Abstract
Magnesium (Mg) has a strong application potential as a lightweight metal. Yet, its absolute strength still needs improvement. In this work, we demonstrate that machine learning can be utilized to guide the development of high-strength Mg cast alloys. In the design framework, the composition and heat treatment condition are iteratively optimized by a surrogate model that is also evolving. After two iterations, a new alloy with the composition of Mg-10.0Al-2.0Sn-2.0Zn-0.1Ca-0.1Mn (at. pct) was identified. After aging at 200 °C for 96 hours, this alloy shows a Vickers hardness value of 110.5 Hv, which surpasses the highest value (102.5 Hv) in the initial dataset from literature. Finally, microstructure of the optimized alloy was characterized to understand the origin of its high hardness. This work demonstrates the potential of data-driven approaches for material development.
Similar content being viewed by others
Data Availability Statement
Supplementary data to this article can be found online at https://jbox.sjtu.edu.cn/l/5odMQf.
References
[1]S. Celotto: Acta Mater., 2000, vol. 48, pp. 1775-1787.
[2]J. Wang, N. Stanford: Acta Mater., 2015, vol. 100, pp. 53-63.
[3]J. Jayaraj, C.L. Mendis, T. Ohkubo, K. Oh-ishi and K. Hono: Scripta Mater., 2010, vol. 63, pp. 831-834.
[4]J.F. Nie and B. C. Muddle: Acta Mater., 2000, vol. 48, pp. 1691-1703.
[5]J. Jain, P. Cizek, W.J. Poole, M.R. Barnett: Acta Mater., 2013, vol. 61, pp. 4091-4102.
Y. Kang, H. Yan, R. Chen: Mater. Sci. Eng. A, 2015, vol. 646, pp. 361-368.
[7]C.Q. Liu, H.W. Chen, H. Liu, X.J. Zhao, J.F. Nie: Acta Mater., 2018, vol. 144, pp.590-600.
[8]J.F. Nie: Metall. Mater. Trans. A, 2012, vol. 43, pp. 3891-3939.
[9]Q. Luo, Y. Guo, B. Liu, Y. Feng, J. Zhang, Q. Li, and K. Chou: J. Mater. Sci. Technol., 2020, vol. 44, pp. 171-190.
[10]L. Deng and X. Li: IEEE Trans. Audio Speech Lang. Process., 2013, vol. 21, pp. 1060-1088.
K. He, X. Zhang, S. Ren, J. Sun: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2016, pp. 770–78.
R. Collobert, J. Weston, L. Bottou, M. Karlen, K. Kavukcuoglu, P. Kuksa: J. Mach. Learn Res., 2011, pp. 2493–2537.
[13]P. Raccuglia, K. Elbert, P. Adler, C. Falk, M. Wenny, A. Mollo, M. Zeller, S. Friedler, and J. Schrier: Nature, 2016, vol. 533, pp. 73-76.
[14]X. Xu, L. Wang, G. Zhu, X. Zeng: JOM, 2020, vol. 72, pp. 3935-3942.
[15]R. Ramprasad, R. Batra, and G. Pilania, A. Mannodi-Kanakkithodi, and C. Kim: npj Comput. Mater., 2017, vol. 3, pp. 1-13.
[16]A. Agrawal and A. Choudhary: APL Materials., 2016, vol. 4, p. 053208.
[17]A. Rovinelli, M. Sangid, H. Proudhon, and W. Ludwig: npj Comput. Mater., 2018, vol. 4, pp. 1-10.
[18]C. Shen, C. Wang, X. Wei, Y. Li, S. V.D. Zwaag, and W. Xu: Acta Mater., 2019, vol. 179, pp. 201-214.
[19]C. Wen, Y. Zhang, C. Wang, D. Xue, Y. Bai, S. Antonov, L. Dai, T. Lookman, and Y. Su: Acta Mater., 2019, vol. 170, pp. 109-117.
[20]C. Wang, H. Fu, L. Jiang, D. Xue, and J. Xie: npj Comput. Mater., 2019, vol. 5, pp. 1-8.
[21]B. DeCost, T. Francis, and E. Holm: Acta Mater., 2017, vol. 133, pp. 30-40.
[22]D. Xue, P. V. Balachandran, J. Hogden, J. Theiler, D. Xue, and T. Lookman: Nature Commun., 2016, vol. 7, pp. 1-9.
[23]D. Xue, D. Xue, R. Yan, Y. Zhou, and P. V. Balachandran, X. Dong, J. Sun, and T. Lookman: Acta Mater., 2017, vol. 125, pp. 532-541.
[24]T. Lookman, P. V. Balachandran, D. Xue, and R. Yuan: npj Comput. Mater., 2019, vol. 5, pp. 1-17.
[26]E. Schubert, J. Sander, M. Ester, H.P. Kriegel, and X. Xu: ACM Transactions on Database Systems, 2017, vol. 42, pp. 1-21.
[27]C. Liu, H. Chen, C. He, Y. Zhang, and J.F. Nie: Mater. Charact., 2016, vol. 113, pp. 214-221.
[28]R. Ramprasad, R. Batra, G. Pilania, A. Mannodi-Kanakkithodi, C. Kim: npj Comput. Mater., 2017, vol. 3(1), pp. 1-13.
[29]P.N. Tan, M. Steinbach, and V. Kumar: Introduction to Data Mining, Person, New York, 2005.
[30]T. Chen, and C. Guestrin: XGBoosting: A Scalable Tree Boosting System, ACM, San Francisco, 2016, pp. 785-794.
[31]K. Zhang, H. Li, X. Liang, Z. Chen, and L. Wang: Mater. Charact., 2020, vol. 161, p. 110146.
[32]X. Huang, and S. Huang: JOM, 2020, vol. 72, pp. 1384-1394.
[33]L. Kaelbling: Learning in Embedded Systems, MIT press, Cambridge, MA, 1993
[34]D.R. Jones, M. Schonlau, and W.J. Welch: J. Global Optim., 1998, vol. 13, pp. 455-492.
[35]Y. Wang, Y. Tian, T. Kirk, O. Laris, J. H.Ross Jr., R. D.Noebe, V. Keylin, R. Arroyave: Acta Mater., 2020, vol. 194, pp. 144-155.
T. Xiao, Y. Xu, K. Yang, J. Zhang, Y. Peng, Z. Zhang. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2015, vol. 7, pp. 842–50.
A. Viswanath, H. Dieringa, K.K. AjithKumar, U.T.S. Pillai, and B. C. Pai: J. Magn. Alloy, 2015, vol. 3, pp. 16-22.
[38]Y. Xu, X. Zeng, K. Wang, and B. Huang: Philos. Mag., 2015, vol. 95, pp. 1626-1645.
F.R. Elsayed, T.T. Sasaki, C.L. Mendis, T. Ohkubo, and K. Hono: Mater. Sci. Eng. A, 2013, vol. 566, pp. 22-29.
[40]S. Jo, S. Kim, T. Kim, Y. Go, C. Yang, B. You, Y. Kim: J. Alloy Compd., 2018, vol. 749, pp. 794-802.
[41]D. Duly, W.Z. Zhang, and M. Audier: Phil. Mag. A, 1995, vol. 71, pp. 187-204.
Acknowledgments
This work has been financially supported by the National Key Research and Development Program of China (No. 2016YFB0701203) and a collaborative research project (No. 18X120010001) between University of Michigan and Shanghai Jiao Tong University. L.W. is sponsored by the Youth Cheung Kong Scholars Program (No. Q2018077) and the Shanghai Rising-Star Program (No. 20QA1405000). X.Z. is partly supported by the National Natural Science Foundation of China (No. 51825101).
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Manuscript submitted August 24, 2020; accepted December 14, 2020.
Rights and permissions
About this article
Cite this article
Liu, Y., Wang, L., Zhang, H. et al. Accelerated Development of High-Strength Magnesium Alloys by Machine Learning. Metall Mater Trans A 52, 943–954 (2021). https://doi.org/10.1007/s11661-020-06132-1
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11661-020-06132-1