Graphical abstract
摘要
数据驱动蠕变断裂寿命预测的最先进技术将微观结构和变形机制纳入机器学习。然而, 在进行实验之前, 未知合金的微观结构和变形机制是不可获得和不确定的, 因此限制了模型的外推。我们报道了一个简化、准确和可推广的替代模型, 使用在Autogluon中实现的自动机器学习算法预测镍基单晶高温合金的蠕变断裂寿命。在不将微观结构信息或变形机制纳入机器学习框架的情况下, 我们证明了可以在独立的测试数据上提高蠕变断裂寿命的预测精度。避免了将微观结构和变形机制与机器学习相结合, 不仅使替代模型易于适用于广阔的未探索的成分/加工空间, 而且有助于新合金的有效逆向设计。我们的工作表明, 自动机器学习软件可以在最少的人为干预下创建代理模型, 在高温合金的设计中显示出良好前景。
References
Feng WH, Chang JX, Zhu SD. Nickel-based single crystal superalloys with different rhenium contents. Rare Met. 2021;45(3):353. https://doi.org/10.1373/j.cnki.cjrm.XY20050020.
Tian SG, Su Y, Qian BJ, Yu XF, Liang FS, Li AA. Creep behavior of a single crystal nickel-based superalloy containing 4.2% Re. Mater Des. 2012;37:236. https://doi.org/10.1016/j.matdes.2012.01.008.
Zhang XS, Chen YZ, Hu JL. Recent advances in the development of aerospace materials. Prog Aerosp Sci. 2018;97:22. https://doi.org/10.1016/j.paerosci.2018.01.001.
Zhang W, Wang XW, Chen HF, Zhang TY, Gong JM. Evaluation of the effect of various prior creep-fatigue interaction damages on subsequent tensile and creep properties of 9% Cr steel. Int J Fatigue. 2019;125:440. https://doi.org/10.1016/j.ijfatigue.2019.04.018.
Cui LQ, Yu JJ, Liu JL, Jin T, Sun XF. The creep deformation mechanisms of a newly designed nickel-base superalloy. Mat Sci Eng A. 2018;710:309. https://doi.org/10.1016/j.msea.2017.11.002.
Coakley J, Dye D, Basoalto H. Creep and creep modelling of a multimodal nickel-base superalloy. Acta mater. 2011;59(3):854. https://doi.org/10.1016/j.actamat.2010.08.035.
Zhang JW, Wang GZ, Xuan FZ, Tu ST. The influence of stress-regime dependent creep model and ductility in the prediction of creep crack growth rate in Cr–Mo–V steel. Mater Des. 2015;65:644. https://doi.org/10.1016/j.matdes.2014.09.070.
Kim YK, Kim D, Kim HK, Oh CS, Lee BJ. An intermediate temperature creep model for Ni-based superalloys. Int J Plast. 2016;79:153. https://doi.org/10.1016/j.ijplas.2015.12.008.
Prasad SC, Rao IJ, Rajagopal KR. A continuum model for the creep of single crystal nickel-base superalloys. Acta Mater. 2005;53(3):669. https://doi.org/10.1016/j.actamat.2004.10.020.
Kim WG, Yin SN, Lee GG, Kim YW, Kim SJ. Creep oxidation behaviour and creep strength prediction for alloy 617. Int J Pres Ves Pip. 2010;87(6):289. https://doi.org/10.1016/j.ijpvp.2010.03.008.
Wang JQ, Fa YZ, Tian Y, Yu XH. A machine-learning approach to predict creep properties of Cr–Mo steel with time-temperature parameters. J Mater Res Technol. 2021;13:635. https://doi.org/10.1016/j.jmrt.2021.04.079.
Wang CC, Wei XL, Ren D, Wang X, Xu W. High-throughput map design of creep life in low-alloy steels by integrating machine learning with a genetic algorithm. Mater Design. 2022;213: 110326. https://doi.org/10.1016/j.matdes.2021.110326.
Tamura M, Abe F, Shiba K, Sakasegawa H, Tanigawa H. Larson-Miller constant of heat-resistant steel. Metall Mater Trans A. 2013;44(6):2645. https://doi.org/10.1007/s11661-013-1631-0.
Hore S, Ghosh RN. Computer simulation of the high temperature creep behaviour of Cr–Mo steels. Mat Sci Eng A. 2011;528(19–20):6095. https://doi.org/10.1007/s11661-013-1631-0.
Meng QH, Wang ZQ. Creep damage models and their applications for crack growth analysis in pipes: a review. Eng Fract Mech. 2019;205:547. https://doi.org/10.1016/j.engfracmech.2015.09.055.
Vladimirov IN, Reese S, Eggeler G. Constitutive modelling of the anisotropic creep behaviour of nickel-base single crystal superalloys. Int J Mech Sci. 2009;51(4):305. https://doi.org/10.1016/j.ijmecsci.2009.02.004.
Dang YY, Zhao XB, Yuan Y, Ying HF, Lu JT, Yang Z, Gu Y. Predicting long-term creep-rupture property of inconel 740 and 740H. Mater High Temp. 2016;33(1):1. https://doi.org/10.1179/1878641315Y.0000000010.
MacLachlan DW, Knowles DM. Modelling and prediction of the stress rupture behaviour of single crystal superalloys. Mat Sci Eng A. 2001;302(2):275. https://doi.org/10.1016/S0921-5093(00)01829-3.
Ramprasad R, Batra R, Pilania G, Mannodi-Kanakkithodi A, Kim C. Machine learning in materials informatics: recent applications and prospects. Npj Comput Mater. 2017;3(1):1. https://doi.org/10.1038/s41524-017-0056-5.
Wang XY, Wang JJ, Zhang CJ, Tong WW, Jiang B, Lu GX, Wen ZX, Feng T. Creep prediction model for nickel-based single-crystal superalloys considering precipitation of TCP phase. Rare Met. 2021;40(10):2892. https://doi.org/10.1007/s12598-020-01670-4.
Lookman T, Balachandran PV, Xue DZ, Yuan RH. Active learning in materials science with emphasis on adaptive sampling using uncertainties for targeted design. Npj Comput Mater. 2019;5(1):1. https://doi.org/10.1038/s41524-019-0153-8.
Biswas S, Castellanos DF, Zaiser M. Prediction of creep failure time using machine learning. Sci Rep. 2020;10(1):1. https://doi.org/10.1038/s41598-020-72969-6.
Shin D, Yamamoto Y, Brady MP, Lee S, Haynes JA. Modern data analytics approach to predict creep of high-temperature alloys. Acta Mater. 2019;168:321. https://doi.org/10.1016/j.actamat.2019.02.017.
Liu Y, Wu JM, Wang ZC, Lu XG, Avdeev M, Shi SQ, Wang CY, Yu T. Predicting creep rupture life of Ni-based single crystal superalloys using divide-and-conquer approach based machine learning. Acta Mater. 2020;195:454. https://doi.org/10.1016/j.actamat.2020.05.001.
Schweizer FA. Single crystal nickel-base super alloy, August 23 1988. US Patent 4,765,850.
Tamaki H, Yoshinari A, Okayama A, Kobayashi M, Kageyama K, Ohno T. High strength Ni-base superalloy for directionally solidified castings, April 18 2000. US Patent 6,051,083.
Naik SK. High strength nickel base single crystal alloys, December 5 1989. US Patent 4,885,216.
Kobayashi T, Koizumi Y, Yokokawa T, Osawa M, Harada H, Maruko T. Development of 4th generation SC Superalloys without Re. J Jpn I Met. 2005;69(2):272. https://doi.org/10.2320/jinstmet.69.272.
Erickson N, Mueller J, Shirkov A, Zhang H, Larroy P, Li M, Smola A. 2020. Autogluon-tabular: robust and accurate automl for structured data. arXiv preprint https://doi.org/10.48550/arXiv.2003.06505.
Chen TQ, He T, Benesty M, Khotilovich V, Tang Y, Cho H, Chen KL, Mitchell R, Cano I, Zhou T. Xgboost: extreme gradient boosting. R packag vers 04–2. 2015;1(4):1.
Ke GL, Meng Q, Finley T, Wang TF, Chen W, Ma WD, Ye QW, Liu TY. Lightgbm: a highly efficient gradient boosting decision tree. Adv. Neural Inf. Process. Syst. 2017;30. https://github.com/Microsoft/LightGBM.
Prokhorenkova L, Gusev G, Vorobev A, Dorogush AV, Gulin A. Catboost: unbiased boosting with categorical features. Adv. Neural Inf. Process. Syst. 2018;31. https://github.com/catboost/catboost.
Breiman L. Random forests. Mach Learn. 2001;45(1):5. https://doi.org/10.1023/A:1010933404324.
Geurts P, Ernst D, Wehenkel L. Extremely randomized trees. Mach Learn. 2006;63(1):3. https://doi.org/10.1007/s10994-006-6226-1.
Peterson LE. K-nearest neighbor. Scholarpedia. 2009;4(2):1883. https://doi.org/10.4249/scholarpedia.1883.
Sun JY, Wei LL, Li QS, Gong SK, Guo HB. Microstructure stability of γ′+ β Ni–Al coated single-crystal superalloy N5 annealed at 1100°C. Rare Met. 2021;40(3):693. https://doi.org/10.1007/s12598-017-0954-1.
Chen JY, Feng Q, Cao LM, Sun ZQ. Improvement of stress–rupture property by Cr addition in Ni-based single crystal superalloys. Mat Sci Eng A. 2011;528(10–11):3791. https://doi.org/10.1016/j.msea.2011.01.060.
Wu XX, Makineni SK, Liebscher CH, Dehm G, Mianroodi JR, Shanthraj P, Svendsen B, Burger D, Eggeler G, Raabe D, Gault B. Unveiling the Re effect in Ni-based single crystal superalloys. Nat Commun. 2020;11(1):389. https://doi.org/10.1038/s41467-019-14062-9.
Lu F, Antonov S, Lu S, Zhang JC, Li LF, Wang D, Zhang J, Feng Q. Unveiling the Re effect on long-term coarsening behaviors of γ′ precipitates in Ni-based single crystal superalloys. Acta Mater. 2022;233:117979. https://doi.org/10.1016/j.actamat.2022.117979.
Kim IS, Choi BG, Jung JE, Do J, Seok WY, Lee YH, Jeong IY. Effect of heat treatment on microstructural evolution and creep behaviors of a conventionally cast nickel-based superalloy. Mater Charact. 2020;165:110378. https://doi.org/10.1016/j.matchar.2020.110378.
Huang YS, Wang XG, Cui CY, Li JG, Ye LH, Hou GC, Yang YH, Liu JL, Liu JD, Zhou YZ, Sun XF. The effect of coarsening of γ′ precipitate on creep properties of Ni-based single crystal superalloys during long-term aging. Mat Sci Eng A. 2020;773: 138886. https://doi.org/10.1016/j.msea.2019.138886.
Li Y, Chen K, Narayan RL, Ramamurty U, Wang YD, Long JC, Tamura N, Zhou X. Multi-scale microstructural investigation of a laser 3D printed Ni-based superalloy. Addit Manuf. 2020;34: 101220. https://doi.org/10.1016/j.addma.2020.101220.
Acknowledgements
This study was financially supported by the National Key Research and Development Program of China (No. 2021YFB3702601), the National Science and Technology Major Project of China (No. J2019-VI-0023-0140), the National Natural Science Foundation of China (No. 52002326) and the Natural Science Foundation of Chongqing (No. cstc2021jcyj-msxmX0602).
Author information
Authors and Affiliations
Corresponding authors
Ethics declarations
Conflict of interests
The authors declare that they have no conflict of interest.
Supplementary Information
Below is the link to the electronic supplementary material.
Rights and permissions
About this article
Cite this article
Zhou, CL., Yuan, RH., Liao, WJ. et al. Creep rupture life predictions for Ni-based single crystal superalloys with automated machine learning. Rare Met. 43, 2884–2890 (2024). https://doi.org/10.1007/s12598-023-02559-8
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12598-023-02559-8