERIALS SCIENCE & TECHNOLOGY (2021)

Article Materials Science, Multidisciplinary

Second-nearest-neighbor modified embedded-atom method interatomic potential for V-M (M = Cu, Mo, Ti) binary systems

Jaemin Wang et al.

Summary: Interatomic potentials for V-M binary systems were developed using the 2NN MEAM formalism, reproducing a wide range of material properties in agreement with experimental data or first-principles calculations. This allows for studying hydrogen permeability in vanadium alloys and potential development of ternary system potentials containing vanadium.

COMPUTATIONAL MATERIALS SCIENCE (2021)

Article Chemistry, Physical

Machine Learning-Based Strength Prediction for Refractory High-Entropy Alloys of the Al-Cr-Nb-Ti-V-Zr System

Denis Klimenko et al.

Summary: This study successfully predicted new compositions of high-entropy alloys with desired phase composition and mechanical properties using a combination of machine learning, phenomenological rules, and CALPHAD modeling. Additionally, precise predictions of yield strength at different temperatures were made, with one alloy showing excellent ductility and yield strength at both 20 degrees C and 800 degrees C.

MATERIALS (2021)

Article Materials Science, Multidisciplinary

Construction of a machine-learning-based prediction model for mechanical properties of ultra-fine-grained Fe-C alloy

Jin Liang Du et al.

Summary: This study aimed to predict the mechanical properties of ultra-fine-grained Fe-C alloy by designing a machine-learning model, which achieved high accuracy using a BP neural network. The research lays a foundation for producing high-stability and high-performance steel products.

JOURNAL OF MATERIALS RESEARCH AND TECHNOLOGY-JMR&T (2021)

Article Nanoscience & Nanotechnology

Effects of Al alloying on microstructure and mechanical properties of VCoNi medium entropy alloy

J. Tian et al.

Summary: Alloying with aluminum and thermomechanical treatment resulted in the formation of a refined and heterogeneous microstructure with nanoscaled precipitates in equiatomic VCoNi medium entropy alloys. The composite alloy exhibited comprehensive mechanical properties with increased yield strength, ultimate tensile strength, and elongation, which can be attributed to the enhanced strengthening contributions from dislocation, solid solution, and precipitation. This study provides insights into developing high-performance medium entropy alloys through composition and treatment optimization.

MATERIALS SCIENCE AND ENGINEERING A-STRUCTURAL MATERIALS PROPERTIES MICROSTRUCTURE AND PROCESSING (2021)

Article Materials Science, Multidisciplinary

Machine learning assisted composition effective design for precipitation strengthened copper alloys

Hongtao Zhang et al.

Summary: A machine learning strategy was proposed to design alloys with remarkable properties by screening key alloy factors and utilizing Bayesian optimization, successfully designing new copper alloys with improved hardness and electrical conductivity, achieving simultaneous improvement of conflicting properties.

ACTA MATERIALIA (2021)

Article Materials Science, Multidisciplinary

Modeling solid solution strengthening in high entropy alloys using machine learning

Cheng Wen et al.

Summary: This study developed a relationship characterized by the electronegative difference of elements to represent solid solution strengthening, and proposed a more superior model for predicting the solid solution strength/hardness of high entropy alloys, thereby accelerating the alloy design process.

ACTA MATERIALIA (2021)

Article Thermodynamics

Computational design of V-CoCrFeMnNi high-entropy alloys: An atomistic simulation study

Won-Mi Choi et al.

Summary: Researchers have attempted to enhance the strength of CoCrFeMnNi HEA by adding vanadium (V) in order to stabilize the bcc phase and increase atomic size. Utilizing atomistic simulation, they developed a Co-Cr-Fe-Mn-Ni-V hexanary potential and proposed an empirical equation to estimate the effect of alloying elements on the critical resolved shear stress. As a result, two novel V-added HEAs were designed with higher strength compared to previously developed non-equiatomic CoCrFeMnNi HEAs.

CALPHAD-COMPUTER COUPLING OF PHASE DIAGRAMS AND THERMOCHEMISTRY (2021)

Article Materials Science, Multidisciplinary

Second nearest-neighbor modified embedded-atom method interatomic potentials for the Mo-M (M = Al, Co, Cr, Fe, Ni, Ti) binary alloy systems

Sang-Ho Oh et al.

Summary: New interatomic potentials for Mo-metal (metal = Al, Co, Cr, Fe, Ni, Ti) binary alloy systems have been developed based on the second nearest-neighbor modified embedded-atom method (2NN MEAM) formalism. These potentials reproduce the structural and thermodynamic properties of binary alloys well and can be extended to Pt-Mo-metal multicomponent alloy systems. This work expands the use of 2NN MEAM interatomic potentials into Pt-based multicomponent systems, enabling the design of efficient noble metal catalysts with a greater variety of alloying elements.

COMPUTATIONAL MATERIALS SCIENCE (2021)

Article Chemistry, Multidisciplinary

Machine Learning Accelerated, High Throughput, Multi-Objective Optimization of Multiprincipal Element Alloys

Tian Guo et al.

Summary: By integrating molecular dynamics simulation, machine learning algorithms, and genetic algorithms, researchers have developed an efficient design strategy for MPEAs, successfully predicting optimal compositions of CoNiCrFeMn alloys with high stiffness and critical resolved shear stress.

SMALL (2021)

Article Multidisciplinary Sciences

A machine-learning-based alloy design platform that enables both forward and inverse predictions for thermo-mechanically controlled processed (TMCP) steel alloys

Jin-Woong Lee et al.

Summary: This study predicts mechanical properties of steel alloys using a machine-learning platform, achieving acceptable results with non-linear algorithms. Subsequently, an elitist-reinforced non-dominated sorting genetic algorithm is employed for inverse prediction, with visual representation and analysis through holographic research strategy.

SCIENTIFIC REPORTS (2021)

Article Materials Science, Multidisciplinary

Molecular dynamics simulation and machine learning of mechanical response in non-equiatomic FeCrNiCoMn high-entropy alloy

Liang Zhang et al.

Summary: The study utilized molecular dynamics simulation and machine learning methods to investigate the mechanical properties of non-equiatomic high-entropy alloys, establishing a database describing the relationship between material composition and mechanical properties based on experimental testing. The deep neural network (DNN) model outperformed others in binary classification of yield stress, with the elemental composition strategy guiding the design of polycrystal samples. This research demonstrates that computational study combined with machine learning can provide valuable guidance for designing high-strength HEAs and accelerating the development of new alloy materials.

JOURNAL OF MATERIALS RESEARCH AND TECHNOLOGY-JMR&T (2021)

Article Multidisciplinary Sciences

Nanoscale precipitates as sustainable dislocation sources for enhanced ductility and high strength

Shenyou Peng et al.

PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA (2020)

Article Materials Science, Multidisciplinary

Mechanical Performance Improvement by Nitrogen Addition in N-CoCrNi Compositionally Complex Alloys

Dennis Edgard Jodi et al.

METALLURGICAL AND MATERIALS TRANSACTIONS A-PHYSICAL METALLURGY AND MATERIALS SCIENCE (2020)

Article Thermodynamics

Second nearest-neighbor modified embedded-atom method interatomic potentials for the Co-M (M = Ti, V) binary systems

Sang-Ho Oh et al.

CALPHAD-COMPUTER COUPLING OF PHASE DIAGRAMS AND THERMOCHEMISTRY (2020)

Article Chemistry, Physical

Coupling physics in machine learning to predict properties of high-temperatures alloys

Jian Peng et al.

NPJ COMPUTATIONAL MATERIALS (2020)

Article Thermodynamics

A thermodynamic description of the Al-Cu-Fe-Mn system for an immiscible medium-entropy alloy design

Hyeon-Seok Do et al.

CALPHAD-COMPUTER COUPLING OF PHASE DIAGRAMS AND THERMOCHEMISTRY (2020)

Article Nanoscience & Nanotechnology

Thermal stability of AlCoFeMnNi high-entropy alloy

Anirudha Karati et al.

SCRIPTA MATERIALIA (2019)

Article Materials Science, Multidisciplinary

Effect of Annealing Temperature on Microstructure and Mechanical Properties of a Severe Cold-Rolled FeCoCrNiMn High-Entropy Alloy

Ziyong Li et al.

METALLURGICAL AND MATERIALS TRANSACTIONS A-PHYSICAL METALLURGY AND MATERIALS SCIENCE (2019)

Article Nanoscience & Nanotechnology

Corrosion-resistant high entropy alloy with high strength and ductility

S. S. Nene et al.

SCRIPTA MATERIALIA (2019)

Article Thermodynamics

A thermodynamic description of the Co-Cr-Fe-Ni-V system for high-entropy alloy design

Won-Mi Choi et al.

CALPHAD-COMPUTER COUPLING OF PHASE DIAGRAMS AND THERMOCHEMISTRY (2019)

Article Materials Science, Multidisciplinary

Physical metallurgy-guided machine learning and artificial intelligent design of ultrahigh-strength stainless steel

Chunguang Shen et al.

ACTA MATERIALIA (2019)

Article Chemistry, Multidisciplinary

Ultrastrong Medium-Entropy Single-Phase Alloys Designed via Severe Lattice Distortion

Seok Su Sohn et al.

ADVANCED MATERIALS (2019)

Article Chemistry, Physical

2018 Table of static dipole polarizabilities of the neutral elements in the periodic table

Peter Schwerdtfeger et al.

MOLECULAR PHYSICS (2019)

Article Materials Science, Multidisciplinary

Machine learning assisted design of high entropy alloys with desired property

Cheng Wen et al.

ACTA MATERIALIA (2019)

Article Nanoscience & Nanotechnology

Equilibrium high entropy alloy phase stability from experiments and thermodynamic modeling

James E. Saal et al.

SCRIPTA MATERIALIA (2018)

Article Chemistry, Physical

Critical assessment of Pt surface energy - An atomistic study

Jin-Soo Kim et al.

SURFACE SCIENCE (2018)

Article Chemistry, Physical

Understanding the physical metallurgy of the CoCrFeMnNi high-entropy alloy: an atomistic simulation study

Won-Mi Choi et al.

NPJ COMPUTATIONAL MATERIALS (2018)

Article Materials Science, Multidisciplinary

The search for high entropy alloys: A high-throughput ab-initio approach

Yoav Lederer et al.

ACTA MATERIALIA (2018)

Article Chemistry, Physical

A Thermodynamic Modelling of the Stability of Sigma Phase in the Cr-Fe-Ni-V High-Entropy Alloy System

Won-Mi Choi et al.

JOURNAL OF PHASE EQUILIBRIA AND DIFFUSION (2018)

Article Chemistry, Physical

High entropy effect on structure and properties of (Fe, Co, Ni, Cr)-B amorphous alloys

J. Ding et al.

JOURNAL OF ALLOYS AND COMPOUNDS (2017)

Review Materials Science, Multidisciplinary

A critical review of high entropy alloys and related concepts

D. B. Miracle et al.

ACTA MATERIALIA (2017)

Article Thermodynamics

Second nearest-neighbor modified embedded-atom method interatomic potentials for the Pt-M (M = Al, Co, Cu, Mo, Ni, Ti, V) binary systems

Jin-Soo Kim et al.

CALPHAD-COMPUTER COUPLING OF PHASE DIAGRAMS AND THERMOCHEMISTRY (2017)

Article Thermodynamics

Modified embedded-atom interatomic potential for Fe-Ni, Cr-Ni and Fe-Cr-Ni systems

Changjun Wu et al.

CALPHAD-COMPUTER COUPLING OF PHASE DIAGRAMS AND THERMOCHEMISTRY (2017)

Article Materials Science, Multidisciplinary

Modified embedded-atom method interatomic potentials for the Co-Cr, Co-Fe, Co-Mn, Cr-Mn and Mn-Ni binary systems

Won-Mi Choi et al.

COMPUTATIONAL MATERIALS SCIENCE (2017)

Article Materials Science, Multidisciplinary

High-entropy alloy: challenges and prospects

Y. F. Ye et al.

MATERIALS TODAY (2016)

Article Materials Science, Multidisciplinary

Computational intelligence based design of age-hardenable aluminium alloys for different temperature regimes

Swati Dey et al.

MATERIALS & DESIGN (2016)

Article Materials Science, Multidisciplinary

Mechanical properties of Austenitic Stainless Steel 304L and 316L at elevated temperatures

Raghuram Karthik Desu et al.

JOURNAL OF MATERIALS RESEARCH AND TECHNOLOGY-JMR&T (2016)

Article Materials Science, Multidisciplinary

Phase stability of non-equiatomic CoCrFeMnNi high entropy alloys

Duancheng Ma et al.

ACTA MATERIALIA (2015)

Article Materials Science, Multidisciplinary

Modified embedded-atom method interatomic potentials for the Ni-Co binary and the Ni-Al-Co ternary systems

Young-Kwang Kim et al.

MODELLING AND SIMULATION IN MATERIALS SCIENCE AND ENGINEERING (2015)

Review Engineering, Manufacturing

OpenCalphad - a free thermodynamic software

Bo Sundman et al.

INTEGRATING MATERIALS AND MANUFACTURING INNOVATION (2015)

Article Engineering, Chemical

Prediction of hydrogen permeability in V-Al and V-Ni alloys

Jae-Hyeok Shim et al.

JOURNAL OF MEMBRANE SCIENCE (2013)

Article Thermodynamics

Atomistic modeling of pure Co and Co-Al system

Wei-Ping Dong et al.

CALPHAD-COMPUTER COUPLING OF PHASE DIAGRAMS AND THERMOCHEMISTRY (2012)

Article Materials Science, Multidisciplinary

Microstructure and wear behavior of AlxCo1.5CrFeNi1.5Tiy high-entropy alloys

Ming-Hao Chuang et al.

ACTA MATERIALIA (2011)

Article Physics, Condensed Matter

Modified embedded-atom method interatomic potential for the Fe-Al system

Eunkoo Lee et al.

JOURNAL OF PHYSICS-CONDENSED MATTER (2010)

Article Materials Science, Multidisciplinary

Growth and characterization of indium phosphide single-crystal nanoneedles on microcrystalline silicon surfaces

N. P. Kobayashi et al.

APPLIED PHYSICS A-MATERIALS SCIENCE & PROCESSING (2006)

Article Nanoscience & Nanotechnology

Microstructural development in equiatomic multicomponent alloys

B Cantor et al.

MATERIALS SCIENCE AND ENGINEERING A-STRUCTURAL MATERIALS PROPERTIES MICROSTRUCTURE AND PROCESSING (2004)

Article Materials Science, Multidisciplinary

Nanostructured high-entropy alloys with multiple principal elements: Novel alloy design concepts and outcomes

JW Yeh et al.

ADVANCED ENGINEERING MATERIALS (2004)

Article Thermodynamics

THERMO-CALC & DICTRA, computational tools for materials science

JO Andersson et al.

CALPHAD-COMPUTER COUPLING OF PHASE DIAGRAMS AND THERMOCHEMISTRY (2002)

Article Thermodynamics

A semi-empirical atomic potential for the Fe-Cr binary system

BJ Lee et al.

CALPHAD-COMPUTER COUPLING OF PHASE DIAGRAMS AND THERMOCHEMISTRY (2001)

Article Materials Science, Multidisciplinary

Second nearest-neighbor modified embedded atom method potentials for bcc transition metals

BJ Lee et al.

PHYSICAL REVIEW B (2001)

Article Materials Science, Multidisciplinary

Second nearest-neighbor modified embedded-atom-method potential

BJ Lee et al.

PHYSICAL REVIEW B (2000)