Model-free data-driven identification algorithm enhanced by local manifold learning. (English) Zbl 1514.74095
Summary: Reliable and consistent material data identification is essential to the data-driven computational mechanics paradigm. This paper presents a generalized data-driven identification (DDI) approach to constructing material databases of high quality. We integrate the locally convex reconstruction method into DDI to formulate the local-convexity DDI (LCDDI) method. The LCDDI method can learn the local structures of material data and thus produce structure-informed optimal material data points for solving stresses with given strains. The effectiveness of the LCDDI method at addressing large acquisitions of material data with a complex heterogeneous strain field is demonstrated through two numerical experiments: a perforated elastic plate and a center-holed elasto-plastic plate. Convergence studies show that results using the LCDDI method are dramatically improved. We further explain how the LCDDI method manages to accurately identify mechanical stress fields and a high-fidelity material database under the condition of imbalanced distribution of elastic and plastic deformation. Discussion of the LCDDI method in regards to the oversampling issue, the capability of full-domain analysis, and importance sampling is given. Finally, we conclude that the LCDDI method can extract a vast amount of material data points with improved quality from full-field strain measurements, and can serve as a more reliable technique for material data acquisition.
Keywords:
material data acquisition; material data structure; local-convex data-driven identification; material database quality; perforated elastic plate; center-holed elasto-plastic plateReferences:
| [1] | Pierron, F.; Grediac, M., Towards material testing 2.0. a review of test design for identification of constitutive parameters from full-field measurements, Strain, 57, 1 (2021) · doi:10.1111/str.12370 |
| [2] | Sutton MA, Orteu JJ, Schreier H (2009) Image correlation for shape, motion and deformation measurements: basic concepts, theory and applications. Springer Science and Business Media |
| [3] | He Q, Laurence DW, Lee C-H, Chen J-S (2020) Manifold learning based data-driven modeling for soft biological tissues. J Biomech 117:110124 |
| [4] | Bishara D, Xie Y, Liu WK, Li S (2022) A state-of-the-art review on machine learning-based multiscale modeling, simulation, homogenization and design of materials. Arch Comput Methods Eng |
| [5] | Bessa, MA; Bostanabad, R.; Liu, Z.; Hu, A.; Apley, DW; Brinson, C.; Chen, W.; Liu, WK; Countering the curse of dimensionality, A framework for data-driven analysis of materials under uncertainty, Comput Methods Appl Mech Eng, 320, 633-667 (2017) · Zbl 1439.74014 · doi:10.1016/j.cma.2017.03.037 |
| [6] | Mozaffar, M.; Bostanabad, R.; Chen, W.; Ehmann, K.; Cao, J.; Bessa, MA, Deep learning predicts path-dependent plasticity, Proc Natl Acad Sci, 116, 52, 26414-26420 (2019) · doi:10.1073/pnas.1911815116 |
| [7] | He X, Chen J-S (2022) Thermodynamically consistent machine-learned internal state variable approach for data-driven modeling of path-dependent materials. Comput Methods Appl Mech Eng 402:115348 · Zbl 1507.74007 |
| [8] | Liu, D.; Hang Yang, KI; Elkhodary, ST; Liu, WK; Guo, X., Mechanistically informed data-driven modeling of cyclic plasticity via artificial neural networks, Comput Methods Appl Mech Eng, 393 (2022) · Zbl 1507.74082 · doi:10.1016/j.cma.2022.114766 |
| [9] | Heider, Y.; Wang, K.; Sun, WC, So(3)-invariance of informed-graph-based deep neural network for anisotropic elastoplastic materials, Comput Methods Appl Mech Eng, 363 (2020) · Zbl 1436.74012 · doi:10.1016/j.cma.2020.112875 |
| [10] | Zeliang Liu, CTW; Koishi, M., A deep material network for multiscale topology learning and accelerated nonlinear modeling of heterogeneous materials, Comput Methods Appl Mech Eng, 345, 1138-1168 (2019) · Zbl 1440.74340 · doi:10.1016/j.cma.2018.09.020 |
| [11] | Liu, Z.; Wu, CT, Exploring the 3d architectures of deep material network in data-driven multiscale mechanics, J Mech Phys Solids, 127, 20-46 (2019) · Zbl 1477.74006 · doi:10.1016/j.jmps.2019.03.004 |
| [12] | Kirchdoerfer, T.; Ortiz, M., Data-driven computational mechanics, Comput Methods Appl Mech Eng, 304, 81-101 (2016) · Zbl 1425.74503 · doi:10.1016/j.cma.2016.02.001 |
| [13] | Conti, S.; Müller, S.; Ortiz, M., Data-driven problems in elasticity, Arch Ration Mech Anal, 229, 1, 79-123 (2018) · Zbl 1402.35276 · doi:10.1007/s00205-017-1214-0 |
| [14] | Kirchdoerfer, T.; Ortiz, M., Data-driven computing in dynamics, Int J Numer Meth Eng, 113, 11, 1697-1710 (2018) · Zbl 07868547 · doi:10.1002/nme.5716 |
| [15] | Nguyen, LTK; Keip, MA, A data-driven approach to nonlinear elasticity, Comput Struct, 194, 97-115 (2018) · doi:10.1016/j.compstruc.2017.07.031 |
| [16] | Yang, J.; Rui, X.; Heng, H.; Huang, Q.; Huang, W., Structural-genome-driven computing for composite structures, Compos Struct, 215, 446-453 (2019) · doi:10.1016/j.compstruct.2019.02.064 |
| [17] | Eggersmann, R.; Kirchdoerfer, T.; Reese, S.; Stainier, L.; Ortiz, M., Model-free data-driven inelasticity, Comput Methods Appl Mech Eng, 350, 81-99 (2019) · Zbl 1441.74048 · doi:10.1016/j.cma.2019.02.016 |
| [18] | He, Q.; Chen, J-S, A physics-constrained data-driven approach based on locally convex reconstruction for noisy database, Comput Methods Appl Mech Eng, 363 (2020) · Zbl 1436.62725 · doi:10.1016/j.cma.2019.112791 |
| [19] | Eggersmann, R.; Stainier, L.; Ortiz, M.; Reese, S., Model-free data-driven computational mechanics enhanced by tensor voting, Comput Methods Appl Mech Eng, 373 (2021) · Zbl 1506.74492 · doi:10.1016/j.cma.2020.113499 |
| [20] | Rui, X.; Yang, J.; Yan, W.; Huang, Q.; Giunta, G.; Belouettar, S.; Zahrouni, H.; Zineb, TB; Heng, H., Data-driven multiscale finite element method: From concurrence to separation, Comput Methods Appl Mech Eng, 363 (2020) · Zbl 1436.74077 · doi:10.1016/j.cma.2020.112893 |
| [21] | Karapiperis, K.; Stainier, L.; Ortiz, M.; Andrade, JE, Data-driven multiscale modeling in mechanics, J Mech Phys Solids, 147 (2021) · doi:10.1016/j.jmps.2020.104239 |
| [22] | Mora-Macías, J.; Ayensa-Jiménez, J.; Reina-Romo, E.; Doweidar, MH; Domínguez, J.; Doblaré, M.; Sanz-Herrera, JA, A multiscale data-driven approach for bone tissue biomechanics, Comput Methods Appl Mech Eng, 368 (2020) · Zbl 1506.74209 · doi:10.1016/j.cma.2020.113136 |
| [23] | Cheng, Yu; Kafka, OL; Liu, WK, Multiresolution clustering analysis for efficient modeling of hierarchical material systems, Comput Mech, 67, 5, 1293-1306 (2021) · Zbl 1468.74092 · doi:10.1007/s00466-021-01982-x |
| [24] | Kafka, OL; Jones, KK; Cheng, Yu; Cheng, P.; Liu, WK, Image-based multiscale modeling with spatially varying microstructures from experiments: Demonstration with additively manufactured metal in fatigue and fracture, J Mech Phys Solids, 150 (2021) · doi:10.1016/j.jmps.2021.104350 |
| [25] | Leygue, A.; Coret, M.; Réthoré, J.; Stainier, L.; Verron, E., Data-based derivation of material response, Comput Methods Appl Mech Eng, 331, 184-196 (2018) · Zbl 1439.74050 · doi:10.1016/j.cma.2017.11.013 |
| [26] | Leygue, A.; Seghir, R.; Réthoré, J.; Coret, M.; Verron, E.; Stainier, L., Non-parametric material state field extraction from full field measurements, Comput Mech, 64, 2, 501-509 (2019) · Zbl 1464.74023 · doi:10.1007/s00466-019-01725-z |
| [27] | Valdés-Alonzo G, Binetruy C, Eck B, García-González A, Leygue A (2021) Phase distribution and properties identification of heterogeneous materials: a data-driven approach. Comput Methods Appl Mech Eng 390:114354 · Zbl 1507.74104 |
| [28] | Dalémat, M.; Coret, M.; Leygue, A.; Verron, E., Measuring stress field without constitutive equation, Mech Mater, 136 (2019) · doi:10.1016/j.mechmat.2019.103087 |
| [29] | Tung-Huan, S.; Nian-Hu, L.; Chen, C-H; Chen, C-S, Full-field stress and strain measurements revealing energy dissipation characteristics in martensitic band of cu-al-mn shape memory alloy, Mater Today Commun, 24 (2020) · doi:10.1016/j.mtcomm.2020.101321 |
| [30] | Stainier, L.; Leygue, A.; Ortiz, M., Model-free data-driven methods in mechanics: material data identification and solvers, Comput Mech, 64, 2, 381-393 (2019) · Zbl 1470.74077 · doi:10.1007/s00466-019-01731-1 |
| [31] | Kirchdoerfer, T.; Ortiz, M., Data driven computing with noisy material data sets, Comput Methods Appl Mech Eng, 326, 622-641 (2017) · Zbl 1464.62282 · doi:10.1016/j.cma.2017.07.039 |
| [32] | Dalémat M, Coret M, Leygue A, Verron E (2019) Reliability of the data-driven identification algorithm with respect to incomplete input data, 1st edn. Routledge and CRC Press, London, pp 311-316 |
| [33] | John A (2007) Lee and Michel Verleysen. Nonlinear Dimensionality Reduction, Springer Science and Business Media · Zbl 1128.68024 |
| [34] | Roweis, ST; Saul, LK, Nonlinear dimensionality reduction by locally linear embedding, Science, 290, 5500, 2323 (2000) · doi:10.1126/science.290.5500.2323 |
| [35] | Saul, LK; Roweis, ST, Think globally, fit locally: unsupervised learning of low dimensional manifolds, J Mach Learn Res, 4, null, 119-155 (2003) · Zbl 1093.68089 |
| [36] | He, X.; He, Q.; Chen, J-S; Sinha, U.; Sinha, S., Physics-constrained local convexity data-driven modeling of anisotropic nonlinear elastic solids, Data-Centric Eng, 1, E19 (2020) · doi:10.1017/dce.2020.20 |
| [37] | Lawson, CL; Hanson, RJ, Solving least squares problems. Classics in applied mathematics, Socr Ind Appl Math (1995) · Zbl 0860.65029 · doi:10.1137/1.9781611971217 |
| [38] | Boyd, S.; Vandenberghe, L., Convex optimization (2004), Cambridge: Cambridge University Press, Cambridge · Zbl 1058.90049 · doi:10.1017/CBO9780511804441 |
| [39] | Dalemat M (2019) A successful investigation for the model-free identification of the material response : a datadriven approach for elastomer membranes. Thesis, École centrale de Nantes |
| [40] | Kanno, Y., Mixed-integer programming formulation of a data-driven solver in computational elasticity, Optim Lett, 13, 7, 1505-1514 (2019) · Zbl 1430.90432 · doi:10.1007/s11590-019-01409-w |
| [41] | He, X.; He, Q.; Chen, J-S, Deep autoencoders for physics-constrained data-driven nonlinear materials modeling, Comput Methods Appl Mech Eng, 385 (2021) · Zbl 1502.74109 · doi:10.1016/j.cma.2021.114034 |
| [42] | Eggersmann, R.; Stainier, L.; Ortiz, M.; Reese, S., Efficient data structures for model-free data-driven computational mechanics, Comput Methods Appl Mech Eng, 382 (2021) · Zbl 1506.74002 · doi:10.1016/j.cma.2021.113855 |
| [43] | Tung-Huan, S.; Nian-Hu, L.; Chen, C-H; Chen, C-S, On the decrease in transformation stress in a bicrystal cu-al-mn shape-memory alloy during cyclic compressive deformation, Materials, 14, 16, 4439 (2021) · doi:10.3390/ma14164439 |
| [44] | Hoerig, C.; Ghaboussi, J.; Insana, MF, Data-driven elasticity imaging using cartesian neural network constitutive models and the autoprogressive method, IEEE Trans Med Imaging, 38, 5, 1150-1160 (2019) · doi:10.1109/TMI.2018.2879495 |
| [45] | Hoerig, C.; Ghaboussi, J.; Insana, MF, Physics-guided machine learning for 3-d quantitative quasi-static elasticity imaging, Phys Med Biol, 65, 6 (2020) · doi:10.1088/1361-6560/ab7505 |
| [46] | Ronneberger O, Fischer P, Brox T (2015) U-net: convolutional networks for biomedical image segmentation. In: Navab N, Hornegger J, Wells WM, Frangi AF (eds), Medical image computing and computer-assisted intervention—MICCAI 2015, pp 234-241. Springer International Publishing |
| [47] | Hoerl, AE; Kennard, RW, Ridge regression: biased estimation for nonorthogonal problems, Technometrics, 12, 1, 55-67 (1970) · Zbl 0202.17205 · doi:10.1080/00401706.1970.10488634 |
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.
