A multi-objective feature optimization strategy for developing high-entropy alloys with optimal strength and ductility

Abstract

Selecting appropriate material features is essential for effective data-driven materials design. Here, we propose a multi-objective feature optimization strategy that identifies feature subsets to improve both prediction accuracy and active learning efficiency for iterative experimentation. Our approach integrates an evolutionary genetic algorithm to explore an expanded feature space, encompassing both traditional feature pools and a continuous numerical representation of elements rather than relying solely on discrete values. We demonstrate this strategy by identifying high-entropy alloys (HEAs) with optimal strength and ductility. Results show that the optimized feature subsets reduce prediction errors by 20% for strength and 11% for ductility. Additionally, within fewer than three feedback iterations, HEAs with outstanding combinations of yield strength and ductility are identified, highlighting the high efficiency of this approach. This multi-objective feature optimization strategy is adaptable to other material systems, offering a pathway to improve machine learning performance and accelerate materials discovery.

Keywords

feature engineering / high entropy alloys / machine learning / materials features / multi-objective feature optimization

References

[1] Lei Z, Liu X, Wu Y, et al. Enhanced strength and ductility in a high-entropy alloy via ordered oxygen complexes. Nature. 2018; 563(7732): 546-550.

[2] Xiong J, Shi S, Zhang T. Machine learning of phases and mechanical properties in complex concentrated alloys. J Mater Sci Technol. 2021; 87: 133-142.

[3] Deng H, Wang M, Xie Z, et al. Enhancement of strength and ductility in non-equiatomic cocrni medium-entropy alloy at room temperature via transformation-induced plasticity. Mater Sci Eng A. 2021; 804:140516.

[4] Shi Y, Yang B, Xie X, Brechtl J, Dahmen KA, Liaw PK. Corrosion of Al xCoCrFeNi high-entropy alloys: Al-content and potential scan-rate dependent pitting behavior. Corros Sci. 2017; 119: 33-45.

[5] Ouyang G, Singh P, Su R, et al. Design of refractory multi-principal-element alloys for high-temperature applications. NPJ Comput Mater. 2023; 9(1): 141.

[6] Listyawan TA, Agustianingrum MP, Na YS, Lim KR, Park N. Improving high-temperature oxidation behavior by modifying Al and Co content in Al-Co-Cr-Fe-Ni high-entropy alloy. J Mater Sci Technol. 2022; 129: 115-126.

[7] Bai H, Su R, Zhao RZ, et al. Oxidation behavior and microstructural evolution of FeCoNiTiCu five-element high-entropy alloy nanoparticles. J Mater Sci Technol. 2024; 177: 133-141.

[8] Raccuglia P, Elbert KC, Adler PD, et al. Machine-learning-assisted materials discovery using failed experiments. Nature. 2016; 533(7601): 73-76.

[9] Butler KT, Davies DW, Cartwright H, Isayev O, Walsh A. Machine learning for molecular and materials science. Nature. 2018; 559(7715): 547-555.

[10] Chen Y, Wang S, Xiong J, et al. Identifying facile material descriptors for Charpy impact toughness in low-alloy steel via machine learning. J Mech Sci Technol. 2023; 132: 213-222.

[11] Himanen L, Geurts A, Foster AS, Rinke P. Data-driven materials science: status, challenges, and perspectives. Adv Sci. 2019; 6(21):1900808.

[12] Zhang H, Fu H, He X, et al. Dramatically enhanced combination of ultimate tensile strength and electric conductivity of alloys via machine learning screening. Acta Mater. 2020; 200: 803-810.

[13] Vazquez G, Singh P, Sauceda D, et al. Efficient machine-learning model for fast assessment of elastic properties of high-entropy alloys. Acta Mater. 2022; 232:117924.

[14] Liu X, Li X, He Q, et al. Machine learning-based glass formation prediction in multicomponent alloys. Acta Mater. 2020; 201: 182-190.

[15] Kwak S, Kim J, Ding H, et al. Using multiple regression analysis to predict directionally solidified TiAl mechanical property. J Mech Sci Technol. 2022; 104: 285-291.

[16] Xu B, Yin H, Jiang X, et al. Data-driven design of Ni-based turbine disc superalloys to improve yield strength. J Mech Sci Technol. 2023; 155: 175-191.

[17] Pan S, Yu J, Han J, et al. Customized development of promising Cu-Cr-Ni-Co-Si alloys enabled by integrated machine learning and characterization. Acta Mater. 2023; 243:118484.

[18] Xue D, Balachandran P, Hogden J, Theiler J, Xue D, Lookman T. Accelerated search for materials with targeted properties by adaptive design. Nat Commun. 2016; 7(1):11241.

[19] He J, Su X, Wang C, et al. Machine learning assisted predictions of multi-component phase diagrams and fine boundary information. Acta Mater. 2022; 240:118341.

[20] Wen C, Zhang Y, Wang C, et al. Machine learning assisted design of high entropy alloys with desired property. Acta Mater. 2019; 170: 109-117

[21] Li J, Xie B, Fang Q, Liu B, Liu Y, Liaw PK. High-throughput simulation combined machine learning search for optimum elemental composition in medium entropy alloy. J Mater Sci Technol. 2021; 68: 70-75.

[22] Jha D, Ward L, Paul A, et al. ElemNet: deep learning the chemistry of materials from only elemental composition. Sci Rep. 2018; 8(1):17593.

[23] Pilania G, Balachandran PV, Gubernatis JE, Lookman T. Classification of ABO3 perovskite solids: a machine learning study. Acta Crystallogr B Struct Sci Cryst Eng Mater. 2015; 71(5): 507-513.

[24] Li X, Shan G, Shek CH. Machine learning prediction of magnetic properties of Fe-based metallic glasses considering glass forming ability. J Mech Sci Technol. 2022; 103: 113-120.

[25] Chen W, Schmidt JN, Yan D, Vohra Y, Chen C. Machine learning and evolutionary pre-diction of superhard B-C-N compounds. NPJ Comput Mater. 2021; 7(1): 114.

[26] Kaufmann K, Vecchio KS. Searching for high entropy alloys: a machine learning approach. Acta Mater. 2020; 198: 178-222.

[27] Tandoc C, Hu Y, Qi L, Liaw PK. Mining of lattice distortion, strength, and intrinsic ductility of refractory high entropy alloys. NPJ Comput Mater. 2023; 9(1): 53.

[28] Ghiringhelli LM, Vybira J, Levchenko SV, Drax C, Scheffler M. Big data of materials science: critical role of the descriptor. Phys Rev Lett. 2014; 114:105503.

[29] Ouyang R, Curtarolo S, Ahmetcik E, Scheffler M, Ghiringhelli LM. Sisso: a compressed-sensing method for systematically identifying efficient physical models of materials properties. Phys Rev Mater. 2018; 2(8):083802.

[30] Bartel CJ, Millican SL, Deml AM, et al. Physical descriptor for the Gibbs energy of inorganic crystalline solids and temperature-dependent materials chemistry. Nat Commun. 2018; 9(1):4168.

[31] Gou W, Shi Z, Zhu Y, et al. Multi-objective optimization of three mechanical properties of Mg alloys through machine learning. MGE Adv. 2024; 2(3): e54.

[32] Zhang Y, Wen C, Wang C, et al. Phase prediction in high entropy alloys with a rational selection of materials descriptors and machine learning models. Acta Mater. 2019; 185: 528-539.

[33] Liu Y, Zou X, Ma S, Maxim A, Shi S. Feature selection method reducing correlations among features by embedding domain knowledge. Acta Mater. 2022; 238:118195.

[34] Wang J, Xu P, Ji X, Li M, Lu W. MIC-SHAP: an ensemble feature selection method for materials machine learning. Mater Today Commun. 2023; 37:106910.

[35] Liu Y, Wu J, Maxim A, Shi S. Multi-layer feature selection incorporating weighted score-based expert knowledge toward modeling materials with targeted properties. Adv Theory Simul. 2020; 3(2):1900215.

[36] Zhang Y, Wen C, Dang P, Lookman T, Xue D, Su Y. Toward ultra-high strength high entropy alloys via feature engineering. J Mech Sci Technol. 2024; 200: 243-252.

[37] Florian H, Loïc MR, Alán AG. Chimera: enabling hierarchy based multi-objective optimization for self-driving laboratories. Chem Sci. 2018; 9(39): 7642-7655.

[38] Florian H, Matteo A, Riley JH, Loïc MR, Aspuru-Guzik A. Gryffin: an algorithm for Bayesian optimization of categorical variables informed by expert knowledge. Appl Phys Rev. 2021; 8(3):031406.

[39] Li X, Shan G, Zhang J, Shek C. Accelerated design for magnetic high entropy alloys using data-driven multi-objective optimization. J Mater Chem C. 2022; 10(45): 17291-17302.

[40] Deb K, Pratap A, Agarwal S, Meyarivan T. A fast and elitist multiobjective genetic algorithm: NSGA-II. IEEE Trans Evol Comput. 2002; 6(2): 182-197.

[41] Zhang Y, Zhou Y, Lin J, Chen G, Liaw PK. Solid-solution phase formation rules for multi-component alloys. Adv Eng Mater. 2008; 10(6): 534-538.

[42] Wu Y, Cai Y, Chen X, et al. Phase composition and solid solution strengthening effect in TiZrNbMoV high-entropy alloys. Mater Des. 2015; 83: 651-660.

[43] Poletti MG, Battezzati L. Electronic and thermodynamic criteria for the occurrence of high entropy alloys in metallic systems. Acta Mater. 2014; 75: 297-306.

[44] Guo S. Phase selection rules for cast high entropy alloys: an overview. Mater Sci Technol. 2015; 31(10): 1223-1230.

RIGHTS & PERMISSIONS

2025 The Author(s). Materials Genome Engineering Advances published by Wiley-VCH GmbH on behalf of University of Science and Technology Beijing.