Multi-objective optimization of three mechanical properties of Mg alloys through machine learning

Abstract

Conventional trial-and-error method is usually time-consuming and expensive for multi-objective optimization of Mg alloys. Although machine learning exhibits great potential to accelerate related research studies, machine learning prediction of properties of Mg alloys is often a prediction of a single target at a time. To address this, this paper integrates non-dominated sorting genetic algorithm III multi-objective optimization algorithm with light gradient boosting machine algorithm to simultaneously optimize yield strength, ultimate tensile strength, and elongation of Mg alloys. This is the first time that simultaneous machine learning optimization of these three objectives has been achieved for Mg alloys.

Keywords

alloy design / machine learning / Mg alloys / multi-objective optimization

References

1	Alaneme KK, Okotete EA. Enhancing plastic deformability of Mg and its alloys—a review of traditional and nascent developments. J Magnesium Alloys. 2017;5(4):460-475.
2	Zeng Z, Stanford N, Davies CHJ, Nie J-F. Birbilis N. Magnesium extrusion alloys: a review of developments and prospects. Int Mater Rev. 2019;64(1):27-62.
3	Ghorbani M, Boley M, Nakashima PNH, Birbilis N. A machine learning approach for accelerated design of magnesium alloys. Part B: regression and property prediction. J Magnesium Alloys. 2023;11(11):4197-4205.
4	Wang Y, Xie T, Tang Q, et al. High-throughput calculations combining machine learning to investigate the corrosion properties of binary Mg alloys. J Magnesium Alloys. 2022;12(1):1406-1418.
5	Dong S, Wang Y, Li J, Li Y, Wang L, Zhang J. Machine learning aided prediction and design for the mechanical properties of magnesium alloys. Met Mater Int. 2024;30(3):593-606.
6	Hou H, Wang J, Ye L, Zhu S, Wang L, Guan S. Prediction of mechanical properties of biomedical magnesium alloys based on ensemble machine learning. Mater Lett. 2023;348:134605.
7	Mi X, Dai L, Jing X, et al. Accelerated design of high-performance Mg-Mn-based magnesium alloys based on novel Bayesian optimization. J Magnesium Alloys. 2024;12(2):750-766.
8	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.
9	Jiang L, Zhang Z, Hu H, He X, Fu H, Xie J. A rapid and effective method for alloy materials design via sample data transfer machine learning. npj Comput Mater. 2023;9(1):26.
10	Feng X, Wang Z, Jiang L, Zhao F, Zhang Z. Simultaneous enhancement in mechanical and corrosion properties of Al-Mg-Si alloys using machine learning. J Mater Sci Technol. 2023;167:1-13.
11	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.
12	Deb K, Jain H. An evolutionary many-objective optimization algorithm using reference-point-based nondominated sorting approach, Part I: solving problems with box constraints. IEEE Trans Evol Comput. 2014;18(4):577-601.
13	Jain H, Deb K. An evolutionary many-objective optimization algorithm using reference-point based nondominated sorting approach, Part II: handling constraints and extending to an adaptive approach. IEEE Trans Evol Comput. 2014;18(4):602-622.
14	Ma D, Zhou S, Han Y, Ma W, Huang H. Multi-objective ship weather routing method based on the improved NSGA-III algorithm. J Ind Inf Integr. 2024;38:100570.
15	Dong Z-R, Luo W-W. Ship pipe route design based on NSGA-III and multi-population parallel evolution. Ocean Eng. 2024;293:116666.
16	Wang Y, Wang G, Yao G, Shen Q, Yu X, He S. Combining GA-SVM and NSGA-III multi-objective optimization to reduce the emission and fuel consumption of high-pressure common-rail diesel engine. Energy. 2023;278:127965.
17	Sun X, Fu J. Many-objective optimization of BEV design parameters based on gradient boosting decision tree models and the NSGA-III algorithm considering the ambient temperature. Energy. 2024;288:129840.
18	Liu Y, You K, Jiang Y, et al. Multi-objective optimal scheduling of automated construction equipment using non-dominated sorting genetic algorithm (NSGA-III). Autom ConStruct. 2022;143:104587.
19	Wang J, Wu Z, Yang L, et al. Investigation on distributed rescheduling with cutting tool maintenance based on NSGA-III in large-scale panel furniture intelligent manufacturing. J Manuf Process. 2024;112:214-224.
20	Li S, Zhang M, Wang N, et al. Intelligent scheduling method for multimachine cooperative operation based on NSGA-III and improved ant colony algorithm. Comput Electron Agric. 2023;204:107532.
21	Tanhadoust A, Madhkhan M, Nehdi ML. Two-stage multi-objective optimization of reinforced concrete buildings based on nondominated sorting genetic algorithm (NSGA-III). J Build Eng. 2023;75:107022.
22	Cao Z, Zhang Y, Wang Z, Zhao L. Multi-objective optimization of assembly free-form cable-stiffened reticulated shell considering the influence of initial states. Structures. 2024;62:106198.
23	Liu YH, Zhang ZR, Wang J, et al. A novel Mg-Gd-Y-Zn-Cu-Ni alloy with excellent combination of strength and dissolution via peak-aging treatment. J Magnesium Alloys. 2023;11(2):720-734.
24	Niu H-Y, Deng K-K. Nie K-B, Cao F-F Zhang X-C, Li W-G. Microstructure, mechanical properties and corrosion properties of Mg-4Zn-xNi alloys for degradable fracturing ball applications. J Alloys Compd. 2019;787:1290-1300.
25	Zhang Y, Wang X, Kuang Y, Liu B, Zhang K, Fang D. Enhanced mechanical properties and degradation rate of Mg-3Zn-1Y based alloy by Cu addition for degradable fracturing ball applications. Mater Lett. 2017;195:194-197.
26	Wang J, Li T, Li HX, et al. Effect of trace Ni addition on microstructure, mechanical and corrosion properties of the extruded Mg–Gd–Y–Zr–Ni alloys for dissoluble fracturing tools. J Magnesium Alloys. 2020;9(5):1632-1643.
27	Dai C, Wang J, Pan Y, et al. Achieving exceptionally high strength and rapid degradation rate of Mg-Er-Ni alloy by strengthening with lamellar γ0 and bulk LPSO phases. J Mater Sci Technol. 2024;168:88-102.
28	He G, Zhou Y, Gu Z, et al. Low-cost high-strength Mg–7Zn-xAl-0.3Mn (x=1, 3, 5) cast magnesium alloys via grain boundary strengthening and precipitation strengthening. Mater Sci Eng A. 2023;885:145664.
29	Huang Q, Liu Y, Tong M, et al. Enhancing tensile strength of Mg–Al–Ca wrought alloys by increasing Ca concentration. Vacuum. 2020;177:109356.
30	Wen Y, Guan B, Xin Y, et al. Solute atom mediated Hall-Petch relations for magnesium binary alloys. Scr Mater. 2022;210:114451.
31	Zhao D, Li G, Li P, et al. A comparative study on the microstructures and mechanical properties of the Mg-xCa/Mn/Ce alloys and pure Mg. Mater Sci Eng A. 2021;803:140508.
32	Wang Z, Guan Y, Wang T, et al. Microstructure and mechanical properties of AZ31 magnesium alloy sheets processed by constrained groove pressing. Mater Sci Eng A. 2019;745:450-459.
33	Wang J, Wei F, Shi B, Ding Y, Jin P. The effect of Y content on microstructure and tensile properties of the as-extruded Mg–1Al–xY alloy. Mater Sci Eng A. 2019;765:138288.
34	Verma R, Srinivasan A, Jayaganthan R, Nath SK, Goel S. Studies on tensile behaviour and microstructural evolution of UFG Mg-4Zn-4Gd alloy processed through hot rolling. Mater Sci Eng A. 2017;704:412-426.
35	Tang Y, Le Q, Misra RDK, Su G, Cui J. Influence of extruding temperature and heat treatment process on microstructure and mechanical properties of three structures containing Mg-Li alloy bars. Mater Sci Eng A. 2018;712:266-280.
36	Chen X, Jia Y, Le Q, Ning S, Li X, Yu F. The interaction between in situ grain refiner and ultrasonic treatment and its influence on the mechanical properties of Mg–Sm–Al magnesium alloy. J Mater Res Technol. 2020;9(4):9262-9270.
37	Xiao B, Song J, Tang A, et al. Effect of pass reduction on distribution of shear bands and mechanical properties of AZ31B alloy sheets prepared by on-line heating rolling. J Mater Process Technol. 2020;280:116611.
38	Zhao T, Hu Y, Zhang C, et al. Influence of extrusion conditions on microstructure and mechanical properties of Mg-2Gd-0.3Zr magnesium alloy. J Magnesium Alloys. 2022;10(2):387-399.
39	Yang W, Quan GF, Ji B, et al. Effect of Y content and equal channel angular pressing on the microstructure, texture and mechanical property of extruded Mg-Y alloys. J Magnesium Alloys. 2022;10(1):195-208.
40	Sriraman N, Kumaran S, Narayanan N S. Influence of thermomechanical processing on microstructure, mechanical and strain hardening properties of single-phase Mg-4Li-0.5Ca alloy for structural application. J Magnesium Alloys. 2020;8(4):1262-1268.
41	Liu C, Chen X, Chen J, Atrens A, Pan F. The effects of Ca and Mn on the microstructure, texture and mechanical properties of Mg-4 Zn alloy. J Magnesium Alloys. 2021;9(3):1084-1097.
42	Yao H, Wen J, Xiong Y, Lu Y, Ren F, Cao W. Extrusion temperature impacts on biometallic Mg-2.0Zn-0.5Zr-3.0Gd (wt%) solid-solution alloy. J Alloys Compd. 2018;739:468-480.
43	Tang J, Huo Q, Zhang Z, et al. Enhancing the creep resistance of a dilute Mg-1.5 wt%Nd alloy plate via pre-compression and subsequent peak-aging. J Alloys Compd. 2021;861:158590.
44	Li W, Zhu S, Sun Y, Guan S. Microstructure and properties of biodegradable Mg–Zn–Y-Nd alloy micro-tubes prepared by an improved method. J Alloys Compd. 2020;835:155369.
45	Li B, Hou L, Wu R, et al. Microstructure and thermal conductivity of Mg-2Zn-Zr alloy. J Alloys Compd. 2017;722:772-777.
46	Hu T, Xiao W, Wang F, et al. Improving tensile properties of Mg-Sn-Zn magnesium alloy sheets using pre-tension and ageing treatment. J Alloys Compd. 2018;735:1494-1504.
47	Li Z, Gu X, Lou S, Zheng Y. The development of binary Mg–Ca alloys for use as biodegradable materials within bone. Biomaterials. 2008;29(10):1329-1344.
48	Yao Y, Huang ZH, Ma H, et al. High strength Mg-1.4Gd-1.2Y-0.4Zn sheet and its strengthening mechanisms. Mater Sci Eng A. 2019;747:17-26.
49	Zhao J, Jiang B, Yuan Y, et al. Influence of Ca and Zn synergistic alloying on the microstructure, tensile properties and strain hardening of Mg-1Gd alloy. Mater Sci Eng A. 2020;785:139344.
50	Xu Q, Guan L, Jiang Y, Tang G, Wang S. Improved plasticity of Mg–Al–Zn alloy by electropulsing tension. Mater Lett. 2010;64(9):1085-1087.
51	Zhou G, Jain MK, Wu P, Shao Y, Li D, Peng Y. Experiment and crystal plasticity analysis on plastic deformation of AZ31B Mg alloy sheet under intermediate temperatures: how deformation mechanisms evolve. Int J Plast. 2016;79:19-47.
52	Ong SP, Richards WD, Jain A, et al. Python Materials Genomics (pymatgen): a robust, open-source python library for materials analysis. Comput Mater Sci. 2013;68:314-319.
53	Zhang YX, Xing GC, Sha ZD, Poh LH. A two-step fused machine learning approach for the prediction of glass-forming ability of metallic glasses. J Alloys Compd. 2021;875:160040.
54	Zhang H, Fu H, Zhu S, Yong W, Xie J. Machine learning assisted composition effective design for precipitation strengthened copper alloys. Acta Mater. 2021;215:117118.
55	Cui Z, Chang Y, Zhang J, Cai X, Zhang W. Improved NSGA-III with selection-and-elimination operator. Swarm Evol Comput. 2019;49:23-33.
56	Shi B, Lookman T, Xue D. Multi-objective optimization and its application in materials science. MGE Adv. 2023;1(2):e14.
57	Ke G, Meng Q, Finley T, et al. LightGBM: a highly efficient gradient boosting decision tree. In: Proceedings of the 31st International Conference on Neural Information Processing Systems. Curran Associates Inc.;2017:3149-3157.
58	Zhao J, Xu J, Liu Y, Wang Q, Jiang B, Pan F. Role of Zn addition on the microstructure and tensile property in Mg–Mn–Nd alloys. J Mater Res Technol. 2023;27:7964-7969.
59	Li L, Yuan T, Yuan X. The microstructure regulation and property enhancement of directed energy deposited Al-Zn-Mg-Cu-Si-Zr alloy with various Zr contents. Mater Chem Phys. 2023;297:127318.
60	Guan K, Egusa D, Abe E, et al. Microstructures and mechanical properties of as-cast Mg-Sm-Zn-Zr alloys with varying Gd contents. J Magnesium Alloys. 2022;10(5):1220-1234.
61	Lv B, Peng J, Peng Y, Tang A. The effect of addition of Nd and Ce on the microstructure and mechanical properties of ZM21 Mg alloy. J Magnesium Alloys. 2013;1(1):94-100.
62	Xu J, Guan B, Xin Y, Huang G, Wu P, Liu Q. Revealing the role of pyramidal <c+a>slip in the high ductility of Mg-Li alloy. J Magnesium Alloys. 2021;12(3):1021-1025.
63	Wang Q, Zhai H, Liu L, et al. Novel Mg-Bi-Mn wrought alloys: the effects of extrusion temperature and Mn addition on their microstructures and mechanical properties. J Magnesium Alloys. 2022;10(9):2588-2606.
64	Bai Y, Ye B, Guo J, Wang L, Kong X, Ding W. Mechanical properties and yield asymmetry of Mg-Y-Zn alloys: competitive behavior of second phases. Mater Char. 2020;164:110301.
65	Ci W, Deng L, Chen X, et al. Effect of minor Gd addition on microstructure, mechanical performance, and corrosion behavior of Mg–Y–Gd alloys. J Mater Res Technol. 2023;26:4107-4120.
66	Zheng Z, Dong Z, Jiang B, et al. Evolution of strength with rare-earth content in highly-alloyed Mg-Gd-Y alloys. Scr Mater. 2024;238:115772.
67	Jiang L, Fu H, Zhang Z, et al. Synchronously enhancing the strength, toughness, and stress corrosion resistance of high-end aluminum alloys via interpretable machine learning. Acta Mater. 2024;270:119873.
68	Abe E, Kawamura Y, Hayashi K, Inoue A. Long-period ordered structure in a high-strength nanocrystalline Mg-1 at%Zn-2 at%Y alloy studied by atomic-resolution Z-contrast STEM. Acta Mater. 2002;50(15):3845-3857.
69	Tan W, Li T, Li S, Fang D, Ding X, Sun J. High strength-ductility and rapid degradation rate of as-cast Mg-Cu-Al alloys for application in fracturing balls. J Mater Sci Technol. 2021;94:22-31.
70	Shi Z-Z, Li X-M. Yao S-L, et al. 300 MPa grade biodegradable highstrength ductile low-alloy (BHSDLA) Zn-Mn-Mg alloys: an in vitro study. J Mater Sci Technol. 2023;138:233-244.
71	Cao M, Xue Z, Lv Z-Y. Sun J-L, Shi Z-Z. Wang L-N. 300 MPa grade highly ductile biodegradable Zn-2Cu-(0.2-0.8)Li alloys with novel ternary phases. J Mater Sci Technol. 2023;157:234-245.
72	Shi ZZ, Li M, Li XM, Wang LN. Surface-roughness-induced plasticity in a biodegradable Zn alloy. Adv Mater. 2022;35(50).
73	Wang Y, Chen C, Tao Y, Wen Z, Chen B, Zhang H. A many-objective optimization of industrial environmental management using NSGAIII: a case of China’s iron and steel industry. Appl Energy. 2019;242:46-56.
74	Chaudhari P, Thakur AK, Kumar R, Banerjee N, Kumar A. Comparison of NSGA-III with NSGA-II for multi objective optimization of adiabatic styrene reactor. Mater Today Commun. 2022;57:1509-1514.