×

CPINet: parameter identification of path-dependent constitutive model with automatic denoising based on CNN-LSTM. (English) Zbl 1478.74013

Summary: Based on convolutional neural network (CNN) and improved long short-term memory (LSTM) neural network, a deep learning model CPINet is proposed for instant and accurate identification of path-dependent constitutive model parameters with excellent denoising performance. The elastic-plastic constitutive model with isotropic hardening is taken as an example for illustration. The results show that the CPINet can capture the intricate relationship between the strain field sequence and the non-temporal features (loading sequence and geometry dimensions) to identify constitutive parameters instantly and accurately. The denoising analysis revealed that the denoising processing and strain feature extraction of CNN provides excellent denoising ability to CPINet. Finally, the CPINet is validated by comparing the identified constitutive parameters of 6061 aluminum alloy with CPINet and finite element model updating method. To our knowledge, this is the first study that demonstrates the feasibility and considerable potential of using a deep learning technique to instantly and accurately identify constitutive parameters.

MSC:

74C05 Small-strain, rate-independent theories of plasticity (including rigid-plastic and elasto-plastic materials)
74A20 Theory of constitutive functions in solid mechanics
74S99 Numerical and other methods in solid mechanics
92B20 Neural networks for/in biological studies, artificial life and related topics
PDF BibTeX XML Cite
Full Text: DOI

References:

[1] Abueidda, D. W.; Koric, S.; Sobh, N. A., Topology optimization of 2D structures with nonlinearities using deep learning, Comput. Struct., 237, 106283 (2020)
[2] Abueidda, D. W.; Koric, S.; Sobh, N. A.; Sehitoglu, H., Deep learning for plasticity and thermo-viscoplasticity, Int. J. Plast., 136, 102852 (2021)
[3] Aswendt, P.; Schmidt, C. D.; Zielke, D.; Schubert, S., ESPI solution for non-contacting MEMS-on-wafer testing, Opt Laser. Eng., 40, 501-515 (2003)
[4] Avril, S.; Bonnet, M.; Bretelle, A. S.; Grédiac, M.; Hild, F.; Ienny, P.; Latourte, F.; Lemosse, D.; Pagano, S.; Pagnacco, E.; Pierron, F., Overview of identification methods of mechanical parameters based on full-field measurements, Exp. Mech., 48, 4, 381-402 (2008)
[5] Bai, R.; Wei, Y.; Lei, Z.; Jiang, H.; Tao, W.; Yan, C.; Li, X., Local zone-wise elastic-plastic constitutive parameters of Laser-welded aluminium alloy 6061 using digital image correlation, Opt Laser. Eng., 101, 28-34 (2018)
[6] Bai, R.; Jiang, H.; Lei, Z.; Liu, D.; Yang, Chen; Yan, C.; Tao, W.; Chu, Q., Virtual field method for identifying elastic-plastic constitutive parameters of aluminum alloy laser welding considering kinematic hardening, Opt Laser. Eng., 110, 122-131 (2018)
[7] Bessa, M. A.; Bostanabad, R.; Liu, Z.; Hu, A.; Daniel, W. A.; Brinson, C.; Chen, W.; Liu, W. K., A framework for data-driven analysis of materials under uncertainty: countering the curse of dimensionality, Comput. Methods Appl. Mech. Eng., 320, 633-667 (2017) · Zbl 1439.74014
[8] Boureau, Y. L.; Ponce, J.; LeCun, Y., A theoretical analysis of feature pooling in visual recognition, ICML, 111-118 (2010)
[9] Bresolin, F. L.; Vassoler, J. M., A numerical study of the constitutive characterization of thermoplastic materials submitted to finite strain, Int. J. Solid Struct., 206, 456-471 (2020)
[10] Cha, Y.; Wooram; Choi, W., Deep learning-based crack damage detection using convolutional neural networks, Comput. Aided Civ. Infrastruct. Eng., 32, 361-378 (2017)
[11] Chen, F.; Luo, W. D.; Dale, M.; Petniunas, A.; Harwood, P.; Brown, G. M., High-speed ESPI and related techniques: overview and its application in the automotive industry, Opt Laser. Eng., 40, 459-485 (2003)
[12] Claire, D.; Hild, F.; Roux, S., A finite element formulation to identify damage fields: the equilibrium gap method, Int. J. Numer. Methods Eng., 61, 189-208 (2004) · Zbl 1075.74641
[13] Eberhart, R.; Kennedy, J., A new optimizer using particle swarm theory, Proc 6th Int Symp Micro Machine Human Science, 39-43 (1995)
[14] Florentin, E.; Lubineau, G., Identification of the parameters of an elastic material model using the constitutive equation gap method, Comput. Mech., 46, 521-531 (2010) · Zbl 1358.74058
[15] Haddadi, H.; Belhabib, S., Improving the characterization of a hardening law using digital image correlation over an enhanced heterogeneous tensile test, Int. J. Mech. Sci., 62, 47-56 (2012)
[16] Hochreiter, S.; Schmidhuber, J., Long short-term memory, Neural Comput., 9, 1735-1780 (1997)
[18] Hu, Y.; Liu, F.; Zhu, W.; Zhu, J., Thermally coupled constitutive relations of thermoelastic materials and determination of their material constants based on digital image correlation with a laser engraved speckle pattern, Mech. Mater., 121, 10-20 (2018)
[19] Ioffe, S.; Szegedy, C., Batch normalization: accelerating deep network training by reducing internal covariate shift, J. Mach. Learn. Res., 37, 448-456 (2015)
[20] Jain, V.; Seung, S., Natural image denoising with convolutional networks, NIPS (News Physiol. Sci.), 8, 769-776 (2008)
[21] Jia, F.; Lei, Y.; Lu, N.; Xing, S., Deep normalized convolutional neural network for imbalanced fault classification of machinery and its understanding via visualization, Mech. Syst. Signal Process., 110, 349-367 (2018)
[22] Jiang, X.; Wang, H.; Li, Y.; Mo, K., Machine Learning based parameter tuning strategy for MMC based topology optimization, Adv EngSoftw, 149, 102841 (2020)
[23] Kallioras, N. A.; Kazakis, G.; Lagaros, N. D., Accelerated topology optimization by means of deep learning, Struct Multidiscip O, 62, 1185-1212 (2020)
[24] Kertész, G.; Szénási, S.; Vámossy, Z., Comparative analysis of image projection-based descriptors in Siamese neural networks, Adv. Eng. Software, 154, 102963 (2021)
[25] Kingma, DP; Ba, J., Adam: a method for stochastic optimization (2014), arXiv preprint arXiv:1412.6980
[26] Krizhevsky, A.; Sutskever, I.; Hinton, G., ImageNet classification with deep convolutional neural networks, NIPS (News Physiol. Sci.), 1106-1114 (2012)
[27] Latourte, F.; Chrysochoos, A.; Pagano, S.; Wattrisse, B., Elastoplastic behavior identification for heterogeneous loadings and materials, Exp. Mech., 48, 435-449 (2008)
[28] Lefkimmiatis, S., Universal denoising networks: a novel CNN-based network architecture for image denoising (2017), arXiv preprint arXiv:1711.07807
[29] Li, Y.; Li, S.; Chen, Y.; Han, G., Constitutive parameters identification based on dic assisted thermo-mechanical tensile test for hot stamping of boron steel, J. Mater. Process. Technol., 271, 429-443 (2019)
[30] Maas, A. L.; Hannun, A. Y.; Ng, A. Y., Rectifier nonlinearities improve neural network acoustic models, Proc ICML, 30 (2013)
[31] Martins, J. M.P.; Andrade-Campos, A.; Thuillier, S., Comparison of inverse identification strategies for constitutive mechanical models using full-field measurements, Int. J. Mech. Sci., 145, 330-345 (2018)
[32] Mozaffar, M.; Bostanabad, R.; Chen, W.; Ehmann, K.; Bessa, M. A., Deep learning predicts path-dependent plasticity, Proc. Natl. Acad. Sci. U.S.A., 116, 26414-26420 (2019)
[33] Murugan, P.; Durairaj, S., Regularization and optimization strategies in deep convolutional neural network (2017), arXiv preprint. arXiv: 1712.04711
[34] Nguyen-Thanh, V. M.; Zhuang, X.; Rabczuk, T., A deep energy method for finite deformation hyperelasticity, Eur. J. Mech. Solid., 80, 103874 (2020) · Zbl 1472.74213
[35] Périé, J. N.; Leclerc, H.; Roux, S.; Hild, F., Digital image correlation and biaxial test on composite material for anisotropic damage law identification, Int. J. Solid Struct., 46, 2388-2396 (2009) · Zbl 1217.74004
[36] Prates, P. A.; Pereira, A. F.G.; Oliveira, M. C.; Fernandes, J. V., Analytical sensitivity matrix for the inverse identification of hardening parameters of metal sheets, Eur. J. Mech. Solid., 75, 205-215 (2019) · Zbl 1473.74052
[37] Rahmani, B.; Ghossein, E.; Villemure, I.; Levesque, M., In-situ mechanical properties identification of 3d particulate composites using the virtual fields method, Int. J. Solid Struct., 51, 3076-3086 (2014)
[38] Roux, S.; Hild, F., Optimal procedure for the identification of constitutive parameters from experimentally measured displacement fields, Int. J. Solid Struct., 184, 14-23 (2020)
[39] Saranath, K. M.; Ramji, M., Local zone wise elastic and plastic properties of electron beam welded Ti-6Al-4V alloy using digital image correlation technique: a comparative study between uniform stress and virtual fields method, Opt Laser. Eng., 68, 222-234 (2015)
[40] Sessa, S.; Vaiana, N.; Paradiso, M.; Rosati, L., An inverse identification strategy for the mechanical parameters of a phenomenological hysteretic constitutive model, Mech. Syst. Signal Process., 139, 106622 (2020)
[41] Soukup, D.; Huber‐Mörk, R., Convolutional neural networks for steel surface defect detection from photometric stereo images, (Proceedings of 10th ISVC (2014), NV: NV Las Vegas), 668-677
[42] Spranghers, K.; Vasilakos, I.; Lecompte, D.; Sol, H.; Vantomme, J., Identification of the plastic behavior of aluminum plates under free air explosions using inverse methods and full-field measurements, Int. J. Solid Struct., 51, 210-226 (2014)
[43] Srivastava, N.; Hinton, G.; Krizhevsky, A.; Sutskever, I.; Salakhutdinov, R., Dropout: a simple way to prevent neural networks from overfitting, J. Mach. Learn. Res., 15, 1929-1958 (2014) · Zbl 1318.68153
[44] Su, Y.; Zhang, Q. C.; Gao, Z.; Xu, X., Noise-induced bias for convolution-based interpolation in digital image correlation, Opt Express, 24, 1175-1195 (2016)
[45] Su, Y.; Zhang, Q.; Xu, X.; Gao, Z., Quality assessment of speckle patterns for DIC by consideration of both systematic errors and random errors, Opt Laser. Eng., 86, 132-142 (2016)
[46] Su, Y.; Zhang, Q.; Xu, X.; Gao, Z., Quality assessment of speckle patterns for DIC by consideration of both systematic errors and random errors, Opt Laser. Eng., 86, 132-142 (2016)
[47] Sutton, M. A.; Yan, J. H.; Avril, S.; Pierron, F.; Adeeb, S. M., Identification of heterogeneous constitutive parameters in a welded specimen: uniform stress and virtual fields methods for material property estimation, Exp. Mech., 48, 451-464 (2008)
[48] Valeri, G.; Koohbor, B.; Kidane, A.; Sutton, M. A., Determining the tensile response of materials at high temperature using DIC and the virtual fields method, Opt Laser. Eng., 91, 53-61 (2017)
[49] Yu, Y.; Hur, T.; Jung, J.; Jang, I. G., Deep learning for determining a near-optimal topological design without any iteration, Struct Multidiscip O, 59, 787-799 (2019)
[50] Zhang, K.; Zuo, W.; Chen, Y.; Meng, D.; Zhang, L., Beyond a Gaussian denoiser: residual learning of deep CNN for image denoising, IEEE Trans. Image Process., 26, 3142-3155 (2017) · Zbl 1409.94754
[51] Zhang, K.; Zuo, W.; Zhang, L., FFDNet: toward a fast and flexible solution for CNN-Based image denoising, IEEE Trans. Image Process., 27, 4608-4622 (2017)
[52] Zhang, Z.; Wen, G.; Chen, S., Weld image deep learning-based on-line defects detection using convolutional neural networks for al alloy in robotic arc welding, J. Manuf. Process., 45, 208-216 (2019)
[53] Zhang, N.; Shen, S. L.; Zhou, A.; Jin, Y., Application of LSTM approach for modelling stress-strain behaviour of soil, Appl. Soft Comput., 100, 106959 (2021)
[54] Zhou, G.; Yang, X.; Zhang, C.; Li, Z.; Xiao, Z., Deep learning enabled cutting tool selection for special-shaped machining features of complex products, Adv. Eng. Software, 133, 1-11 (2019)
[55] Zhuang, X.; Guo, H.; Alajlan, N.; Zhu, H.; Rabczuk, T., Deep autoencoder based energy method for the bending, vibration, and buckling analysis of Kirchhoff plates with transfer learning, Eur. J. Mech. Solid., 87, 104225 (2021) · Zbl 07362890
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. It attempts to reflect the references listed in the original paper as accurately as possible without claiming the completeness or perfect precision of the matching.