Dynamic fracture of a bicontinuously nanostructured copolymer: A deep-learning analysis of big-data-generating experiment
Source abstract
Abstract
Here, we report measurements of detailed dynamic cohesive properties (DCPs) beyond the dynamic fracture toughness of a bicontinuously nanostructured copolymer, polyurea, under an extremely loading rate, from deep-learning analyses of a dynamic big-data-generating experiment. We first describe a new Dynamic Line-Image Shearing Interferometer (DL-ISI), which uses a streak camera to record optical fringes of displacement-gradient vs time profile along a line on sample's rear surface. This system enables us to detect crack initiation and growth processes in plate-impact experiments. Then, we present a convolutional neural network (CNN) based deep-learning framework, trained by extensive finite-element simulations, that inversely determines the accurate DCPs from the DL-ISI fringe images. For the measurements, plate-impact experiments were performed on a set of samples with a mid-plane crack. A Conditional Generative Adversarial Networks (cGAN) was employed first to reconstruct missing DL-ISI fringes with recorded partial DL-ISI fringes. Then, the CNN and a correlation method were applied to the fully reconstructed fringes to get the dynamic fracture toughness, 12.1kJ/m^2, cohesive strength, 302 MPa, and maximum cohesive separation, 80.5 um, within 0.4%, 2.7%, and 2.2% differences, respectively. For the first time, the DCPs of polyurea have been successfully obtained by the DL-ISI with the pre-trained CNN and correlation analyses of cGAN-reconstructed data sets. The dynamic cohesive strength is found to be nearly three times higher than the dynamic-failure-initiation strength. The high dynamic fracture toughness is found to stem from both high dynamic cohesive strength and high ductility of the dynamic cohesive separation.
Source: openaire · Quality: candidate unverified · Source record ↗
Research context
OpenAlex topics: Probabilistic and Robust Engineering Design · Machine Learning in Materials Science · Rheology and Fluid Dynamics Studies
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (62)
Show source-provided references
1. Tensorflow: A system for large-scale machine learning
2. Ashby · 2012
3. The mathematical theory of equilibrium cracks in brittle fracture10.1016/S0065-2156(08)70121-2 ↗
4. Bojarski, M., Del Testa, D., Dworakowski, D., Firner, B., Flepp, B., Goyal, P., Jackel, L.D., Monfort, M., Muller, U., Zhang, J., 2016. End to end learning for self-driving cars. arXiv preprint arXiv:1604.07316.
5. Testing, experiments and properties of HSREP: pressure and strain-rate sensitivity of an elastomer: (1) pressure-shear plate impact experiments; (2) constitutive modeling
6. Structure-property relationships and melt rheology of segmented, non-chain extended polyureas: effect of soft segment molecular weight10.1016/j.polymer.2006.10.029 ↗
7. Yielding of steel sheets containing slits10.1016/0022-5096(60)90013-2 ↗
8. Espinosa · 1992
9. Characterize traction-separation relation and interfacial imperfections by data-driven machine learning models10.1038/s41598-021-93852-y ↗
10. Fernández-Godino, M.G., Park, C., Kim, N.H., Haftka, R.T., 2016. Review of multi-fidelity models. arXiv preprint arXiv:1609.07196.
11. Crack propagation in an elastic solid subjected to general loading—I. Constant rate of extension10.1016/0022-5096(72)90006-3 ↗
12. Crack propagation in an elastic solid subjected to general loading—III. Stress wave loading10.1016/0022-5096(73)90029-X ↗
13. Freund · 1998
14. A first-order perturbation analysis of crack trapping by arrays of obstacles10.1115/1.3176178 ↗
15. Goodfellow, I.J., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., Bengio, Y., 2014. Generative adversarial networks. arXiv preprint arXiv:1406.2661.
16. Material-model-based determination of the shock-hugoniot relations in nanosegregated polyurea10.1007/s11665-013-0769-7 ↗
17. Experimental and computational study of the shearing resistance of polyurea at high pressures and high strain rates10.1007/s11665-014-1316-x ↗
18. Grunschel · 2009
19. Cohesive-zone laws for void growth - I. Experimental field projection of crack-tip crazing in glassy polymers10.1016/j.jmps.2009.04.003 ↗
20. Extraction of cohesive-zone laws from elastic far-fields of a cohesive crack tip: a field projection method10.1016/S0022-5096(03)00023-1 ↗
21. Using deep learning to predict fracture patterns in crystalline solids10.1016/j.matt.2020.04.019 ↗
22. Isola, P., Zhu, J.Y., Zhou, T., Efros, A.A., 2016. Image-to-image translation with conditional adversarial networks. arXiv preprint arXiv:1611.07004.10.1109/CVPR.2017.632 ↗
23. Dynamic tensile strength of polyurea-bonded steel/E-glass composite joints10.1080/01694243.2012.705545 ↗
24. Jin · 2022 · 45
25. Jin, H., Machnicki, C., Hegarty, J., Kim, K.S., 2022b. Nanophase deformation-fragmentation and self-reorganization: Sources of nanostructured copolymer's toughness. In Preparation.
26. Physics-informed machine learning10.1038/s42254-021-00314-5 ↗
27. Dynamic fracture-toughness testing of a hierarchically nano-structured solid
28. Kim · 1980
29. A combined normal-and transverse-displacement interferometer with an application to impact of y-cut quartz10.1063/1.323448 ↗
30. Adhesion, slip, cohesive zones and energy fluxes for elastic spheres in contact10.1016/S0022-5096(97)00070-7 ↗
31. Kingma, D.P., Ba, J., 2014. Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980.
32. ImageNet classification with deep convolutional neural networks
33. Optical alignment of impact faces for plate impact experiments10.1063/1.323734 ↗
34. Deep learning10.1038/nature14539 ↗
35. Micromechanics of friction: effects of nanometre-scale roughness
36. Micromechanics of rough surface adhesion: a homogenized projection method10.1016/S0894-9166(09)60288-3 ↗
37. Extraction of mechanical properties of materials through deep learning from instrumented indentation10.1073/pnas.1922210117 ↗
38. A composite neural network that learns from multi-fidelity data: Application to function approximation and inverse PDE problems10.1016/j.jcp.2019.109020 ↗
39. Mirza, M., Osindero, S., 2014. Conditional generative adversarial nets. arXiv preprint arXiv:1411.1784.
40. A deep learning approach to the inverse problem of modulus identification in elasticity10.1557/s43577-020-00006-y ↗
41. Simulation trained CNN for accurate embedded crack length, location, and orientation prediction from ultrasound measurements10.1016/j.ijsolstr.2022.111521 ↗
42. Deep face recognition
43. An experimental investigation into dynamic fracture.1. Crack initiation and arrest10.1007/BF00963460 ↗
44. Ravichandran · 1987
45. Dynamic fracture under plane-wave loading10.1007/BF00960599 ↗
46. Rezaei, M., Harmuth, K., Gierke, W., Kellermeier, T., Fischer, M., Yang, H., Meinel, C., 2017. Conditional adversarial network for semantic segmentation of brain tumor. arXiv preprint arXiv:1708.05227.10.1007/978-3-319-75238-9_21 ↗
47. Three-dimensional perturbation solution for a dynamic planar crack moving unsteadily in a model elastic solid10.1016/0022-5096(94)90044-2 ↗
48. Ronneberger, O., Fischer, P., Brox, T., 2015. U-Net: convolutional networks for biomedical image segmentation. arXiv preprint arXiv:1505.04597.10.1007/978-3-319-24574-4_28 ↗
49. Inverse molecular design using machine learning: generative models for matter engineering10.1126/science.aat2663 ↗
50. Deep elastic strain engineering of bandgap through machine learning (vol 116, pg 4117, 2019)
51. Identification of the interfacial cohesive law parameters of FRP strips externally bonded to concrete using machine learning techniques10.1016/j.engfracmech.2021.107643 ↗
52. A coherent gradient sensor for crack tip deformation measurements - analysis and experimental results10.1007/BF00036631 ↗
53. Effect of strain-dependent cohesive zone model on predictions of crack growth resistance10.1016/0020-7683(95)00261-8 ↗
54. Molecular recognition in poly(epsilon-caprolactone)-based thermoplastic elastomers10.1021/bm060688t ↗
55. Void nucleation by inclusion debonding in a crystal matrix10.1088/0965-0393/1/2/001 ↗
56. Deep learning model to predict complex stress and strain fields in hierarchical composites10.1126/sciadv.abd7416 ↗
57. End-to-end deep learning method to predict complete strain and stress tensors for complex hierarchical composite microstructures10.1016/j.jmps.2021.104506 ↗
58. Dynamic tensile strength of polyurea10.1557/jmr.2011.405 ↗
59. Analyses of internal structures and defects in materials using physics-informed neural networks10.1126/sciadv.abk0644 ↗
60. Zhang, E., Yin, M., Karniadakis, G.E., 2020. Physics-informed neural networks for nonhomogeneous material identification in elasticity imaging. arXiv preprint arXiv:2009.04525.
61. Shear band propagation from a crack tip10.1016/j.jmps.2003.09.027 ↗
62. Shear band propagation from a crack tip subjected to mode II shear wave loading10.1016/j.ijsolstr.2006.09.030 ↗