Deciphering the strength-ductility trade-off in (CuNiMn)-X alloys via interpretable machine learning

Abstract

Existing machine learning-assisted alloy design studies often treat models as “black boxes”, lacking interpretability and thus failing to translate predictions into physically meaningful design guidelines. Herein, we propose an integrated strategy combining feature engineering, autonomous model optimization, and interpretability analysis for the efficient design of (CuNiMn)-X alloys, where X denotes Al, Ti, Cr, and Fe alloying elements, with strength-ductility synergy. Through feature cleaning and grid-based hyperparameter optimization, prediction accuracies of 92.6%, 89.2%, and 88.1% are achieved for the microstructure, compressive strength, and fracture strain models, respectively. Experimental validation of the optimized alloy shows errors of -5.0% for compressive strength and -3.2% for fracture strain. SHapley Additive exPlanations analysis reveals the underlying physical mechanisms: valence electron concentration (M-E10) governs phase selection; mean atomic radius (M-A4) and its variance dominate compressive strength via lattice distortion; variances of fusion enthalpy, covalent radius, and shear modulus collectively control compressive strain through triple homogeneity in thermodynamics, structure, and elasticity. This analysis unveils a mirror-image symmetry between high strength and high ductility in feature space, elucidating the strength-ductility trade-off. Guided by predictions, the (CuNiMn)-Al16Cr16Fe16 alloy is experimentally validated, exhibiting a compressive strength of 2,542 MPa and fracture strain of 15.8%. The microstructure consists of Cr-rich body-centered cubic dendrite arms and a Cu-Ni-Fe-Al-rich face-centered cubic interdendritic network, forming a hard-and-tough dual-phase architecture. This closed-loop design strategy provides a new route for the efficient discovery of CuNiMn-based multi-principal element copper alloys and offers guidance for the broader design of complex multi-principal element alloys.

Keywords

CuNiMn-based multi-principal element copper alloy / machine learning / feature screening / SHAP interpretability / strength–ductility synergy

References

[1] Song Y,Sato S.A lightweight shape-memory alloy with superior temperature-fluctuation resistance.Nature2025;638:965-71 PMCID:PMC11864968

[2] Xia Z,Liu J.Designing Ni₂MnSn Heusler magnetic nanoprecipitate in copper alloy for increased strength and electromagnetic shielding.Nat Commun2024;15:10494 PMCID:PMC11612424

[3] Liu B,Huang Z.Microstructure and properties of a novel ultra-high strength, high elasticity and high plasticity Cu–20Ni–20Mn-0.3Nb-0.3Cr-0.1Zr alloy.J Alloys Compd2021;853:157402

[4] Liu B,Liu Y.Effects of Al addition on corrosion behavior and mechanical property of high-strength and high-elasticity Cu–20Ni–20Mn–0.3Nb–0.3Cr–0.3Zr alloy.Mater Charact2020;167:110476

[5] He BB,Yen HW.High dislocation density-induced large ductility in deformed and partitioned steels.Science2017;357:1029-32

[6] Zhu Y.Ductility and plasticity of nanostructured metals: differences and issues.Mater Today Nano2018;2:15-20

[7] Wang Y,Ma X.The optimum grain size for strength-ductility combination in metals.Int J Plast2023;164:103574

[8] Laws KJ,Sridhar A.High entropy brasses and bronzes - microstructure, phase evolution and properties.J Alloys Compd2015;650:949-61

[9] Nagase T,Matsumuro M,Semboshi S.Alloy design and fabrication of ingots in Cu-Zn-Mn-Ni-Sn high-entropy and Cu-Zn-Mn-Ni medium-entropy brasses.Mater Design2019;181:107900

[10] Gao J,Zhang H.Facile route to bulk ultrafine-grain steels for high strength and ductility.Nature2021;590:262-7 PMCID:PMC7888382

[11] Zeng K,Zhang J.Finely tailoring the local ensembles in heterostructured high entropy alloy catalysts through pulsed annealing.Nat Commun2025;16:3403 PMCID:PMC11985931

[12] Woodgate CD,Pártay LB.Structure, short-range order, and phase stability of the Al_xCrFeCoNi high-entropy alloy: insights from a perturbative, DFT-based analysis.npj Comput Mater2024;10:1445

[13] Wang X,Sun S.Amorphous phase-change memory alloy with no resistance drift.Nat Mater2026;25:456-62 PMCID:PMC12960214

[14] Fu X,Zhao B.Atomic-scale observation of non-classical nucleation-mediated phase transformation in a titanium alloy.Nat Mater2022;21:290-6

[15] Guo Q,Wang K,Liaw PK.Coalescence of Al_0.3CoCrFeNi polycrystalline high-entropy alloy in hot-pressed sintering: a molecular dynamics and phase-field study.npj Comput Mater2023;9:1139

[16] Gao S,Zhu Q.Unveiling the mechanisms of strength-ductility synergy in an additively manufactured nanolamellar high-entropy alloy.Nat Commun2025;16:9934 PMCID:PMC12606152

[17] Tsai ST,Tiwary P.Learning molecular dynamics with simple language model built upon long short-term memory neural network.Nat Commun2020;11:5115 PMCID:PMC7547727

[18] Yin J,Li X.A novel neural network-based alloy design strategy: gated recurrent unit machine learning modeling integrated with orthogonal experiment design and data augmentation.Acta Mater2023;243:118420

[19] Wen C,Zhang Y.Modeling solid solution strengthening in high entropy alloys using machine learning.Acta Mater2021;212:116917

[20] Li B,Zheng ZS.Manipulation of mechanical properties of 7xxx aluminum alloy via a hybrid approach of machine learning and key experiments.J Mater Res Technol2022;19:2483-96

[21] Masood Chaudry, U.; Hamad, K.; Abuhmed, T. Machine learning-aided design of aluminum alloys with high performance.Mater Today Commun2021;26:101897

[22] Sanni O,Ukoba K,Jen T.Application of machine learning models to investigate the performance of stainless steel type 904 with agricultural waste.J Mater Res Technol2022;20:4487-99

[23] Singh A,Shekhar Roy S.Modeling of laser aided direct metal deposition of stainless steel using supervised deep learning algorithms.Mater Today Proc2022;62:360-6

[24] Müller S,Shunmugasundaram R.Deep learning-based segmentation of lithium-ion battery microstructures enhanced by artificially generated electrodes.Nat Commun2021;12:6205 PMCID:PMC8551326

[25] Jiang Z,Yang Y.Machine-learning-revealed statistics of the particle-carbon/binder detachment in lithium-ion battery cathodes.Nat Commun2020;11:2310 PMCID:PMC7210251

[26] Zhang H,He X.Dramatically enhanced combination of ultimate tensile strength and electric conductivity of alloys via machine learning screening.Acta Mater2020;200:803-10

[27] Zhang H,Zhu S,Xie J.Machine learning assisted composition effective design for precipitation strengthened copper alloys.Acta Mater2021;215:117118

[28] Tan F,Lei Q.A strategy for high-entropy copper alloys composition design assisted by deep learning based on data reconstruction and network structure optimization.J Mater Res Technol2024;31:1326-36

[29] Tan F,Jiang Y.Dual engine-driven strategy for advanced copper alloy design employing large language models.Acta Mater2026;306:121886

[30] Tang M,Wang D,Kong D.Performance prediction of 2D vertically stacked MoS₂-WS₂ heterostructures base on first-principles theory and Pearson correlation coefficient.Appl Surf Sci2022;596:153498

[31] Baak M,Snoek H.A new correlation coefficient between categorical, ordinal and interval variables with Pearson characteristics.Comput Stat Data Anal2020;152:107043

[32] Xu H,Zhang C.Exploration of the spatially varying relationships between lead and aluminium concentrations in the topsoil of northern half of Ireland using Geographically Weighted Pearson Correlation Coefficient.Geoderma2022;409:115640

[33] Fu T,Cai Z,Tang Y.Correlation research of phase angle variation and coating performance by means of Pearson’s correlation coefficient.Prog Org Coat2020;139:105459

[34] Zhang H,Zhu Y,Wang B.Microstructure evolution, mechanical properties, and wear properties of AlxCoCrFeNi high-entropy alloys by spark plasma sintering.J Mater Eng Perform2026;35:18225-39

[35] Lu Y,Guo S.A promising new class of high-temperature alloys: eutectic high-entropy alloys.Sci Rep2014;4:6200 PMCID:PMC4145285

[36] Miracle D.A critical review of high entropy alloys and related concepts.Acta Mater2017;122:448-511

[37] Li Z,Deng Y,Tasan CC.Metastable high-entropy dual-phase alloys overcome the strength-ductility trade-off.Nature2016;534:227-30

[38] Mizutani U,Massalski T.The original concepts of the Hume-Rothery rule extended to alloys and compounds whose bonding is metallic, ionic, or covalent, or a changing mixture of these.Prog Mater Sci2021;120:100719

[39] Yang S,Zhong Y.Revisit the VEC criterion in high entropy alloys (HEAs) with high-throughput ab initio calculations: a case study with Al-Co-Cr-Fe-Ni system.J Alloys Compd2022;916:165477

[40] Ward L,Choudhary A.A general-purpose machine learning framework for predicting properties of inorganic materials.npj Comput Mater2016;2:16028

[41] Guo S.Phase stability in high entropy alloys: formation of solid-solution phase or amorphous phase.Prog Nat Sci Mater Int2011;21:433-46

[42] Konovalova EV,Koneva NA,Kozlov EV.Influence of the antiphase domain structure on the long-range atomic order parameter in the Ni₃Mn alloy with superstructure L1₂.Phys Solid State2013;55:2116-9

[43] Dong Y,Jiang L,Li T.Effects of electro-negativity on the stability of topologically close-packed phase in high entropy alloys.Intermetallics2014;52:105-9

[44] Yang X.Prediction of high-entropy stabilized solid-solution in multi-component alloys.Mater Chem Phys2012;132:233-8

[45] Larosa CR,Varvenne C.Solid solution strengthening theories of high-entropy alloys.Mater Charact2019;151:310-7

[46] Toda-Caraballo I.Modelling solid solution hardening in high entropy alloys.Acta Mater2015;85:14-23

[47] Kim YK,Lee KA.Superior temperature-dependent mechanical properties and deformation behavior of equiatomic CoCrFeMnNi high-entropy alloy additively manufactured by selective laser melting.Sci Rep2020;10:8045 PMCID:PMC7229066

[48] Ding J.Local chemical order in high-entropy alloys.Acta Metall Sin2021;57:413-24

[49] Labusch R.A statistical theory of solid solution hardening.Phys Status Solidi1970;41:659-69

[50] Ding J,Asta M.Tunable stacking fault energies by tailoring local chemical order in CrCoNi medium-entropy alloys.Proc Natl Acad Sci U S A2018;115:8919-24 PMCID:PMC6130406

[51] Otto F,Somsen C,Eggeler G.The influences of temperature and microstructure on the tensile properties of a CoCrFeMnNi high-entropy alloy.Acta Mater2013;61:5743-55

[52] Senkov O,Miracle D,Liaw P.Refractory high-entropy alloys.Intermetallics2010;18:1758-65

[53] Varvenne C,Curtin WA.Corrigendum to “Theory of strengthening in fcc high entropy alloys” [Acta Mater. 118 (2016) 164-176].Acta Mater2016;119:242

[54] Li Q,Ma E.Strengthening in multi-principal element alloys with local-chemical-order roughened dislocation pathways.Nat Commun2019;10:11464 PMCID:PMC6687833