Machine learning-enabled constrained multi-objective design of architected materials

Source data

Acknowledgements

This work was funded by the National Key Research and Development Program of China (2018YFE0104200, P.W., Y.T., Y.Z.), National Natural Science Foundation of China (52175274, 82172065, and 51875310, P.W.), and Tsinghua-Toyota Joint Research Fund (P.W.) and Tsinghua Precision Medicine Foundation (P.W.); Y.W. would like to acknowledge the financial support of the Shuimu fellowship of Tsinghua University.

Author contributions

Y.W. and Y.Q. conceived the idea; P.W. planned the study; Y.W. designed the machine-learning framework; Y.L. and B.P. wrote the relevant code; Y.Q. contributed to the digital design framework. J.D. and Y.Q. performed the FEM simulation and analysis; J.D., B.P., and A.L. performed the experiments; Y.W., B.P., J.D., and Y.Q. wrote the manuscript; B.P., Y.W., and Y.Q. designed and produced the figures. Y.T., L.H., and Y.Z. provided theoretical support. All authors participated in discussions and commented on the manuscript.

Peer review

Peer review information

Nature Communications thanks the anonymous, reviewer(s) for their contribution to the peer review of this work. A peer review file is available.

Data availability

The training datasets of the 3D-CAE and 3D-CNNs, and the FEM simulation dataset generated in this study have been deposited in the GitHub repository at https://github.com/Bop2000/GAD-MALL , ref. ^⁷² . Source data are provided with this paper.

Code availability

The codes for the workflow of the GAD-MALL method, other state-of-the-art active learning algorithms, finite element methods and its automation pipeline, and the TPMS structure generation algorithm are publicly available in the GitHub repository at https://github.com/Bop2000/GAD-MALL , ref. ^⁷² .

Competing interests

The authors declare no competing interests.

Footnotes

Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

These authors contributed equally: Bo Peng, Ye Wei, Yu Qin.

These authors jointly supervised this work: Ye Wei, Yu Qin, Peng Wen.

Contributor Information

Ye Wei, Email: ed.nehcaa-htwr@iew.ey .

Yu Qin, Email: moc.621@59uyniq .

Peng Wen, Email: nc.ude.auhgnist@gnepnew .

Supplementary information

The online version contains supplementary material available at 10.1038/s41467-023-42415-y.

References

1. Zheng X, et al. Ultralight, ultrastiff mechanical metamaterials. Science (1979) 2014; 344 :1373–1377. [ PubMed ] [ Google Scholar ]

2. Jang D, Meza LR, Greer F, Greer JR. Fabrication and deformation of three-dimensional hollow ceramic nanostructures. Nat. Mater. 2013; 12 :893–898. [ PubMed ] [ Google Scholar ]

3. Meza LR, Das S, Greer JR. Strong, lightweight, and recoverable three-dimensional ceramic nanolattices. Science (1979) 2014; 345 :1322–1326. [ PubMed ] [ Google Scholar ]

4. Li X, Gao H. Smaller and stronger. Nat. Mater. 2016; 15 :373–374. [ PubMed ] [ Google Scholar ]

5. Kadic M, Bückmann T, Stenger N, Thiel M, Wegener M. On the practicability of pentamode mechanical metamaterials. Appl Phys. Lett. 2012; 100 :191901. [ Google Scholar ]

6. Yang T, et al. A damage-tolerant, dual-scale, single-crystalline microlattice in the knobby starfish Protoreaster nodosus. Science (1979) 2022; 375 :647–652. [ PubMed ] [ Google Scholar ]

7. Pham M-S, Liu C, Todd I, Lertthanasarn J. Damage-tolerant architected materials inspired by crystal microstructure. Nature. 2019; 565 :305–311. [ PubMed ] [ Google Scholar ]

8. Li J, Fok L, Yin X, Bartal G, Zhang X. Experimental demonstration of an acoustic magnifying hyperlens. Nat. Mater. 2009; 8 :931–934. [ PubMed ] [ Google Scholar ]

9. Schaedler TA, et al. Ultralight metallic microlattices. Science (1979) 2011; 334 :962–965. [ PubMed ] [ Google Scholar ]

10. Schurig D, et al. Metamaterial electromagnetic cloak at microwave frequencies. Science (1979) 2006; 314 :977–980. [ PubMed ] [ Google Scholar ]

11. Magnus F, et al. Magnetic metamaterial. Nat. Mater. 2008; 7 :295–297. [ PubMed ] [ Google Scholar ]

12. Xia, X., Spadaccini, C. M. & Greer, J. R. Responsive materials architected in space and time. Nat. Rev. Mate.r 10.1038/s41578-022-00450-z (2022) [ PMC free article ] [ PubMed ]

13. Hutmacher DW. Scaffolds in tissue engineering bone and cartilage. Biomaterials. 2000; 21 :2529–2543. [ PubMed ] [ Google Scholar ]

14. Freyman TM, Yannas IV, Gibson LJ. Cellular materials as porous scaffolds for tissue engineering. Prog. Mater. Sci. 2001; 46 :273–282. [ Google Scholar ]

15. Bose S, Vahabzadeh S, Bandyopadhyay A. Bone tissue engineering using 3D printing. Mater. Today. 2013; 16 :496–504. [ Google Scholar ]

16. Do A-V, Khorsand B, Geary SM, Salem AK. 3D printing of scaffolds for tissue regeneration applications. Adv. Health. Mater. 2015; 4 :1742–1762. [ PMC free article ] [ PubMed ] [ Google Scholar ]

17. Zhang M, et al. 3D printing of Haversian bone–mimicking scaffolds for multicellular delivery in bone regeneration. Sci. Adv. 2022; 6 :eaaz6725. [ PMC free article ] [ PubMed ] [ Google Scholar ]

18. Christensen J, Kadic M, Kraft O, Wegener M. Vibrant times for mechanical metamaterials. MRS Commun. 2015; 5 :453–462. [ Google Scholar ]

19. Valdevit L, Jacobsen AJ, Greer JR, Carter WB. Protocols for the optimal design of multi-functional cellular structures: from hypersonics to micro-architected materials. J. Am. Ceram. Soc. 2011; 94 :s15–s34. [ Google Scholar ]

20. Martin P. B., O. S. Topology Optimization: Theory, Methods, and Applications . (Springer, 2003).

21. Wang P, Casadei F, Shan S, Weaver JC, Bertoldi K. Harnessing buckling to design tunable locally resonant acoustic metamaterials. Phys. Rev. Lett. 2014; 113 :14301. [ PubMed ] [ Google Scholar ]

22. Mao, Y., He, Q. & Zhao, X. Designing complex architectured materials with generative adversarial networks. Sci. Adv. 6 , 17 (2020). [ PMC free article ] [ PubMed ]

23. Ma C, et al. Accelerated design and characterization of non-uniform cellular materials via a machine-learning based framework. NPJ Comput. Mater. 2020; 6 :40. [ Google Scholar ]

24. Liu Y, Zhao T, Ju W, Shi S. Materials discovery and design using machine learning. J. Materiomics. 2017; 3 :159–177. [ Google Scholar ]

25. Hanakata PZ, Cubuk ED, Campbell DK, Park HS. Accelerated search and design of stretchable graphene kirigami using machine learning. Phys. Rev. Lett. 2018; 121 :255304. [ PubMed ] [ Google Scholar ]

26. Buehler MJ. Generating 3D architectured nature-inspired materials and granular media using diffusion models based on language cues. Oxf. Open Mater. Sci. 2022; 2 :itac010. [ PMC free article ] [ PubMed ] [ Google Scholar ]

27. Dimas LS, Bratzel GH, Eylon I, Buehler MJ. Tough composites inspired by mineralized natural materials: computation, 3D printing, and testing. Adv. Funct. Mater. 2013; 23 :4629–4638. [ Google Scholar ]

28. Hippalgaonkar, K. et al. Knowledge-integrated machine learning for materials: lessons from gameplaying and robotics. Nat. Rev. Mater. 8 , 1–20 (2023).

29. Lughofer E. Hybrid active learning for reducing the annotation effort of operators in classification systems. Pattern Recognit. 2012; 45 :884–896. [ Google Scholar ]

30. Settles, B. Active learning literature survey. Computer Sciences Technical Report 1648 . (University of Wisconsin–Madison, 2009).

31. Li, B. et al. Computational discovery of microstructured composites with optimal strength-toughness trade-offs. https://arxiv.org/abs/2302.01078 (2023).

32. Erps T, et al. Accelerated discovery of 3D printing materials using data-driven multiobjective optimization. Sci. Adv. 2021; 7 :eabf7435. [ PMC free article ] [ PubMed ] [ Google Scholar ]

33. Yuan, R. et al. Accelerated discovery of large electrostrains in BaTiO3-based piezoelectrics using active learning. Adv. Mater. 30 , 02884 (2018). [ PubMed ]

34. Zhong M, et al. Accelerated discovery of CO2 electrocatalysts using active machine learning. Nature. 2020; 581 :178–183. [ PubMed ] [ Google Scholar ]

35. Koch PN, Simpson TW, Allen JK, Mistree F. Statistical approximations for multidisciplinary design optimization: the problem of size. J. Aircr. 1999; 36 :275–286. [ Google Scholar ]

36. Sanchez-Lengeling B, Aspuru-Guzik A. Inverse molecular design using machine learning: Generative models for matter engineering. Science (1979) 2018; 361 :360–365. [ PubMed ] [ Google Scholar ]

37. Rao Z, et al. Machine learning–enabled high-entropy alloy discovery. Science (1979) 2022; 378 :78–85. [ PubMed ] [ Google Scholar ]

38. Wang X, et al. Topological design and additive manufacturing of porous metals for bone scaffolds and orthopaedic implants: a review. Biomaterials. 2016; 83 :127–141. [ PubMed ] [ Google Scholar ]

39. Yang H, et al. Alloying design of biodegradable zinc as promising bone implants for load-bearing applications. Nat. Commun. 2020; 11 :401. [ PMC free article ] [ PubMed ] [ Google Scholar ]

40. Bidan CM, et al. Geometry as a factor for tissue growth: towards shape optimization of tissue engineering scaffolds. Adv. Health. Mater. 2013; 2 :186–194. [ PubMed ] [ Google Scholar ]

41. Downing D, Jones A, Brandt M, Leary M. Increased efficiency gyroid structures by tailored material distribution. Mater. Des. 2021; 197 :109096. [ Google Scholar ]

42. Lim J, You C, Dayyani I. Multi-objective topology optimization and structural analysis of periodic spaceframe structures. Mater. Des. 2020; 190 :108552. [ Google Scholar ]

43. Wu J, Aage N, Westermann R, Sigmund O. Infill optimization for additive manufacturing—approaching bone-like porous structures. IEEE Trans. Vis. Comput Graph. 2017; 24 :1127–1140. [ PubMed ] [ Google Scholar ]

44. Li D, et al. Optimal design and modeling of gyroid-based functionally graded cellular structures for additive manufacturing. Computer-Aided Design. 2018; 104 :87–99. [ Google Scholar ]

45. Ehrig S, et al. Surface tension determines tissue shape and growth kinetics. Sci. Adv. 2019; 5 :eaav9394. [ PMC free article ] [ PubMed ] [ Google Scholar ]

46. Cai Z, Liu Z, Hu X, Kuang H, Zhai J. The effect of porosity on the mechanical properties of 3D-printed triply periodic minimal surface (TPMS) bioscaffold. Biodesign Manuf. 2019; 2 :242–255. [ Google Scholar ]

47. Qin Y, et al. Processing optimization, mechanical properties, corrosion behavior and cytocompatibility of additively manufactured Zn-0.7Li biodegradable metals. Acta Biomater. 2022; 142 :388–401. [ PubMed ] [ Google Scholar ]

48. Zhao D, et al. Material–structure–function integrated additive manufacturing of degradable metallic bone implants for load-bearing applications. Adv. Funct. Mater. 2023; 33 :2213128. [ Google Scholar ]

49. Yánez A, Cuadrado A, Martel O, Afonso H, Monopoli D. Gyroid porous titanium structures: a versatile solution to be used as scaffolds in bone defect reconstruction. Mater. Des. 2018; 140 :21–29. [ Google Scholar ]

50. Meng, F., Huang, K., Li, H. & Wu, Q. Class activation map generation by representative class selection and multi-layer feature fusion. Preprint at 10.48550/ARXIV.1901.07683 (2019).

51. Deshpande VS, Ashby MF, Fleck NA. Foam topology: bending versus stretching dominated architectures. Acta Mater. 2001; 49 :1035–1040. [ Google Scholar ]

52. Bauer J, et al. Nanolattices: an emerging class of mechanical metamaterials. Adv. Mater. 2017; 29 :1701850. [ PubMed ] [ Google Scholar ]

53. Krizhevsky A, Sutskever I, Hinton GE. ImageNet classification with deep convolutional neural networks. Commun. ACM. 2017; 60 :84–90. [ Google Scholar ]

54. Alzubaidi L, et al. Review of deep learning: concepts, CNN architectures, challenges, applications, future directions. J. Big Data. 2021; 8 :53. [ PMC free article ] [ PubMed ] [ Google Scholar ]

55. Russell, S. J. & Norvig, P. Artificial Intelligence: A Modern Approach . (Malaysia; Pearson Education Limited, 2016).

56. Donnay G, Pawson DL. X-ray diffraction studies of echinoderm plates. Science (1979) 1969; 166 :1147–1150. [ PubMed ] [ Google Scholar ]

57. Winter B, et al. Coexistence of both gyroid chiralities in individual butterfly wing scales of Callophrys rubi. Proc. Natl Acad. Sci. USA. 2015; 112 :12911–12916. [ PMC free article ] [ PubMed ] [ Google Scholar ]

58. Saranathan V, et al. Structure, function, and self-assembly of single network gyroid (I 4132) photonic crystals in butterfly wing scales. Proc. Natl Acad. Sci. USA. 2010; 107 :11676–11681. [ PMC free article ] [ PubMed ] [ Google Scholar ]

59. Wilts BD, Michielsen K, de Raedt H, Stavenga DG. Iridescence and spectral filtering of the gyroid-type photonic crystals in Parides sesostris wing scales. Interface Focus. 2012; 2 :681–687. [ PMC free article ] [ PubMed ] [ Google Scholar ]

60. Michielsen K, Stavenga DG. Gyroid cuticular structures in butterfly wing scales: biological photonic crystals. J. R. Soc. Interface. 2008; 5 :85–94. [ PMC free article ] [ PubMed ] [ Google Scholar ]

61. Seago AE, Brady P, Vigneron J-P, Schultz TD. Gold bugs and beyond: a review of iridescence and structural colour mechanisms in beetles (Coleoptera) J. R. Soc. Interface. 2009; 6 :S165–S184. [ PMC free article ] [ PubMed ] [ Google Scholar ]

62. Galusha JW, Richey LR, Gardner JS, Cha JN, Bartl MH. Discovery of a diamond-based photonic crystal structure in beetle scales. Phys. Rev. E. 2008; 77 :50904. [ PubMed ] [ Google Scholar ]

63. Almsherqi Z, Margadant F, Deng Y. A look through ‘lens’ cubic mitochondria. Interface Focus. 2012; 2 :539–545. [ PMC free article ] [ PubMed ] [ Google Scholar ]

64. Rajagopalan S, Robb RA. Schwarz meets Schwann: design and fabrication of biomorphic and durataxic tissue engineering scaffolds. Med. Image Anal. 2006; 10 :693–712. [ PubMed ] [ Google Scholar ]

65. Yousaf MN, Houseman BT, Mrksich M. Using electroactive substrates to pattern the attachment of two different cell populations. Proc. Natl Acad. Sci. USA. 2001; 98 :5992–5996. [ PMC free article ] [ PubMed ] [ Google Scholar ]

66. Noireaux V, et al. Growing an actin gel on spherical surfaces. Biophys. J. 2000; 78 :1643–1654. [ PMC free article ] [ PubMed ] [ Google Scholar ]

67. Spalazzi JP, Dionisio KL, Jiang J, Lu HH. Osteoblast and chondrocyte interactions during coculture on scaffolds. IEEE Eng. Med. Biol. Mag. 2003; 22 :27–34. [ PubMed ] [ Google Scholar ]

68. Al-Ketan O, Abu Al-Rub RK. MSLattice: a free software for generating uniform and graded lattices based on triply periodic minimal surfaces. Mater. Des. Process. Commun. 2021; 3 :e205. [ Google Scholar ]

69. Gabbrielli R, Turner IG, Bowen CR. Development of modelling methods for materials to be used as bone substitutes. in. Key Eng. Mater. 2008; 361 :903–906. [ Google Scholar ]

70. Smith, M. ABAQUS/Standard User’s Manual, Version 6.9 . (Dassault Systèmes Simulia Corp, 2009).

71. Abadi, M. et al. Tensorflow: large-scale machine learning on heterogeneous distributed systems. https://arxiv.org/abs/1603.04467 (2016).

72. Bo Peng et al. Machine learning-enabled constrained multi-objective design of architected materials. GAD-MALL 10.5281/zenodo.8286910 (2023). [ PMC free article ] [ PubMed ]

Articles from Nature Communications are provided here courtesy of Nature Publishing Group