Big data-assisted digital twins for the smart design and manufacturing of advanced materials: from atoms to products

Abstract

Motivated by the ever-increasing wealth of data boosted by national strategies in terms of data-driven Integrated Computational Materials Engineering (ICME), Materials Genome Engineering, Materials Genome Infrastructures, Industry 4.0, Materials 4.0 and so on, materials informatics represents a unique strategy in revealing the fundamental relationships in the development and manufacturing of advanced materials. Materials developments are becoming ever more integrated with robust data-driven and data-intensive technologies. In the present review, big data-assisted digital twins (DTs) for the smart design and manufacturing of advanced materials are presented from the perspective of the digital thread. In the introduction of the DT design paradigm in the ICME era, the simulation aspects of DT and the data and design infrastructures are discussed. Referring to the simulation and theoretical factors of DTs, high-throughput simulation and automation and artificial intelligence-assisted multiscale atomistic modeling are detailed through several cases studies. With respect to data and data mining technologies, entropy and its application for attribute selection in decision trees are discussed to emphasize knowledge-based modeling, simulation and data analysis in machine learning coherently. Guided by the perspectives and case studies of the digital thread, we present our recent work on the design, manufacturing and product service via big data-assisted DTs for smart design and manufacturing by integrating some of these advanced concepts and technologies. It is believed that big data-assisted DTs for smart design and manufacturing effectively support better products with the application of novel materials by reducing the time and cost of materials design and deployment.

Keywords

ICME / Materials Genome Engineering / high-throughput / automation / workflow / data mining / digital thread

References

[1] Zhang TY.Informatics is fueling new materials discovery.J Mater Inf2021;1:6

[2] Zhang TY.New tool in the box.J Mater Inf2021;1:1

[3] Rajan K.Materials informatics.Materials Today2005;8:38-45

[4] Kalidindi SR,Li S.Role of materials data science and informatics in accelerated materials innovation.MRS Bull2016;41:596-602

[5] Kalidindi SR,Mcdowell DL.Vision for data and informatics in the future materials innovation ecosystem.JOM2016;68:2126-37

[6] Liu Z.A materials research paradigm driven by computation.JOM2009;61:18-20

[7] Liu Z.Ocean of data: integrating first-principles calculations and CALPHAD modeling with machine learning.J Phase Equilib Diffus2018;39:635-49

[8] A national strategic plan for advanced manufacturing. Available from: https://www.nist.gov/oam/national-strategic-plan-advanced-manufacturing [Last accessed on 23 Feb 2022]

[9] Wang WY,Lin D.DID code: a bridge connecting the materials genome engineering database with inheritable integrated intelligent manufacturing.Engineering2020;6:612-20

[10] Olson GB.Computational design of hierarchically structured materials.Science1997;277:1237-42

[11] Raccuglia P,Adler PD.Machine-learning-assisted materials discovery using failed experiments.Nature2016;533:73-6

[12] Marzari N.Materials modelling: the frontiers and the challenges.Nat Mater2016;15:381-2

[13] Kalinin SV,Archibald RK.Big-deep-smart data in imaging for guiding materials design.Nat Mater2015;14:973-80

[14] Kusiak A.Smart manufacturing must embrace big data.Nature2017;544:23-5

[15] Curtarolo S,Nardelli MB,Sanvito S.The high-throughput highway to computational materials design.Nat Mater2013;12:191-201

[16] Debnath A,Sun H.Generative deep learning as a tool for inverse design of high entropy refractory alloys.J Mater Inf2021;1:3

[17] National Science and Technology Council. Materials genome initiative for global competitiveness. Available from: https://www.researchgate.net/publication/267901251_Materials_Genome_Initiative_for_Global_Competitiveness [Last accessed on 23 Feb 2022]

[18] Wang W, Li J, Liu W, Liu Z. Integrated computational materials engineering for advanced materials: a brief review.Computational Materials Science2019;158:42-8

[19] Zhou J,Zhou Y,Zang J.Toward new-generation intelligent manufacturing.Engineering2018;4:11-20

[20] Zhong RY,Klotz E.Intelligent manufacturing in the context of Industry 4.0: a review.Engineering2017;3:616-30

[21] Rickman J,Kalinin S.Materials informatics: from the atomic-level to the continuum.Acta Materialia2019;168:473-510

[22] Lookman T,Rajan K.Information science for materials discovery and design. Cham: Springer; 2016.

[23] Liu Z.The Penn State-Georgia Tech CCMD: ushering in the ICME Era.Integr Mater Manuf Innov2014;3:409-28

[24] National Academies of Sciences, Engineering, and Medicine; Policy and Global Affairs; Government-University-Industry Research Roundtable. The Fourth Industrial Revolution: Proceedings of a Workshop - In Brief. Washington: The National Academies Press; 2017.

[25] The future of manufacturing: a new era of opportunity and challenge for the UK. Available from: https://assets.publishing.service.gov.uk/government/uploads/system/uploads/attachment_data/file/25 [Last accessed on 23 Feb 2022]

[26] Tao F.Make more digital twins.Nature2019;573:490-1

[27] Cui B,Ooi BC.Big data: the driver for innovation in databases.Natl Sci Rev2014;1:27-30

[28] Boschert S.Digital twin - the simulation aspect. In: Hehenberger P, Bradley D, editoes. Mechatronic Futures. Cham: Springer; 2016. p. 59-74.

[29] Wang WY,Lin D.A brief review of data-driven ICME for intelligently discovering advanced structural metal materials: Insight into atomic and electronic building blocks.J Mater Res2020;35:872-89

[30] Yi Y,Liu X,Feng J.Digital twin-based smart assembly process design and application framework for complex products and its case study.J Manuf Syst2021;58:94-107

[31] Ferguson S. Apollo 13: the first digital twin. Available from: https://blogs.sw.siemens.com/simcenter/apollo-13-the-first-digital-twin/ [Last accessed on 23 Feb 2022]

[32] Jose R.Materials 4.0: materials big data enabled materials discovery.Applied Materials Today2018;10:127-32

[33] Xiong W.Cybermaterials: materials by design and accelerated insertion of materials.npj Comput Mater2016;2

[34] Craig PL. Modeling software for Materials 4.0. Available from: https://news.psu.edu/story/670090/2021/09/21/academics/modeling-software-materials-40 [Last accessed on 23 Feb 2022]

[35] Bocklund B,Egorov A,Roslyakova I.ESPEI for efficient thermodynamic database development, modification, and uncertainty quantification: application to Cu-Mg.MRS Communications2019;9:618-27

[36] Liu Z.Computational thermodynamics and its applications.Acta Materialia2020;200:745-92

[37] Kaufman L.CALPHAD, first and second generation - Birth of the materials genome.Scripta Materialia2014;70:3-6

[38] Olson G.Materials genomics: from CALPHAD to flight.Scripta Materialia2014;70:25-30

[39] Liu Z.Perspective on Materials Genome®.Chin Sci Bull2014;59:1619-23

[40] Liu Z.First-principles calculations and CALPHAD modeling of thermodynamics.J Phase Equilib Diffus2009;30:517-34

[41] Wang Y,Bocklund BJ.DFTTK: Density Functional Theory ToolKit for high-throughput lattice dynamics calculations.Calphad2021;75:102355

[42] Shin D.Computational materials system design. 1st ed. Cham: Springer; 2018. DOI: 10.1007/978-3-319-68280-8

[43] Zhou BC,Liu ZK.Electrons to phases of magnesium. In: Horstemeyer MF, editor. Integrated computational materials engineering (ICME) for metals: concepts and case studies. Hoboken: John Wiley & Sons; 2018; p. 237-82.

[44] Liu X,Kosters J. Vision 2040: a roadmap for integrated, multiscale modeling and simulation of materials and systems. Available from: https://ntrs.nasa.gov/api/citations/20180002010/downloads/20180002010.pdf [Last accessed on 23 Feb 2022]

[45] National Science & Technology Council. Strategy for American Leadership in Advanced Manufacturing. Available from: https://trumpwhitehouse.archives.gov/wp-content/uploads/2018/10/Advanced-Manufacturing-Strategic-Plan-2018.pdf [Last accessed on 23 Feb 2022]

[46] Broderick SR,Rajan K.Harnessing the big data paradigm for ICME: shifting from materials selection to materials enabled design.JOM2016;68:2109-15

[47] Zhang M,Huang B.Digital twin data: methods and key technologies.digitaltwin2021;1:2

[48] Robbins DW.A simple, multidimensional approach to high-throughput discovery of catalytic reactions.Science2011;333:1423-7 PMCID:PMC3261636

[49] Otis RA.High-throughput thermodynamic modeling and uncertainty quantification for ICME.JOM2017;69:886-92

[50] de Walle A, Sun R, Hong Q, Kadkhodaei S. Software tools for high-throughput CALPHAD from first-principles data.Calphad2017;58:70-81

[51] Mounet N,Schwaller P.Two-dimensional materials from high-throughput computational exfoliation of experimentally known compounds.Nat Nanotechnol2018;13:246-52

[52] Li R,Wang WY,Zhang Y.High-throughput calculations for high-entropy alloys: a brief review.Front Mater2020;7:290

[53] Shang S,Wang WY.A comprehensive first-principles study of pure elements: vacancy formation and migration energies and self-diffusion coefficients.Acta Materialia2016;109:128-41

[54] Saal JE,Aykol M,Wolverton C.Materials design and discovery with high-throughput density functional theory: the open quantum materials database (OQMD).JOM2013;65:1501-9

[55] Jain A,Moore CJ.A high-throughput infrastructure for density functional theory calculations.Computational Materials Science2011;50:2295-310

[56] Krajewski AM,Xu J. Extensible structure-informed prediction of formation energy with improved accuracy and usability employing neural networks. Available from: https://arxiv.org/abs/2008.13654. https://arxiv.org/abs/2008.13654 [Last accessed on 23 Feb 2022]

[57] Kim K,He J,Agrawal A.Machine-learning-accelerated high-throughput materials screening: discovery of novel quaternary Heusler compounds.Phys Rev Materials2018;2:123801

[58] Curtarolo S,Hart GL.AFLOW: an automatic framework for high-throughput materials discovery.Computational Materials Science2012;58:218-26

[59] Oganov AR,Zhu Q.Structure prediction drives materials discovery.Nat Rev Mater2019;4:331-48

[60] Mathew K,Faghaninia A.Atomate: a high-level interface to generate, execute, and analyze computational materials science workflows.Computational Materials Science2017;139:140-52

[61] Baskes MI.Application of the embedded-atom method to covalent materials: a semiempirical potential for silicon.Phys Rev Lett1987;59:2666-9

[62] Daw MS.Semiempirical, quantum mechanical calculation of hydrogen embrittlement in metals.Phys Rev Lett1983;50:1285-8

[63] Mishin Y.Angular-dependent interatomic potential for tantalum.Acta Materialia2006;54:5013-26

[64] Mishin Y,Papaconstantopoulos D.Phase stability in the Fe-Ni system: investigation by first-principles calculations and atomistic simulations.Acta Materialia2005;53:4029-41

[65] Onat B,Malone BD.Implanted neural network potentials: application to Li-Si alloys.Phys Rev B2018;97:094106

[66] Zong H,Ding X,Lookman T.Developing an interatomic potential for martensitic phase transformations in zirconium by machine learning.npj Comput Mater2018;4:48

[67] Zhang L,Wang H,E W.Deep potential molecular dynamics: a scalable model with the accuracy of quantum mechanics.Phys Rev Lett2018;120:143001

[68] Jia W,Chen M.Pushing the limit of molecular dynamics with ab initio accuracy to 100 million atoms with machine learning. SC20: International Conference for High Performance Computing, Networking, Storage and Analysis; 2020 Nov 9-19; Atlanta, GA, USA. IEEE; 2020. p. 1-14.

[69] Chen X,Zhao Y,Chu W.TensorAlloy: an automatic atomistic neural network program for alloys.Computer Physics Communications2020;250:107057

[70] Chen X,Gao X.Machine learning enhanced empirical potentials for metals and alloys.Computer Physics Communications2021;269:108132

[71] Shang HH,Gao XY.TensorKMC: kinetic monte Carlo simulation of 50 trillion atoms driven by deep learning on a new generation of Sunway supercomputer. The International Conference for High Performance Computing, Networking, Storage and Analysis (SC’ 21); St. Louis, Missouri. New York, NY, USA: Association for Computing Machinery; 2021. p. 1-14.

[72] Bramer M.Principles of data mining. London: Springer: 2016.

[73] Ball P.Four decades of materials developments transform society.MRS Bull2013;38:873-85

[74] de Walle A, Nataraj C, Liu Z. The thermodynamic database database.Calphad2018;61:173-8

[75] Zou C,Wang WY.Integrating data mining and machine learning to discover high-strength ductile titanium alloys.Acta Materialia2021;202:211-21

[76] Wang WY,Wang Y.Atomic and electronic basis for the serrations of refractory high-entropy alloys.npj Comput Mater2017;3

[77] Wang WY,Wang Y.Power law scaled hardness of Mn strengthened nanocrystalline AlMn non-equilibrium solid solutions.Scripta Mater2016;120:31-6

[78] Umehara M,Guevarra D,Boyd DA.Analyzing machine learning models to accelerate generation of fundamental materials insights.npj Comput Mater2019;5:34

[79] Liu ZK,Shang S.Thermal expansion anomaly regulated by entropy.Sci Rep2014;4:7043 PMCID:PMC4229665

[80] Rickman JM,Harmer MP.Materials informatics for the screening of multi-principal elements and high-entropy alloys.Nat Commun2019;10:2618 PMCID:PMC6565683

[81] Ye Y,Lu J,Yang Y.High-entropy alloy: challenges and prospects.Materials Today2016;19:349-62

[82] Rost CM,Borman T.Entropy-stabilized oxides.Nat Commun2015;6:8485 PMCID:PMC4598836

[83] Bramer M.Decision tree induction: using entropy for attribute selection. Principles of data mining. London: Springer; 2016. p. 49-62.

[84] Bramer M.Decision tree induction: using frequency tables for attribute selection. Principles of data mining. London: Springer; 2016. p. 63-78.

[85] Liu ZK.Materials 4.0 and the Materials Genome Initative.Adv Mater Process2020;178:50

[86] Chiarello F,Bonaccorsi A.Extracting and mapping industry 4.0 technologies using wikipedia.Comput Ind2018;100:244-57

[87] Qi Q.Digital twin and big data towards smart manufacturing and industry 4.0: 360 degree comparison.IEEE Access2018;6:3585-93

[88] Qi Q,Hu T.Enabling technologies and tools for digital twin.J Manuf Syst2021;58:3-21

[89] Tao F,Wang L.Digital twins and cyber-physical systems toward smart manufacturing and industry 4.0: correlation and comparison.Engineering2019;5:653-61

[90] Pettey C. Prepare for the impact of digital twins. Available from: https://www.gartner.com/smarterwithgartner/prepare-for-the-impact-of-digital-twins [Last accessed on 23 Feb 2022]

[91] Lim KYH,Chen C.A digital twin-enhanced system for engineering product family design and optimization.J Manuf Syst2020;57:82-93

[92] Mukhtarkhanov M,Talamona D.Application of stereolithography based 3D printing technology in investment casting.Micromachines (Basel)2020;11:946 PMCID:PMC7589843

[93] Francalanza E,Constantinescu C.A knowledge-based tool for designing cyber physical production systems.Comput Ind2017;84:39-58