Browse > Article
http://dx.doi.org/10.12989/sem.2022.83.2.273

A posteriori error estimation via mode-based finite element formulation using deep learning  

Jung, Jaeho (Korea Atomic Energy Research Institute)
Park, Seunghwan (Department of Mechanical Engineering, Korea Advanced Institute of Science and Technology)
Lee, Chaemin (Department of Mechanical Engineering, Korea Advanced Institute of Science and Technology)
Publication Information
Structural Engineering and Mechanics / v.83, no.2, 2022 , pp. 273-282 More about this Journal
Abstract
In this paper, we propose a new concept for error estimation in finite element solutions, which we call mode-based error estimation. The proposed error estimation predicts a posteriori error calculated by the difference between the direct finite element (FE) approximation and the recovered FE approximation. The mode-based FE formulation for the recently developed self-updated finite element is employed to calculate the recovered solution. The formulation is constructed by searching for optimal bending directions for each element, and deep learning is adopted to help find the optimal bending directions. Through various numerical examples using four-node quadrilateral finite elements, we demonstrate the improved predictive capability of the proposed error estimator compared with other competitive methods.
Keywords
deep learning; error estimation; finite element analysis; four-node quadrilateral finite element; mode-based formulation; self-updated finite element;
Citations & Related Records
Times Cited By KSCI : 2  (Citation Analysis)
연도 인용수 순위
1 Zienkiewicz, O.C. and Zhu, J.Z. (1992b), "The superconvergent patch recovery and a posteriori error estimates. Part 1: The recovery technique", Int. J. Numer. Meth. Eng., 33(7), 1331-1364. https://doi.org/10.1002/nme.1620330702.   DOI
2 Zienkiewicz, O.C. and Zhu, J.Z. (1992c), "The superconvergent patch recovery and a posteriori error estimates. Part 2: Error estimates and adaptivity", Int. J. Numer. Meth. Eng., 33(7), 1365-1382. https://doi.org/10.1002/nme.1620330703.   DOI
3 Kim, S. and Lee, P.S. (2018), "A new enriched 4-node 2D solid finite element free from the linear dependence problem", Comput. Struct., 202, 25-43. https://doi.org/10.1016/j.compstruc.2018.03.001.   DOI
4 Kojic, M. and Bathe, K.J. (2005), Inelastic Analysis of Solids and Structures, Springer, Berlin.
5 Kunert, G. and Nicaise, S. (2003), "Zienkiewicz-Zhu error estimators on anisotropic tetrahedral and triangular finite element meshes", Math. Model. Numer. Anal., 37(6), 1013-1043. https://doi.org/10.1051/m2an:2003065.   DOI
6 Ozakca, M. (2003), "Comparison of error estimation methods and adaptivity for plane stress/strain problems", Struct. Eng. Mech., 15(5), 579-608. https://doi.org/10.12989/sem.2003.15.5.579.   DOI
7 Bank, R.E. (1986), "Analysis of a local a posteriori error estimate for elliptic equations, in Babuska", Accuracy Estimates and Adaptive Refinements in Finite Element Computations, 119, https://ci.nii.ac.jp/naid/10010425158.
8 Lee, C. and Kim, S. (2020), "Towards improving finite element solutions automatically with enriched 2D solid elements", Struct. Eng. Mech., 76(3), 379-393. https://doi.org/10.12989/sem.2020.76.3.379.   DOI
9 Lee, C., Kim, S. and Lee, P.S. (2021), "The strain-smoothed 4-node quadrilateral finite element", Comput. Meth. Appl. Mech. Eng., 373, 113481. https://doi.org/10.1016/j.cma.2020.113481.   DOI
10 Lee, C. and Lee, P.S. (2019), "The strain-smoothed MITC3+ shell finite element", Comput. Struct., 223, 106096. https://doi.org/10.1016/j.compstruc.2019.07.005.   DOI
11 Babuska, I. and Rheinboldt, W. (1979), "Analysis of optimal finite-element meshes in R1", Math. Comput., 33(146), 435-463. https://doi.org/10.1090/S0025-5718-1979-0521270-2.   DOI
12 Babuska, I. and Miller, A.D. (1987), "A feedback element method with a posteriori error estimation: Part I. The finite element method and some basic properties of the a posteriori error estimator", Comput. Meth. Appl. Mech. Eng., 61, 1-40. https://doi.org/10.1016/0045-7825(87)90114-9.   DOI
13 Rank, E. and Zienkiewicz, O. (1987), "A simple error estimator in the finite element method", Commun. Numer. Meth. Eng., 3(3), 243-249. https://doi.org/10.1002/cnm.1630030311.   DOI
14 Zienkiewicz, O.C. and Zhu, J.Z. (1987), "A simple error estimator and adaptive procedure for practical engineerng analysis", Int. J. Numer. Meth. Eng., 24(2), 337-357. https://doi.org/10.1002/cnm.1630030311.   DOI
15 Hinton, E. and Campbell, J.S. (1974), "Local and global smoothing of discontinuous finite element functions using a least squares method", Int. J. Numer. Meth. Eng., 8, 461-480. https://doi.org/10.1002/nme.1620080303.   DOI
16 Bank, R.E. and Weiser, A. (1985), "Some a posteriori error estimators for elliptic partial differential equations", Math. Comput., 44(170), 283-301. https://doi.org/10.2307/2007953.   DOI
17 Ainsworth, M., Zhu, J.Z., Craig, A.W. and Zienkiewicz, O.C. (1989), "Analysis of the Zienkiewicz-Zhu a-posteriori error estimator in the finite element method", Int. J. Numer. Meth. Eng., 28(9), 2161-2174. https://doi.org/10.1002/nme.1620280912.   DOI
18 Jun, H., Yoon, K., Lee, P.S. and Bathe, K.J. (2018), "The MITC3+ shell element enriched in membrane displacements by interpolation covers", Comput. Meth. Appl. Mech. Eng., 337, 458-480. https://doi.org/10.1016/j.cma.2018.04.007.   DOI
19 Lee, C. and Lee, P.S. (2018), "A new strain smoothing method for triangular and tetrahedral finite elements", Comput. Meth. Appl. Mech. Eng., 341, 939-955. https://doi.org/10.1016/j.cma.2018.07.022.   DOI
20 Oliver, J. and Fuenmayor, F. (1993), "Analysis of the effectivity of the Zienkiewicz-Zhu error estimator", WIT Trans. Built Environ., 2, 309-324.
21 Babuska, I. and Rheinboldt, W.C. (1978), "A-posteriori error estimates for the finite element method", Int. J. Numer. Meth. Eng., 12(10), 1597-1615. https://doi.org/10.1002/nme.1620121010.   DOI
22 Bathe, K.J. (2006), Finite Element Procedures, Klaus-Jurgen Bathe, Watertown, MA, USA.
23 Cook, R.D. (2007), Concepts and Applications of Finite Element Analysis, John Wiley & Sons, New York, NY, USA.
24 Kelly, D.W., De S. R. Gago, J.P., Zienkiewicz, O.C. and Babuska, I. (1983), "A posteriori error analysis and adaptive processes in the finite element method: Part I-error analysis", Int. J. Numer. Meth/ Eng., 19(11), 1593-1619. https://doi.org/10.1002/nme.1620191103.   DOI
25 Tang, X. and Sato, T. (2004), "A posteriori error estimate and hadaptive fe analysis of liquefaction with large deformation", Doboku Gakkai Ronbunshu, 2004(778), 1-15. https://doi.org/10.2208/jscej.2004.778_1   DOI
26 Mota, A. and Abel, J.F. (2000), "On mixed finite element formulations and stress recovery techniques", Int. J. Numer. Meth. Eng., 47(1-3), 191-204. https://doi.org/10.1002/(SICI)1097-0207(20000110/30)47:1/3<191::AID-NME767>3.0.CO;2-S.   DOI
27 Zienkiewicz, O.C. and Zhu, J.Z. (1992a), "The superconvergent patch recovery (SPR) and adaptive finite element refinement", Comput. Meth. Appl. Mech. Eng., 101(1-3), 207-224. https://doi.org/10.1016/0045-7825(92)90023-D.   DOI
28 Jung, J., Jun, H. and Lee, P.S. (2021), "Self-updated four-node finite element using deep learning", Comput. Mech., 69(1), 23-44. https://doi.org/10.1007/s00466-021-02081-7.   DOI
29 Jung, J., Yoon, K. and Lee, P.S. (2020), "Deep learned finite elements", Comput. Meth. Appl. Mech. Eng., 372, 113401. https://doi.org/10.1016/j.cma.2020.113401.   DOI