Machine learning-guided design and development of metallic structural materials

Abstract

In recent years, the advent of machine learning (ML) in materials science has provided a new tool for accelerating the design and discovery of new materials with a superior combination of mechanical properties for structural applications. In this review, we provide a brief overview of the current status of the ML-aided design and development of metallic alloys for structural applications, including high-performance copper alloys, nickel- and cobalt-based superalloys, titanium alloys for biomedical applications and high strength steel. We also present our perspectives regarding the further acceleration of data-driven discovery, development, design and deployment of metallic structural materials and the adoption of ML-based techniques in this endeavor.

Keywords

Structural materials / metallic alloys / materials informatics / machine learning / composition-processing-microstructure-property relationships

References

[1] Callister WD.Materials science and engineering : an introduction. New York: Wiley; 2018.

[2] Rajan K.Materials informatics: the materials “Gene” and big data.Annu Rev Mater Res2015;45:153-69

[3] Williams JC.Progress in structural materials for aerospace systems11The Golden Jubilee Issue - selected topics in Materials Science and Engineering: past, present and future, edited by S. Suresh.Acta Materialia2003;51:5775-99

[4] Rajan K.Combinatorial materials sciences: experimental strategies for accelerated knowledge discovery.Annu Rev Mater Res2008;38:299-322

[5] Miracle DB,Zhang Z,Flores KM.Emerging capabilities for the high-throughput characterization of structural materials.Annu Rev Mater Res2021;51:131-64

[6] Horstemeyer MF.Integrated Computational Materials Engineering (ICME) for metals: using multiscale modeling to invigorate engineering design with science. John Wiley & Sons; 2012

[7] Van Der Giessen E,Bertin N.Roadmap on multiscale materials modeling.Model Simul Mat Sci Eng2020;28:043001

[8] Su Y,BAI Y.Progress in materials genome engineering in China.Acta Metall Sin2020;56:1313-23

[9] Kalidindi SR.Materials data science: current status and future outlook.Annu Rev Mater Res2015;45:171-93

[10] Morgan D.Opportunities and challenges for machine learning in materials science.Annu Rev Mater Res2020;50:71-103

[11] Sparks TD,Parry ME,Brgoch J.Machine learning for structural materials.Annu Rev Mater Res2020;50:27-48

[12] Suh C,Warren JA.Evolving the materials genome: how machine learning is fueling the next generation of materials discovery.Annu Rev Mater Res2020;50:1-25

[13] Hart GLW,Toher C.Machine learning for alloys.Nat Rev Mater2021;6:730-55

[14] Ramakrishna S,Lu W.Materials informatics.J Intell Manuf2019;30:2307-26

[15] Saal JE,Meredig B.Machine learning in materials discovery: confirmed predictions and their underlying approaches.Annu Rev Mater Res2020;50:49-69

[16] Yu J,Chen Y,Liu X.Accelerated design of L12-strengthened Co-base superalloys based on machine learning of experimental data.2020;195:108996

[17] Ruan J,Yang T.Accelerated design of novel W-free high-strength Co-base superalloys with extremely wide γ/γʹ region by machine learning and CALPHAD methods.Acta Materialia2020;186:425-33

[18] Pan S,Yu J.Accelerated discovery of high-performance Cu-Ni-Co-Si alloys through machine learning.2021;209:109929

[19] Yang F,Wang Q.Cluster-formula-embedded machine learning for design of multicomponent β-Ti alloys with low Young’s modulus.npj Comput Mater2020;6:1-11

[20] Xiong S,Wu X.A combined machine learning and density functional theory study of binary Ti-Nb and Ti-Zr alloys: Stability and Young’s modulus.Computational Materials Science2020;184:109830

[21] Zhang H,Zhu S,Xie J.Machine learning assisted composition effective design for precipitation strengthened copper alloys.Acta Materialia2021;215:117118

[22] Liu P,Antonov S.Machine learning assisted design of γ′-strengthened Co-base superalloys with multi-performance optimization.npj Comput Mater2020;6:1-9

[23] Wu C,Wu C.Machine learning recommends affordable new Ti alloy with bone-like modulus.Materials Today2020;34:41-50

[24] Tamura R,Minagawa K.Machine learning-driven optimization in powder manufacturing of Ni-Co based superalloy.2021;198:109290

[25] Qin Z,Wang Y.Phase prediction of Ni-base superalloys via high-throughput experiments and machine learning.Materials Research Letters2021;9:32-40

[26] Guo S,Liu X,Jiang Q.A predicting model for properties of steel using the industrial big data based on machine learning.Computational Materials Science2019;160:95-104

[27] Wang C,Jiang L,Xie J.A property-oriented design strategy for high performance copper alloys via machine learning.npj Comput Mater2019;5:1-8

[28] Yu J,Chen Y.A two-stage predicting model for γ′ solvus temperature of L12-strengthened Co-base superalloys based on machine learning.Intermetallics2019;110:106466

[29] Yi J,Zhao Y.Precipitation behavior of Cu-3.0Ni-0.72Si alloy.Acta Materialia2019;166:261-70

[30] Cheng J,Yu F.Evaluation of nanoscaled precipitates in a Cu-Ni-Si-Cr alloy during aging.J Alloys Compd2014;614:189-95

[31] Hu T,Liu J,Wu C.The crystallographic and morphological evolution of the strengthening precipitates in Cu-Ni-Si alloys.Acta Materialia2013;61:1210-9

[32] Wei H,Zhao Y,Su L.Correlation mechanism of grain orientation/microstructure and mechanical properties of Cu-Ni-Si-Co alloy.Mater Sci Eng A Struct Mater2021;814:141239

[33] Li J,Mi X,Xie H.Microstructure evolution and properties of a quaternary Cu-Ni-Co-Si alloy with high strength and conductivity.Mater Sci Eng A Struct Mater2019;766:138390

[34] Pollock TM.Nickel-based superalloys for advanced turbine engines: chemistry, microstructure and properties.J Propuls Power2006;22:361-74

[35] Reed RC.The superalloys: fundamentals and applications. Cambridge university press; 2008.

[36] Pollock TM.Alloy design for aircraft engines.Nat Mater2016;15:809-15

[37] Smith TM,Antolin N.Phase transformation strengthening of high-temperature superalloys.Nat Commun2016;7:13434 PMCID:PMC5121413

[38] Li Y,Li J,Koizumi Y.Influence of cobalt addition on microstructure and hot workability of IN713C superalloy.2017;122:340-6

[39] Cloots M,Uggowitzer PJ.Microstructural characteristics of the nickel-based alloy IN738LC and the cobalt-based alloy Mar-M509 produced by selective laser melting.Mater Sci Eng A Struct Mater2016;658:68-76

[40] Huron ES,Mourer DP.The influence of grain boundary elements on properties and microstructures of P/M nickel base superalloys.Superalloys2004;2004:73-81

[41] Horst OM,Schreuer J.Thermoelastic properties and γ’-solvus temperatures of single-crystal Ni-base superalloys.J Mater Sci2021;56:7637-58

[42] Chen J,Chen J.Tailoring the creep properties of second-generation Ni-based single crystal superalloys by composition optimization of Mo, W and Ti.Mater Sci Eng A Struct Mater2021;799:140163

[43] Cormier J.Thermal cycling creep resistance of Ni-based single crystal superalloys. Proceedings of the 13th International Symposium of Superalloys, Superalloys. 2016. p. 385-94.

[44] Rame J,Bortoluci Ormastroni LM.Platinum-containing new generation nickel-based superalloy for single crystalline applications. In: Tin S, Hardy M, Clews J, Cormier J, Feng Q, Marcin J, O'brien C, Suzuki A, editors. Superalloys 2020. Cham: Springer International Publishing; 2020. p. 71-81.

[45] Kim H,Seo S,Jeong H.Regression analysis of high-temperature oxidation of Ni-based superalloys using artificial neural network.Corrosion Science2021;180:109207

[46] Suzuki A,Pollock TM.L1₂-strengthened cobalt-base superalloys.Annu Rev Mater Res2015;45:345-68

[47] Sato J,Oikawa K,Kainuma R.Cobalt-base high-temperature alloys.Science2006;312:90-1

[48] Makineni SK,Chattopadhyay K.Low-density, high-temperature Co base superalloys.Annu Rev Mater Res2021;51:187-208

[49] Niinomi M,Nakai M,Li H.Biomedical titanium alloys with Young's moduli close to that of cortical bone.Regen Biomater2016;3:173-85 PMCID:PMC4881615

[50] Wang Q,Liaw PK.Structural Stabilities of β-Ti alloys studied using a new Mo equivalent derived from [β/(α + β)] phase-boundary slopes.Metall and Mat Trans A2015;46:3440-7

[51] Sumitomo N,Hattori T.Experiment study on fracture fixation with low rigidity titanium alloy: plate fixation of tibia fracture model in rabbit.J Mater Sci Mater Med2008;19:1581-6

[52] Abdel-Hady Gepreel M, Niinomi M. Biocompatibility of Ti-alloys for long-term implantation.J Mech Behav Biomed Mater2013;20:407-15

[53] Eisenbarth E,Müller M,Breme J.Biocompatibility of beta-stabilizing elements of titanium alloys.Biomaterials2004;25:5705-13

[54] Peters H.Havkmann J, et al. Industrial data mining in steel industry. 30th Journees Siderurgiques Internationales (JSI); 2012 Dec; Paris.Stahl und Eisen2012;132:

[55] Ordieres-Meré J,Castejón-Limas M.Chapter 20: Data mining experiences in steel industry. Handbook of research on machine learning applications and trends: algorithms, methods and techniques. Capítulo de Libro; 2010. p. 427-39.

[56] Agrawal A,Cecen A,Choudhary AN.Exploration of data science techniques to predict fatigue strength of steel from composition and processing parameters.Integr Mater Manuf Innov2014;3:90-108

[57] Agrawal A.A fatigue strength predictor for steels using ensemble data mining: steel fatigue strength predictor. Proceedings of the 25th ACM International on Conference on information and knowledge management; 2016 Oct 24. 2016; p. 2497-500.

[58] Agrawal A.An online tool for predicting fatigue strength of steel alloys based on ensemble data mining.Int J Fatigue2018;113:389-400

[59] Poon AIF.Opening the black box of AI-Medicine.J Gastroenterol Hepatol2021;36:581-4

[60] Hakkoum H,Abnane I.Assessing and Comparing Interpretability Techniques for Artificial Neural Networks Breast Cancer Classification.Comput Methods Biomech Biomed Eng Imaging Vis2021;9:587-99

[61] Linardatos P,Kotsiantis S.Explainable AI: a review of machine learning interpretability methods.Entropy (Basel)2020;23:18 PMCID:PMC7824368

[62] Elshawi R,Sakr S.On the interpretability of machine learning-based model for predicting hypertension.BMC Med Inform Decis Mak2019;19:146 PMCID:PMC6664803

[63] Yuan R,Balachandran PV.Accelerated discovery of large electrostrains in BaTiO₃-based piezoelectrics using active learning.Adv Mater2018;30:1702884

[64] Lookman T,Xue D.Active learning in materials science with emphasis on adaptive sampling using uncertainties for targeted design.npj Comput Mater2019;5:1-17

[65] Lookman T,Xue D,Theiler J.Statistical inference and adaptive design for materials discovery.Curr Opin Solid State Mater Sci2017;21:121-8

[66] Kim C,Jha A.Active-learning and materials design: the example of high glass transition temperature polymers.MRS Communications2019;9:860-6

[67] Peng GCY,Tepole AB.Multiscale modeling meets machine learning: what can we learn?.Arch Comput Methods Eng2021;28:1017-37 PMCID:PMC8172124

[68] Karniadakis GE,Lu L,Wang S.Physics-informed machine learning.Nat Rev Phys2021;3:422-40