Abstract
The Monte Carlo method is computationally expensive. Especially for reliable response statistics in the tail region, a large number of samples has to be computed. In this paper, we propose a strategy that speeds up the crude Monte Carlo method using artificial intelligence. We introduce a recurrent neural network that replaces the iterative calculation procedure to evaluate nonlinear, hysteretic behavior of a structure subjected to a randomized load history. The new strategy is demonstrated on an academic example, i.e., an elasto-plastic frame, which is loaded by a time-variant force. The trained recurrent neural network reliably approximates the structures mechanical response and considerably reduces the computation time per sample.
Similar content being viewed by others
References
Adam, C., Heuer, R., Ziegler, F.: Reliable dynamic analysis of an uncertain compound bridge under traffic loads. Acta Mech. 223(8), 1567–1581 (2012). https://doi.org/10.1007/s00707-012-0641-0
Azimi, H., Bonakdari, H., Ebtehaj, I., Gharabaghi, B., Khoshbin, F.: Evolutionary design of generalized group method of data handling-type neural network for estimating the hydraulic jump roller length. Acta Mech. 229(3), 1197–1214 (2018). https://doi.org/10.1007/s00707-017-2043-9
Bamer, F., Koeppe, A., Markert, B.: An efficient Monte Carlo simulation strategy based on model order reduction and artificial neural networks. Proc. Appl. Math. Mech. 17(1), 287–288 (2017). https://doi.org/10.1002/pamm.201710113
Bamer, F., Markert, B.: An efficient response identification strategy for nonlinear structures subject to nonstationary generated seismic excitations. Mech. Based Des. Struct. Mach. 45(3), 313–330 (2017). https://doi.org/10.1080/15397734.2017.1317269
Bamer, F., Shi, J., Markert, B.: Efficient solution of the multiple seismic pounding problem using hierarchical substructure techniques. Comput. Mech. 62(4), 761–782 (2018). https://doi.org/10.1007/s00466-017-1525-x
Bampton, M.C.C., Craig, R.R.J.: Coupling of substructures for dynamic analyses. AIAA J. 6(7), 1313–1319 (1968). https://doi.org/10.2514/3.4741
Bathe, K.J.: Finite Element Procedures. Prentice Hall, New York (1996)
Besselink, B., Tabak, U., Lutowska, A., van de Wouw, N., Nijmeijer, H., Rixen, D., Hochstenbach, M., Schilders, W.: A comparison of model reduction techniques from structural dynamics, numerical mathematics and systems and control. J. Sound Vib. 332(19), 4403–4422 (2013). https://doi.org/10.1016/j.jsv.2013.03.025
Breitkopf, P., Naceur, H., Rassineux, A., Villon, P.: Moving least squares response surface approximation: formulation and metal forming applications. Comput. Struct. 83(17), 1411–1428 (2005). https://doi.org/10.1016/j.compstruc.2004.07.011
Bucher, C.: Computational Analysis of Randomness in Structural Mechanics: Structures and Infrastructures Book Series. CRC Press, Boca Raton (2009). Google-Books-ID: nZkt02wl6egC
Cao, B.T., Freitag, S., Meschke, G.: A hybrid RNN-GPOD surrogate model for real-time settlement predictions in mechanised tunnelling. Adv. Model. Simul. Eng. Sci. 3, 5 (2016). https://doi.org/10.1186/s40323-016-0057-9
Capuano, G., Rimoli, J.J.: Smart finite elements: a novel machine learning application. Comput. Methods Appl. Mech. Eng. 345, 363–381 (2019). https://doi.org/10.1016/j.cma.2018.10.046
Challamel, N., Hjiaj, M.: Non-local behavior of plastic softening beams. Acta Mech. 178(3), 125–146 (2005). https://doi.org/10.1007/s00707-005-0225-3
Chan, T.F., Golub, G.H., LeVeque, R.J.: Updating formulae and a pairwise algorithm for computing sample variances. In: COMPSTAT 1982 5th Symposium Held at Toulouse 1982, pp. 30–41. Physica, Heidelberg (1982). https://doi.org/10.1007/978-3-642-51461-6_3
Cho, S.E.: Probabilistic stability analyses of slopes using the ANN-based response surface. Comput. Geotech. 36(5), 787–797 (2009). https://doi.org/10.1016/j.compgeo.2009.01.003
Fotiu, P., Irschik, H., Ziegler, F.: Forced vibrations of an elasto-plastic and deteriorating beam. Acta Mech. 69(1), 193–203 (1987). https://doi.org/10.1007/BF01175721
Freitag, S., Cao, B.T., Ninić, J., Meschke, G.: Recurrent neural networks and proper orthogonal decomposition with interval data for real-time predictions of mechanised tunnelling processes. Comput. Struct. (2017). https://doi.org/10.1016/j.compstruc.2017.03.020
Freitag, S., Graf, W., Kaliske, M.: A material description based on recurrent neural networks for fuzzy data and its application within the finite element method. Comput. Struct. 124, 29–37 (2013). https://doi.org/10.1016/j.compstruc.2012.11.011
Ghaboussi, J., Garrett Jr., J., Wu, X.: Knowledge-based modeling of material behavior with neural networks. J. Eng. Mech. 117(1), 132–153 (1991). https://doi.org/10.1061/(ASCE)0733-9399(1991)117:1(132)
Ghaboussi, J., Pecknold, D.A., Zhang, M., Haj-Ali, R.M.: Autoprogressive training of neural network constitutive models. Int. J. Numer. Meth. Eng. 42(1), 105–126 (1998). https://doi.org/10.1002/(SICI)1097-0207(19980515)42:1<105::AID-NME356>3.0.CO;2-V
Ghaboussi, J., Sidarta, D.E.: New nested adaptive neural networks (NANN) for constitutive modeling. Comput. Geotech. 22(1), 29–52 (1998). https://doi.org/10.1016/S0266-352X(97)00034-7
Glorot, X., Bengio, Y.: Understanding the difficulty of training deep feedforward neural networks. In: International Conference on Artificial Intelligence and Statistics, pp. 249–256 (2010)
Goodfellow, I., Bengio, Y., Courville, A.: Deep Learning. MIT Press, Cambridge (2016)
Graf, W., Freitag, S., Sickert, J.U., Kaliske, M.: Structural analysis with fuzzy data and neural network based material description. Comput. Aided Civ. Infrastruct. Eng. 27(9), 640–654 (2012). https://doi.org/10.1111/j.1467-8667.2012.00779.x
Greff, K., Srivastava, R.K., Koutník, J., Steunebrink, B.R., Schmidhuber, J.: LSTM: A Search Space Odyssey. arXiv:1503.04069 Cs (2015)
Hambli, R.: Application of neural networks and finite element computation for multiscale simulation of bone remodeling. J. Biomech. Eng. 132(11), 114,502–114,502-5 (2010). https://doi.org/10.1115/1.4002536
Hambli, R.: Numerical procedure for multiscale bone adaptation prediction based on neural networks and finite element simulation. Finite Elements Anal. Des. 47(7), 835–842 (2011). https://doi.org/10.1016/j.finel.2011.02.014
Hambli, R., Barkaoui, A.: Multiscale approach for bone remodeling simulation based on finite element and neural network computation. arXiv:1107.3817 Phys. Q-Bio (2011)
Hametner, C., Edelmann, J., Jakubek, S., Mack, W.: An advanced algorithm for partitioning and parameter estimation in local model networks and its application to vehicle vertical dynamics. Acta Mech. 223(8), 1693–1706 (2012). https://doi.org/10.1007/s00707-012-0638-8
Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997). https://doi.org/10.1162/neco.1997.9.8.1735
Hornik, K., Stinchcombe, M., White, H.: Multilayer feedforward networks are universal approximators. Neural Netw. 2(5), 359–366 (1989)
Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. arXiv:1502.03167 Cs (2015)
Irschik, H.: Biaxial dynamic bending of elastoplastic beams. Acta Mech. 62(1), 155–167 (1986). https://doi.org/10.1007/BF01175861
Javadi, A., Rezania, M.: Intelligent finite element method: an evolutionary approach to constitutive modeling. Adv. Eng. Inform. 23(4), 442–451 (2009). https://doi.org/10.1016/j.aei.2009.06.008
Kaliszuk, J., Waszczyszyn, Z.: Reliability analysis of structures by neural network supported monte carlo methods. In: Rutkowski, P.L., Kacprzyk, P.J. (eds.) Neural Networks and Soft Computing, No. 19 in Advances in Soft Computing, pp. 754–759. Physica, HD (2003). https://doi.org/10.1007/978-3-7908-1902-1_117
Kamiński, M.M.: A generalized stochastic perturbation technique for plasticity problems. Comput. Mech. 45(4), 349 (2009). https://doi.org/10.1007/s00466-009-0455-7
Kaveh, A., Laknejadi, K., Alinejad, B.: Performance-based multi-objective optimization of large steel structures. Acta Mech. 223(2), 355–369 (2012). https://doi.org/10.1007/s00707-011-0564-1
Kerschen, G., Golinval, J., Vakakis, A.F., Bergman, L.A.: The method of proper orthogonal decomposition for dynamical characterization and order reduction of mechanical systems: an overview. Nonlinear Dyn. 41(1), 147–169 (2005)
Kingma, D., Ba, J.: Adam: A Method for Stochastic Optimization. arXiv:1412.6980 Cs (2014)
Kleiber, M., Knabel, J., Rojek, J.: Response surface method for probabilistic assessment of metal forming failures. Int. J. Numer. Methods Eng. 60(1), 51–67 (2004). https://doi.org/10.1002/nme.954
Koeppe, A., Bamer, F., Hernandez Padilla, C.A., Markert, B.: Neural network representation of a phase-field model for brittle fracture. Proc. Appl. Math. Mech. 17(1), 253–254 (2017). https://doi.org/10.1002/pamm.201710096
Koeppe, A., Bamer, F., Markert, B.: Model reduction and submodelling using neural networks. Proc. Appl. Math. Mech. 16(1), 537–538 (2016). https://doi.org/10.1002/pamm.201610257
Koeppe, A., Bamer, F., Markert, B.: An intelligent meta-element for linear elastic continua. PAMM 18(1), e201800,283 (2018). https://doi.org/10.1002/pamm.201800283
Koeppe, A., Hernandez Padilla, C.A., Voshage, M., Schleifenbaum, J.H., Markert, B.: Efficient numerical modeling of 3D-printed lattice-cell structures using neural networks. Manufacturing Letters (Special Issue “Industry 4.0”) (2018). https://doi.org/10.1016/j.mfglet.2018.01.002
Kruse, R., Borgelt, C., Braune, C., Klawonn, F., Moewes, C., Steinbrecher, M.: Computational Intelligence. Springer Fachmedien Wiesbaden, Wiesbaden (2015)
LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521(7553), 436–444 (2015). https://doi.org/10.1038/nature14539
Lefik, M., Schrefler, B.A.: Artificial neural network as an incremental non-linear constitutive model for a finite element code. Comput. Methods Appl. Mech. Eng. 192(28–30), 3265–3283 (2003). https://doi.org/10.1016/S0045-7825(03)00350-5
Lü, Q., Low, B.K.: Probabilistic analysis of underground rock excavations using response surface method and SORM. Comput. Geotech. 38(8), 1008–1021 (2011). https://doi.org/10.1016/j.compgeo.2011.07.003
Abadi, M., Agarwal, A., Barham, P., Brevdo, E., Chen, Z., Citro, C., Corrado, G.S., Davis, A., Dean, J., Devin, M., Ghemawat, S., Goodfellow, I., Harp, A., Irving, G., Isard, M., Jia, Y., Jozefowicz, R., Kaiser, L., Kudlur, M., Levenberg, J., Mané, D., Monga, R., Moore, S., Murray, D., Olah, C., Schuster, M., Shlens, J., Steiner, B., Sutskever, I., Talwar, K., Tucker, P., Vanhoucke, V., Vasudevan, V., Viégas, F., Vinyals, O., Warden, P., Wattenberg, M., Wicke, M., Yu, Y., Zheng, X.: TensorFlow: large-scale machine learning on heterogeneous systems. ACM Sigplan Not. 51, 1–1 (2015)
Naceur, H., Ben-Elechi, S., Batoz, J.L., Knopf-Lenoir, C.: Response surface methodology for the rapid design of aluminum sheet metal forming parameters. Mater. Des. 29(4), 781–790 (2008). https://doi.org/10.1016/j.matdes.2007.01.018
Nair, V., Hinton, G.E.: Rectified linear units improve restricted Boltzmann machines. In: Proceedings of the 27th International Conference on Machine Learning (ICML-10), pp. 807–814 (2010)
Oeser, M., Freitag, S.: Modeling of materials with fading memory using neural networks. Int. J. Numer. Meth. Eng. 78(7), 843–862 (2009). https://doi.org/10.1002/nme.2518
Papadrakakis, M., Papadopoulos, V., Lagaros, N.D.: Structural reliability analyis of elastic-plastic structures using neural networks and Monte Carlo simulation. Comput. Methods Appl. Mech. Eng. 136(1–2), 145–163 (1996). https://doi.org/10.1016/0045-7825(96)01011-0
Pradlwarter, H.J., Schuëller, G.I.: On advanced Monte Carlo simulation procedures in stochastic structural dynamics. Int. J. Non-Linear Mech. 32(4), 735–744 (1997). https://doi.org/10.1016/S0020-7462(96)00091-1
Rixen, D.J.: A dual Craig–Bampton method for dynamic substructuring. J. Comput. Appl. Math. 168(1–2), 383–391 (2004). https://doi.org/10.1016/j.cam.2003.12.014
Rumelhart, D.E., Hinton, G.E., Williams, R.J.: Learning representations by back-propagating errors. Cognitive Modeling 323(6088), 533–536. https://doi.org/10.1038/323533a0
Sadeghi, M.H., Lotfan, S.: Identification of non-linear parameter of a cantilever beam model with boundary condition non-linearity in the presence of noise: An NSI- and ANN-based approach. Acta Mech. 228(12), 4451–4469 (2017). https://doi.org/10.1007/s00707-017-1947-8
Schuëller, G.I., Pradlwarter, H.J., Bucher, C.G.: Efficient computational procedures for reliability estimates of MDOF-systems. Int. J. Non-Linear Mech. 26(6), 961–974 (1991). https://doi.org/10.1016/0020-7462(91)90044-T
Shahidi, S.G., Pakzad, S.N.: Generalized response surface model updating using time domain data. J. Struct. Eng. 140(8), A4014,001 (2014). https://doi.org/10.1061/(ASCE)ST.1943-541X.0000915
Stoffel, M., Bamer, F., Markert, B.: Artificial neural networks and intelligent finite elements in non-linear structural mechanics. Thin-Walled Struct. 131, 102–106 (2018). https://doi.org/10.1016/j.tws.2018.06.035
Theocaris, P.S., Bisbos, C., Panagiotopoulos, P.D.: On the parameter identification problem for failure criteria in anisotropic bodies. Acta Mech. 123(1), 37–56 (1997). https://doi.org/10.1007/BF01178399
Theocaris, P.S., Panagiotopoulos, P.D.: Plasticity including the Bauschinger effect, studied by a neural network approach. Acta Mech. 113(1), 63–75 (1995). https://doi.org/10.1007/BF01212634
Wang, H., Pang, M., Zhang, Y.: Effects of strength difference and intermediate principal stress on plane strain elastic-plastic bending of a curved beam. Acta Mech. 227(12), 3351–3366 (2016). https://doi.org/10.1007/s00707-016-1681-7
Wong, S.M., Hobbs, R.E., Onof, C.: An adaptive response surface method for reliability analysis of structures with multiple loading sequences. Struct. Saf. 27(4), 287–308 (2005). https://doi.org/10.1016/j.strusafe.2005.02.001
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Koeppe, A., Bamer, F. & Markert, B. An efficient Monte Carlo strategy for elasto-plastic structures based on recurrent neural networks. Acta Mech 230, 3279–3293 (2019). https://doi.org/10.1007/s00707-019-02436-5
Received:
Revised:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00707-019-02436-5