Machine-learning-enabled composition–process co-design of heat-resistant cast aluminum alloys with superior elevated-temperature strength

Abstract

To address the reliance on trial-and-error methods and the prolonged development cycles inherent in the composition and process design of novel cast aluminum alloys, this study constructed a multi-source feature system integrating alloy composition, physicochemical properties of elements, testing conditions, and process parameters. Employing a three-step feature selection method, a prediction model for high-temperature ultimate tensile strength (UTS) was established with a test set the coefficient of determination of 0.881 and an mean absolute error of 22.639 MPa. Based on this model, a synergistic design of the alloy composition and heat treatment process was conducted by coupling the model with a genetic algorithm (GA), and four novel cast aluminum alloys were experimentally validated. The experimental results indicate that the designed alloys exhibit enhanced elevated-temperature strength compared with the commercial reference alloys. Notably, the ZL-2 alloy demonstrated optimal performance, achieving a UTS of 214.2 MPa when tested at 300 °C after holding at 300 °C for 1 h. Furthermore, SHapley Additive exPlanations (SHAP) analysis revealed significant nonlinear interactions among alloy composition, testing conditions, and process parameters in determining tensile strength. Multiscale microstructural characterization reveals that the exceptional elevated-temperature strength of ZL-2 stems from the synergistic effects of nanoscale Al₂₀Cu₂Mn₃ and Al₂CuMg precipitates, and micron-scale Al₃Ti-containing intermetallics. This study demonstrates the application potential of data-driven methods in the composition-process synergistic design of heat-resistant cast aluminum alloys.

Keywords

Heat-resistant cast aluminum alloys / machine learning / composition-process co-design / precipitation strengthening

References

[1] Javidani M.Application of cast Al–Si alloys in internal combustion engine components.Int Mater Rev2014;59:132-58

[2] Timelli G,Rakhmonov J.Influence of process parameters and Sr addition on the microstructure and casting defects of LPDC A356 alloy for engine blocks.J MaterSci Technol2016;32:515-23

[3] Yan J,Zhang W.Research on accelerated thermal fatigue testing and life prediction of Al-Si alloy pistons under start-stop cycles.Int J Fatigue2025;191:108677

[4] Xiong P,Li Z.A new accelerated thermal fatigue experiment method of pistons and its application.Eng Fail Anal2024;163:108599

[5] Roy S,Rodriguez A,Shyam A.Comparative evaluation of cast aluminum alloys for automotive cylinder heads: Part I - Microstructure evolution.Metall Mater Trans A2017;48:2529-42

[6] Rakhmonov J,Pan L,Chen X.Enhanced mechanical properties of high-temperature-resistant Al–Cu cast alloy by microalloying with Mg.J Alloys Compd2020;827:154305

[7] Jiang L,Langan T.Coupled segregation mechanisms of Sc, Zr and Mn at θ′ interfaces enhances the strength and thermal stability of Al-Cu alloys.Acta Mater2021;206:116634

[8] Bansal U,Mondol S.The interplay of precipitation of ordered compounds and interfacial segregation in Al‐Cu‐Hf‐Si alloys for high-temperature strength.Acta Mater2022;240:118355

[9] Wu Y,Le W,Song W.Optimization of high-temperature mechanical properties of aluminum alloys through exclusive precipitation of T-phase.J Mater Res Technol2024;33:3144-54

[10] Booth-Morrison C,Seidman DN.Coarsening resistance at 400 °C of precipitation-strengthened Al–Zr–Sc–Er alloys.Acta Mater2011;59:7029-42

[11] Gao YH,Zhang JY.Stabilizing nanoprecipitates in Al-Cu alloys for creep resistance at 300°C.Mater Res Lett2019;7:18-25

[12] Yang J,Li H,Lu B.Heat treatment optimization of 2219 aluminum alloy fabricated by wire-arc additive manufacturing.Coatings2023;13:610

[13] Gariboldi E.Enhancing thermal stability and high-temperature properties of foundry Al alloys through Zr and/or Er as minor alloying elements.Int J Metalcast2025;19:3552-65

[14] Qi Y,Yang X.Achieving superior high-temperature mechanical properties in Al-Cu-Li-Sc-Zr alloy with nano-scale microstructure via laser additive manufacturing.Mater Res Lett2024;12:17-25

[15] Lu Q,Li H.Synergy of multiple precipitate/matrix interface structures for a heat resistant high-strength Al alloy.Nat Commun2023;14:2959 PMCID:PMC10205818

[16] Mondol S,Kumar S.Enhancement of high temperature strength of 2219 alloys through small additions of Nb and Zr and a novel heat treatment.Metall Mater Trans A2018;49:3047-57

[17] Mondol S,Kumar S.Improvement of high temperature strength of 2219 alloy by Sc and Zr addition through a novel three-stage heat treatment route.Mater Sci Eng A2018;732:157-66

[18] Cheng S,Zhang M,Zhang L.Forward versus inverse design of Al-Si-Mg-Cu alloys targeting peak comprehensive mechanical properties: a comparative study integrating computational thermodynamics and active learning.Acta Mater2026;306:121930

[19] Jiang L,Hu H,Fu H.A rapid and effective method for alloy materials design via sample data transfer machine learning.npj Comput Mater2023;9:979

[20] 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

[21] Yang C,Jia Y,Li M.A machine learning-based alloy design system to facilitate the rational design of high entropy alloys with enhanced hardness.Acta Mater2022;222:117431

[22] Wang J,Oh S.Multiscale computational framework linking alloy composition to microstructure evolution via machine learning and nanoscale analysis.npj Comput Mater2025;11:1730

[23] Kavousi S.Integration of multiscale simulations and machine learning for predicting dendritic microstructures in solidification of alloys.Acta Mater2025;289:120860

[24] Jiang L,Zhang Z.Synchronously enhancing the strength, toughness, and stress corrosion resistance of high-end aluminum alloys via interpretable machine learning.Acta Mater2024;270:119873

[25] Jiang L,Zhang X.Interpretable machine learning design for concurrent and significant enhancement of the mechanical properties and corrosion resistance of low-density Mg-Li alloys.J Magnes Alloys2025;13:6001-20

[26] Hu M,Knibbe R.Designing unique and high-performance Al alloys via machine learning: mitigating data bias through active learning.Comput Mater Sci2024;244:113204

[27] Li Y,Li Z.Developing novel low-density high-entropy superalloys with high strength and superior creep resistance guided by automated machine learning.Acta Mater2025;285:120656

[28] He S,Li L.Design biomedical β-Ti alloys with exceptional strength-ductility balance via domain knowledge-based machine learning.Acta Mater2025;301:121550

[29] Guru MK,Aydin RC.Machine learning pipeline for Structure–Property modeling in Mg-alloys using microstructure and texture descriptors.Acta Mater2025;295:121132

[30] Pedregosa F,Gramfort A.Scikit-learn: machine learning in Python.J Mach Learn Res2011;12:2825-30https://jmlr.org/papers/v12/pedregosa11a.html. (accessed on 27 Jul 2026)

[31] Lundberg SM. A unified approach to interpreting model predictions. In 31st Conference on Neural Information Processing Systems (NIPS 2017), Long Beach, USA. 2017. https://proceedings.neurips.cc/paper_files/paper/2017/file/8a20a8621978632d76c43dfd28b67767-Paper.pdf. (accessed on 27 Jul 2026)

[32] Jiang L,Yang W,Liu S.Effect of heat treatment on microstructure and dimensional stability of ZL114A aluminum alloy.Trans Nonferrous Met Soc China2010;20:2124-8

[33] Li Y,Xu H.Study on heat treatment process for ZL205A alloy (in Chinese).Foundry Technol2017;38:68-70

[34] Xu S,Lin B.Effects of Fe-addition as a beneficial modifying element on the microstructure and mechanical properties of an Al–Si–Cu–Mg–Ni–Mn piston alloy.Metallogr Microstruct Anal2023;12:401-12

[35] Liao H,Hu Y.Effect of RE addition on solidification process and high-temperature strength of Al−12%Si−4%Cu−1.6%Mn heat-resistant alloy.Trans Nonferrous Met Soc China2019;29:1117-26

[36] Chen J,Wu Y.Contributions to high temperature strengthening from three types of heat-resistant phases formed during solidification, solution treatment and ageing treatment of Al-Cu-Mn-Ni alloys respectively.Mater Sci Eng A2020;772:138819

[37] Li G,Zheng J.Synergistic effect of joint addition of Sb+Mn on high temperature strengthening in Al–4Cu heat-resistant alloy.Mater Sci Eng A2022;851:143623

[38] Li G,Zheng J.Micro-alloying effects of Mn and Zr on the evolution of ageing precipitates and high temperature strength of Al-11.5Si–4Cu alloy after a long-time heat exposure.Mater Sci Eng A2021;828:142121

[39] Chen J,Xu H.Uneven precipitation behavior during the solutionizing course of Al‐Cu‐Mn alloys and their contribution to high temperature strength.Adv Mater Sci Eng2018;2018:6741502

[40] Su R,Jia Y,Qu Y.Study on properties and microstructure of an Al–Cu–Mg–Fe–Ni alloy with two-stage aging treatment.Mater Res Express2019;6:126561

[41] Lin B,Zheng X,Lou Z.Developing high performance mechanical properties at elevated temperature in squeeze cast Al-Cu-Mn-Fe-Ni alloys.Mater Charact2019;150:128-37

[42] Ritchie RO.The conflicts between strength and toughness.Nat Mater2011;10:817-22

[43] Ma Y,Zhang M.Break through the strength-ductility trade-off dilemma in aluminum matrix composites via precipitation-assisted interface tailoring.Acta Mater2023;242:118470

[44] Ma Y,Jiang B.Controlled formation of coherent cuboidal nanoprecipitates in body-centered cubic high-entropy alloys based on Al₂(Ni,Co,Fe,Cr)₁₄ compositions.Acta Mater2018;147:213-25

[45] Ma Y,Jie J,Dong C.Coherent precipitation and strengthening in a dual-phase AlNi₂Co₂Fe_1.5Cr_1.5 high-entropy alloy.Mater Sci Eng A2019;764:138241

[46] Klenam D,Asumadu T,Soboyejo W.Solving the strength-ductility trade-off using complex concentrated alloy design strategy: an overview.Smart Mater Manuf2025;3:100091

[47] Seidman DN,Dunand DC.Precipitation strengthening at ambient and elevated temperatures of heat-treatable Al(Sc) alloys.Acta Mater2002;50:4021-35

[48] Koju R.Atomistic study of grain-boundary segregation and grain-boundary diffusion in Al-Mg alloys.Acta Mater2020;201:596-603

[49] Belov N,Matveeva I.Optimization of phase composition of Al–Cu–Mn–Zr–Sc alloys for rolled products without requirement for solution treatment and quenching.J Alloys Compd2014;583:206-13

[50] Liao H,Suo X.Dispersoid particles precipitated during the solutionizing course of Al-12 wt%Si-4 wt%Cu-1.2 wt%Mn alloy and their influence on high temperature strength.Mater Sci Eng A2017;699:201-9

[51] Wolverton C.Crystal structure and stability of complex precipitate phases in Al–Cu–Mg–(Si) and Al–Zn–Mg alloys.Acta Mater2001;49:3129-42

[52] Gazizov M,Holmestad R.The coarsening behavior of strengthening particles in an Al–Cu–Mg–Ag alloy during creep.Mater Sci Eng A2023;884:145515

[53] Chen XJ,Wang Z.Unveiling micromechanism of Fe minor addition‐induced property degradation of an Al‐5.1Cu‐0.65Mg‐0.8Mn (wt%) alloy.Rare Metals2025;44:3496-513

[54] Lu G,Wang J,Liu C.High-temperature age-hardening behavior of Al–Mg–Si alloys with varying Sn contents.J Mater Res Technol2021;14:2165-73

[55] Hu K,Wang H.The role of in-situ Al₃Ti formed during solidification in improving the high-temperature properties of Al–Cu alloy.Mater Sci Eng A2024;902:146585

[56] Bate P.The effect of deformation on grain growth in Zener pinned systems.Acta Mater2001;49:1453-61