Open Access Open Access  Restricted Access Subscription Access

Modeling and Calibration of Uncertainty in Material Properties of Additively Manufactured Composites

EMIL PITZ, SEAN ROONEY, KISHORE POCHIRAJU

Abstract


Simulations quantifying the uncertainty in structural response and damage evolution require accurate representation of the randomness of the underlying material stiffness and strength behaviors. In this paper, the mean and variance descriptions of variability of strength and stiffness of additively manufactured composite specimens are augmented with random field correlation descriptors that represent the process dependence on the property heterogeneity through microstructure variations. Two correlation lengths and a rotation parameter are introduced into randomized stiffness and strength distribution fields to capture the local heterogeneities in the microstructure of Additively Manufactured (AM) composites. We formulated a simulation and Artificial Intelligence (AI)-based technique to calibrate the correlation length and rotation parameter measures from relatively few samples of experimentally obtained strain field observations using Digital Image Correlation (DIC). The neural networks used for calibrating the correlation lengths of Karhunen-Loève Expansion (KL expansion) from the DIC images are trained using simulated stiffness and strength fields that have known correlation coefficients. A virtual DIC filter is used to add the noise and artifacts from typical DIC analysis to the simulated strain fields. A Deep Neural Network (DNN), whose architecture is optimized using Efficient Neural Architecture Search (ENAS), is trained on 150,000 simulated DIC images. The trained DNN is then used for calibration of KL expansion correlation lengths for additively manufactured composite specimens. The AM composites are loaded in tension and DIC images of the strain fields are generated and presented to the DNNs, which produce the correlation coefficients for the random fields as outputs. Compared to classical optimization methods to calibrate model parameters iteratively, neural networks, once trained, efficiently and quickly predict parameters without the need for a robust simulator and optimization methods.


DOI
10.12783/asc36/35758

Full Text:

PDF

References


L. Wu, V.-D. Nguyen, L. Adam, and L. Noels, “An inverse micro-mechanical

analysis toward the stochastic homogenization of nonlinear random composites,â€

Computer Methods in Applied Mechanics and Engineering, vol. 348,

pp. 97 –138, 2019, ISSN: 0045-7825. DOI: 10.1016/j.cma.2019.01.

L. Wu, C. N. Chung, Z. Major, L. Adam, and L. Noels, “From SEM images

to elastic responses: A stochastic multiscale analysis of UD fiber reinforced

composites,†Composite Structures, vol. 189, pp. 206–227, 2018, ISSN: 0263-

DOI: 10.1016/j.compstruct.2018.01.051.

L. Wu, L. Adam, and L. Noels, “A micromechanics-based inverse study for

stochastic order reduction of elastic UD fiber reinforced composites analyses,â€

International Journal for Numerical Methods in Engineering, vol. 115, no. 12,

pp. 1430–1456, 2018, ISSN: 1097-0207. DOI: 10.1002/nme.5903.

B. Staber, J. Guilleminot, C. Soize, J. Michopoulos, and A. Iliopoulos, “Stochastic

modeling and identification of a hyperelastic constitutive model for laminated

composites,†Computer Methods in Applied Mechanics and Engineering,

vol. 347, pp. 425 –444, 2019, ISSN: 0045-7825. DOI: 10.1016/j.cma.

12.036.

G. J. Yun, L. Zhao, and E. Iarve, “Probabilistic mesh-independent discrete

damage analyses of laminate composites,†Composite Structures, vol. 133,

pp. 22–30, 2015, ISSN: 0263-8223. DOI: 10 . 1016 / j . compstruct .

07.083.

A. Vanaerschot, B. N. Cox, S. V. Lomov, and D. Vandepitte, “Stochastic multiscale

modelling of textile composites based on internal geometry variability,â€

Computers & Structures, vol. 122, pp. 55 –64, 2013, Computational Fluid and

Solid Mechanics 2013, ISSN: 0045-7949. DOI: https://doi.org/10.

/j.compstruc.2012.10.026. [Online]. Available: http://

www.sciencedirect.com/science/article/pii/S0045794912002647.

D. Tal and J. Fish, “Generating a statistically equivalent representative volume

element with discrete defects,†Composite Structures, vol. 153, pp. 791

–803, 2016, ISSN: 0263-8223. DOI: https : / / doi . org / 10 . 1016 /

j.compstruct.2016.06.077. [Online]. Available: http://www.

sciencedirect.com/science/article/pii/S0263822316310790.

A. Gupta, A. Cecen, S. Goyal, A. K. Singh, and S. R. Kalidindi, “Structure–

property linkages using a data science approach: Application to a nonmetallic

inclusion/steel composite system,†Acta Materialia, vol. 91, pp. 239

–254, 2015, ISSN: 1359-6454. DOI: https : / / doi . org / 10 . 1016 /

j . actamat . 2015 . 02 . 045. [Online]. Available: http : / / www .

sciencedirect.com/science/article/pii/S1359645415001603.

P. Meißner, H. Watschke, J. Winter, and T. Vietor, “Artificial neural networksbased

material parameter identification for numerical simulations of additively

manufactured parts by material extrusion,†Polymers, vol. 12, no. 12, 2020,

ISSN: 2073-4360. DOI: 10.3390/polym12122949.

F. Abbassi, T. Belhadj, S. Mistou, and A. Zghal, “Parameter identification of

a mechanical ductile damage using artificial neural networks in sheet metal

forming,†Materials & Design, vol. 45, pp. 605–615, 2013, ISSN: 0261-3069.

DOI: 10.1016/j.matdes.2012.09.032.

A. Chamekh, H. Bel Hadj Salah, and R. Hambli, “Inverse technique identification

of material parameters using finite element and neural network computation,â€

The International Journal of Advanced Manufacturing Technology,

vol. 44, no. 1, p. 173, 2008. DOI: 10.1007/s00170-008-1809-6.

M. Nassef, C. Schenck, and B. Kuhfuss, “Simulation-based parameter identification

of a reduced model using neural networks,†in 2011 9th IEEE International

Conference on Control and Automation (ICCA), 2011, pp. 974–978.

DOI: 10.1109/ICCA.2011.6138002.

T. L¨ahivaara, L. K¨arkk¨ainen, J. M. J. Huttunen, and J. S. Hesthaven, “Deep

convolutional neural networks for estimating porous material parameters with

ultrasound tomography,†The Journal of the Acoustical Society of America,

vol. 143, no. 2, pp. 1148–1158, 2018. DOI: 10.1121/1.5024341.

E. Pitz, S. Rooney, and K. Pochiraju, “Stochastic modelling of additively manufactured

structures using a neural network for identification of random field

parameters,†presented at the ASC 35th Technical (Virtual) Conference, Sep.

DOI: 10.12783/asc35/34974.

R. I. Borja, “J2 plasticity,†in Plasticity: Modeling & Computation. Berlin,

Heidelberg: Springer Berlin Heidelberg, 2013, pp. 31–58, ISBN: 978-3-642-

-6. DOI: 10.1007/978-3-642-38547-6_3. [Online]. Available:

https://doi.org/10.1007/978-3-642-38547-6_3.

A. Der Kiureghian, T. Haukaas, and K. Fujimura, “Structural reliability software

at the university of california, berkeley,†Structural Safety, vol. 28, no. 1,

pp. 44 –67, 2006, Structural Reliability Software, ISSN: 0167-4730. DOI: https:

//doi.org/10.1016/j.strusafe.2005.03.002. [Online]. Available:

http://www.sciencedirect.com/science/article/

pii/S0167473005000160.

M. Voˇrechovsk´y, “Simulation of simply cross correlated random fields by series

expansion methods,†Structural Safety, vol. 30, no. 4, pp. 337–363, 2008,

ISSN: 0167-4730. DOI: 10.1016/j.strusafe.2007.05.002.

R. G. Ghanem and P. D. Spanos, Stochastic Finite Elements: A Spectral Approach.

Berlin, Heidelberg: Springer-Verlag, 1991, ISBN: 0387974563. DOI:

1007/978-1-4612-3094-6.

T. Zhao and Y. Wang, “Simulation of cross-correlated random field samples

from sparse measurements using bayesian compressive sensing,†Mechanical

Systems and Signal Processing, vol. 112, pp. 384–400, 2018, ISSN: 0888-3270.

DOI: 10.1016/j.ymssp.2018.04.042.

K. Fukunaga and W. Koontz, “Representation of random processes using the

finite karhunen-lo`eve expansion,†Information and Control, vol. 16, no. 1,

pp. 85 –101, 1970, ISSN: 0019-9958. DOI: https : / / doi . org / 10 .

/S0019-9958(70)80043-2. [Online]. Available: http://www.

sciencedirect.com/science/article/pii/S0019995870800432.

A. Klenke, Probability Theory, A Comprehensive Course. Springer, London,

, ISBN: 978-1-4471-5361-0. DOI: 10.1007/978-1-4471-5361-0.

M. Reis, S. Diebels, and A. Jung, “Noise reduction for dic measurements,â€

PAMM, vol. 19, no. 1, 2019. DOI: 10.1002/pamm.201900077.

S. N. Olufsen, M. E. Andersen, and E. Fagerholt, “μDic: An open-source

toolkit for digital image correlation,†SoftwareX, vol. 11, p. 100 391, 2020,

ISSN: 2352-7110. DOI: 10.1016/j.softx.2019.100391.

P. Alfeld, “A trivariate clough—tocher scheme for tetrahedral data,†Computer

Aided Geometric Design, vol. 1, no. 2, pp. 169–181, 1984, ISSN: 0167-8396.

DOI: 10.1016/0167-8396(84)90029-3.

P. Virtanen et al., “SciPy 1.0: Fundamental Algorithms for Scientific Computing

in Python,†Nature Methods, vol. 17, pp. 261–272, 2020. DOI: 10.1038/

s41592-019-0686-2.

J.-J. Orteu, D. Garcia, L. Robert, and F. Bugarin, “A speckle texture image generator,â€

presented at the Speckle06: Speckles, From Grains to Flowers, Nimes,

France, 2006. DOI: 10.1117/12.695280.

A. Paszke et al., “Pytorch: An imperative style, high-performance deep learning

library,†in Advances in Neural Information Processing Systems 32, H.

Wallach et al., Eds., Curran Associates, Inc., 2019, pp. 8024–8035. [Online].

Available: http://papers.neurips.cc/paper/9015-pytorchan-

imperative-style-high-performance-deep-learninglibrary.

pdf.

A. Krizhevsky, I. Sutskever, and G. E. Hinton, “Imagenet classification with

deep convolutional neural networks,†Commun. ACM, vol. 60, no. 6, 84–90,

May 2017, ISSN: 0001-0782. DOI: 10.1145/3065386.

H. Pham, M. Y. Guan, B. Zoph, Q. V. Le, and J. Dean, “Efficient neural architecture

search via parameter sharing,†CoRR, vol. abs/1802.03268, 2018.

arXiv: 1802.03268.

B. Zoph and Q. V. Le, “Neural architecture search with reinforcement learning,â€

CoRR, vol. abs/1611.01578, 2016. arXiv: 1611.01578.

B. Zoph, V. Vasudevan, J. Shlens, and Q. V. Le, “Learning transferable architectures

for scalable image recognition,†CoRR, vol. abs/1707.07012, 2017.

arXiv: 1707.07012.

S. Hochreiter and J. Schmidhuber, “Long short-term memory,†Neural Comput.,

vol. 9, no. 8, 1735–1780, Nov. 1997, ISSN: 0899-7667. DOI: 10.1162/

neco.1997.9.8.1735.

I. Sobol, “On the distribution of points in a cube and the approximate evaluation

of integrals,†USSR Computational Mathematics and Mathematical Physics,

vol. 7, no. 4, pp. 86 –112, 1967, ISSN: 0041-5553. DOI: 10.1016/0041-

(67)90144-9.

P. Bratley and B. L. Fox, “Algorithm 659: Implementing sobol’s quasirandom

sequence generator,†ACM Trans. Math. Softw., vol. 14, no. 1, pp. 88–100, Mar.

, ISSN: 0098-3500. DOI: 10.1145/42288.214372.

“Nerual network intelligence.†(Jun. 2021), [Online]. Available: https://

nni.readthedocs.io/en/stable/index.html.

Q. Zhang et al., “Retiarii: A deep learning exploratory-training framework,†in

th fUSENIXg Symposium on Operating Systems Design and Implementation

(fOSDIg 20), 2020, pp. 919–936.

D. P. Kingma and J. Ba, “Adam: A method for stochastic optimization,†in

rd International Conference on Learning Representations, ICLR 2015, San

Diego, CA, USA, May 7-9, 2015, Conference Track Proceedings, Y. Bengio

and Y. LeCun, Eds., 2015. [Online]. Available: http : / / arxiv . org /

abs/1412.6980.

Astm d638-14, standard test method for tensile properties of plastics, Standard,

ASTM International, West Conshohocken, PA, 2014. DOI: 10.1520/

D0638-14. [Online]. Available: www.astm.org.

M. Singh and R. Singh, “Twin screw extrusion for recycling of thermoplastics,â€

in Reference Module in Materials Science and Materials Engineering,

Elsevier, 2020, ISBN: 978-0-12-803581-8. DOI: 10.1016/B978-0-12-

-1.00013-4.


Refbacks

  • There are currently no refbacks.