Interpretable machine learning-based stretch formability prediction of magnesium alloys

Abstract

This study involved the development of an interpretable prediction framework to access the stretch formability of AZ31 magnesium alloys through the combination of the extreme gradient boosting (XGBoost) model with the sparrow search algorithm (SSA). Eleven features were extracted from the microstructures (e.g., grain size (GS), maximum pole intensity (I_max), degree of texture dispersion (μ), radius of maximum pole position (r), and angle of maximum pole position (A)), mechanical properties (e.g., tensile yield strength (TYS), ultimate tensile strength (UTS), elongation-to-failure (EL), and strength difference (ΔS)) and test conditions (e.g., sheet thickness (t) and punch speed (v)) in the data collected from the literature and experiments. Pearson correlation coefficient and exhaustive screening methods identified ten key features (not including UTS) as the final inputs, and they enhanced the prediction accuracy of Index Erichsen (IE), which served as the model’s output. The newly developed SSA-XGBoost model exhibited an improved prediction performance, with a goodness of fit (R²) of 0.91 compared with traditional machine learning models. A new dataset (four samples) was prepared to validate the reliability and generalization capacity of this model, and below 5% errors were observed between predicted and experimental IE values. Based on this result, the quantitative relationship between the key features and IE values was established via Shapley additive explanation method and XGBoost feature importance analysis. I_max, TYS, EL, r, GS, and ΔS showed a crucial influence on the IE of 10 input features. This work offers a reliable and accurate tool for the prediction of the stretch formability of AZ31 magnesium alloys and provides insights into the development of high-formable magnesium alloys.

Keywords

magnesium alloy / machine learning / microstructure / mechanical property / stretch formability

References

[1] ZhangJY, MiaoJS, BalasubramaniN, et al.. Magnesium research and applications: Past, present and future. J. Magnesium Alloys, 2023, 11113867

[2] WangQH, JiangB, ChenDL, et al.. Strategies for enhancing the room-temperature stretch formability of magnesium alloy sheets: A review. J. Mater. Sci., 2021, 562312965

[3] DongJR, ZhangDF, SunJ, DaiQW, PanFS. Effects of different stretching routes on microstructure and mechanical properties of AZ31B magnesium alloy sheets. J. Mater. Sci. Technol., 2015, 319935

[4] T.T. Trang, J.H. Zhang, J.H. Kim, et al., Designing a magnesium alloy with high strength and high formability, Nat. Commun., 9(2018), No. 1, art. No. 2522.

[5] DuttaA, CharitI, JohannesLB, MishraRS. Deep cup forming by superplastic punch stretching of friction stir processed 7075 Al alloy. Mater. Sci. Eng. A, 2005, 3951–2173

[6] WangYJ, ZhangY, JiangHT. Tension: Compression asymmetry and corresponding deformation mechanism in ZA21 magnesium bars with bimodal structure. Int. J. Miner. Metall. Mater., 2023, 30192

[7] HuangXS, SuzukiK, ChinoY. Influences of initial texture on microstructure and stretch formability of Mg–3Al–1Zn alloy sheet obtained by a combination of high temperature and subsequent warm rolling. Scripta Mater., 2010, 634395

[8] YangQS, JiangB, SongB, et al.. The effects of orientation control via tension-compression on microstructural evolution and mechanical behavior of AZ31 Mg alloy sheet. J. Magnesium Alloys, 2022, 102411

[9] KangDH, KimDW, KimS, BaeGT, KimKH, KimNJ. Relationship between stretch formability and work-hardening capacity of twin-roll cast Mg alloys at room temperature. Scripta Mater., 2009, 617768

[10] ParkJW, ShinKS. Improved stretch formability of AZ31 sheet via grain size control. Mater. Sci. Eng. A, 2017, 68856

[11] K. Wei, R. Hu, D.D. Yin, et al., Grain size effect on tensile properties and slip systems of pure magnesium, Acta Mater., 206(2021), art. No. 116604.

[12] H.B. Hou, J.F. Wang, L. Ye, S.J. Zhu, L.G. Wang, and S.K. Guan, Prediction of mechanical properties of biomedical magnesium alloys based on ensemble machine learning, Mater. Lett., 348(2023), art. No. 134605.

[13] S.J. Huang, M.P. Mose, and S. Kannaiyan, A study of the mechanical properties of AZ61 magnesium composite after equal channel angular processing in conjunction with machine learning, Mater. Today Commun., 33(2022), art. No. 104707.

[14] XuXN, WangLY, ZhuGM, ZengXQ. Predicting tensile properties of AZ31 magnesium alloys by machine learning. JOM, 2020, 72113935

[15] ZhangYB, BaiSW, JiangB, LiK, DongZH, PanFS. Modeling the correlation between texture characteristics and tensile properties of AZ31 magnesium alloy based on the artificial neural networks. J. Mater. Res. Technol., 2023, 245286

[16] E.J. Schiessler, T. Würger, S.V. Lamaka, et al., Predicting the inhibition efficiencies of magnesium dissolution modulators using sparse machine learning models, npj Comput. Mater., 7(2021), art. No. 193.

[17] WangYW, XieT, TangQL, et al.. High-throughput calculations combining machine learning to investigate the corrosion properties of binary Mg alloys. J. Magnesium Alloys, 2024, 1241406

[18] Z.X. Lu, S.J. Si, K.Y. He, et al, Prediction of Mg alloy corrosion based on machine learning models, Adv. Mater. Sci. Eng., 2022(2022), art. No. 9597155.

[19] T.Z. Xin, S. Tang, F. Ji, et al., Phase transformations in an ultralight BCC Mg alloy during anisothermal ageing, Acta Mater., 239(2022), art. No. 118248.

[20] SuhJ, Victoria-HernándezJ, LetzigD, GolleR, VolkW. Effect of processing route on texture and cold formability of AZ31 Mg alloy sheets processed by ECAP. Mater. Sci. Eng. A, 2016, 669159

[21] D. Ren, C.C. Wang, X.L. Wei, Q.Q. Lai, and W. Xu, Building a quantitative composition-microstructure-property relationship of dual-phase steels via multimodal data mining, Acta Mater., 252(2023), art. No. 118954.

[22] R.H. Yuan, Z. Liu, P.V. Balachandran, et al., Accelerated discovery of large electrostrains in BaTiO₃-based piezoelectrics using active learning, Adv. Mater., 30(2018), No. 7, art. No. 1702884.

[23] J. Su, Y.Z. Wang, X.K. Niu, S. Sha, and J.Y. Yu, Prediction of ground surface settlement by shield tunneling using XGBoost and Bayesian Optimization, Eng. Appl. Artif. Intell., 114(2022), art. No. 105020.

[24] L.X. Liu, X. Wang, X. Yang, H.J. Liu, J.P. Li, and P.F. Wang, Path planning techniques for mobile robots: Review and prospect, Expert Syst. Appl., 227(2023), art. No. 120254.

[25] M.Z. Sun, J.M. Yang, C.Y. Yang, W.P. Wang, X.B. Wang, and H.F. Li, Research on prediction of PPV in open-pit mine used RUN-XGBoost model, Heliyon, 10(2024), No. 7, art. No. e28246.

[26] L.F. Zhu, Q. Luo, Q.C. Chen, et al., Prediction of ultimate tensile strength of Al–Si alloys based on multimodal fusion learning, Mater. Genome Eng. Adv., 2(2024), No. 1, art. No. e26.

[27] H.T. Zhang, H.D. Fu, S.C. Zhu, W. Yong, and J.X. Xie, Machine learning assisted composition effective design for precipitation strengthened copper alloys, Acta Mater., 215(2021), art. No. 117118.

[28] H.M. Zhou, L.S. Ma, X.L. Niu, et al., A novel hybrid model combined with ensemble embedded feature selection method for estimating reference evapotranspiration in the North China Plain, Agric. Water Manage., 296(2024), art. No. 108807.

[29] NenchevB, TaoQ, DongZH, et al.. Evaluating data-driven algorithms for predicting mechanical properties with small data-sets: A case study on gear steel hardenability. Int. J. Miner. Metall. Mater., 2022, 294836

[30] ChinoY, KimuraK, MabuchiM. Deformation characteristics at room temperature under biaxial tensile stress in textured AZ31 Mg alloy sheets. Acta Mater., 2009, 5751476

[31] WangQH, JiangB, TangAT, et al.. Formation of the elliptical texture and its effect on the mechanical properties and stretch formability of dilute Mg–Sn–Y sheet by Zn addition. Mater. Sci. Eng. A, 2019, 746259

[32] HeC, ZhuHR, YuanM, et al.. Comparison of room-temperature stretch formability of the as extruded Mg-Gd alloys with different double-peak pole spacing. J. Mater. Res. Technol., 2021, 154838

[33] PanchalM, KaushikL, KimMS, RenganayagaluRK, ChoiSH, SinghJ. Effect of pre-twinning and heat treatment on formability of AZX311 Mg alloy. J. Magnesium Alloys, 2024, 1231154

[34] NakataT, KamadoS. Towards tailoring basal texture of rolled Mg alloy sheet by recrystallization for high room-temperature formability: A review. J. Magnesium Alloys, 2023, 11113992

[35] SuhJ, Victoria-HernandezJ, LetzigD, et al.. Improvement in cold formability of AZ31 magnesium alloy sheets processed by equal channel angular pressing. J. Mater. Process. Technol., 2015, 217286

[36] TuJ, ZhouT, LiuL, et al.. Effect of rolling speeds on texture modification and mechanical properties of the AZ31 sheet by a combination of equal channel angular rolling and continuous bending at high temperature. J. Alloy. Compd., 2018, 768598

[37] XuJ, ZhaoJ, JiangB, et al.. Effect of transverse gradient extrusion process on texture and mechanical properties of Mg–3Al–1Zn alloy sheets. J. Mater. Res. Technol., 2023, 276171

[38] Hoseini-AtharMM, MahmudiR, BabuRP, HedströmP. Tailoring the texture of an extruded Mg sheet through constrained groove pressing for achieving low mechanical anisotropy and high yield strength. Scripta Mater., 2020, 186253

[39] WangQH, SongJF, JiangB, et al.. An investigation on microstructure, texture and formability of AZ31 sheet processed by asymmetric porthole die extrusion. Mater. Sci. Eng. A, 2018, 72085

[40] Z.R. Zeng, J.F. Nie, S.W. Xu, C.H.J. Davies, and N. Birbilis, Super-formable pure magnesium at room temperature, Nat. Commun., 8(2017), No. 1, art. No. 972.

[41] SomekawaH, KinoshitaA, KatoA. Great room temperature stretch formability of fine-grained Mg-Mn alloy. Mater. Sci. Eng. A, 2017, 697217

RIGHTS & PERMISSIONS

University of Science and Technology Beijing