Hybrid, finite element-artificial neural network model for composite materials

• Autorzy: Lefik M.

Warianty tytułu

PL

Zastosowanie sztucznych sieci neuronowych w modelowaniu numerycznym kompozytów przy pomocy metody elementów skończonych

• Języki publikacji: EN

Abstrakty

EN

An application of Artificial Neural Networks for a definition of the effective constitutive law for a composite is described in the paper. First, a classical homogenisation procedure is directly interpreted with a use of this numerical tool. Next, a self-learning Finite Element code (FE with ANN inside) is used in the case when the effective constitutive law is deduced from a numerical experiment (substituting here a purely phenomenological approach). The new contribution to the classical self-learning procedure consists of its adaptation to a case of a non-monotonic loading (non-to-one load-deformation curve). This new ability of the method is principally due to the incremental form of the constitutive equation and the respective scheme of the neural network structure. Also an organisation of a constitutive data-base containing learning patterns is suitably modified. It is shown by examples that the training process is very quick. The error of this method is smaller, comparing to other schemes of data acquisition.

PL

W artykule opisano zastosowanie sztucznych sieci neuronowych do określenia efektywnego związku konstytutywnego dla kompozytów. To narzędzie numeryczne użyte zostało dwojako: do bezpośredniego zapisu wyników otrzymanych w ramach klasycznej metody homogenizacji oraz do wnioskowania o własnościach efektywnych na podstawie eksperymentu numerycznego (zastępującego eksperyment rzeczywisty) wykonanego na małej, lecz reprezentatywnej próbce kompozytu. W tym drugim przypadku zastosowano schemat "samouczącego się" programu metody elementów skończonych, w którym związek konstytutywny opisany jest siecią neuronową. Schemat ten zaadaptowano tak, że może być użyty w przypadku obciążeń niemonotonicznych oraz wtedy, gdy zależność: miara odkształcenia-miara naprężenia nie jest wzajemnie jednoznaczna. Te nowe możliwości uzyskane zostały dzięki przedstawieniu związku konstytutywnego w formie przyrostowej oraz opracowania odpowiedniej do tego budowy sieci neuronowej. Schemat "samouczącego się" programu MES charakteryzuje się tym, że proces formułowania nieznanego związku konstytutywnego jest szybki, a zgodność modelu numerycznego z eksperymentem większa niż dla innych metod.

Słowa kluczowe

EN

artificial neural network; composite materials; self-learning FE method

• Wydawca: Polskie Towarzystwo Mechaniki Teoretycznej i Stosowanej
• Czasopismo: Journal of Theoretical and Applied Mechanics
• Rocznik: 2004
• Tom: Vol. 42 nr 3
• Strony: 539--563
• Opis fizyczny: Bibliogr. 36 poz., rys.

Twórcy

autor

Lefik M.

• Chair of Geotechnical Engineering and Engineering Structures, Technical University of Łódź

Bibliografia

• 1. Bandeira A.A., Wriggers P., Pimenta P.M., 2001, Homogenization method leading to interface laws of contact mechanics – a finite element approach for large 3D deformation using ALM, IJMN
• 2. Bonet J., Wood R.D., 1997, Nonlinear Continuum Mechanics for Finite Element Analysis, Cambridge University Press
• 3. Boutin C., 2000, Study of permeability by periodic and self-consistent homogenization, Eur. J. Mech., A, 19, 603-632
• 4. Boutin C., Royer P., Auriault J.L., 1998, Acoustic absorption of porous surfacing with double porosity, Int. J. Solid Structures, 35, (34-35), 4709-4737
• 5. Chen T., Chen H., 1995, Universal approximation to non-linear operators by neural networks with arbitrary activation functions and its application to dynamical systems, IEEE Trans. on Neural Networks, 6, 4, 911-917
• 6. Garcia S., Romo M.P., Taboada-Urtuzuastegui V., 2000, Knowledgebased modelling of sand behaviour, Proceedings of ECCOMAS 2000, Barcelona, 11-14
• 7. Gawin D., Lefik M., Schrefler B.A., 2001, ANN approach to sorption hysteresis within a coupled hygro- thermo-mechanical FE analysis, Int. J. Numer. Meth. Engng., 50, 299-323
• 8. Ghaboussi J., Garrett J.H., Wu X., 1991, Knowledge-based modelling of material behaviour with neural networks, Journal of Engineering Mechanics, 117, 132-151
• 9. Ghaboussi J., Sidarta D.E., 1998, New nested adaptive neural networks (NANN) for constitutive modelling, Computers and Geotechnics, 22, 1, 29-52
• 10. Hashin Z., 1968, Assessment of self-consistent scheme approximation: conductivity of particulate composites, J. Comp. Mater., 2, 284-304
• 11. Hertz J., Krogh A., Palmer G.R., 1991, Introduction to the Theory of Neural Computation, Lecture Notes Vol. I, Santa Fe Institute Studies in the Sciences of Complexity, Addison-Wesley,
• 12. Hu Y.H., Hwang J-N., Eds., 2002, Handbook of Neural Network Signal Processing, CRC PRESS
• 13. Kortesis S., Panagiotopoulos P.D., 1993, Neural networks for computing in structural analysis: Methods and prospects of applications, Int. J. Num. Meth. Eng., 36, 2305-2318
• 14. Kouznetsova V., Brekelmans W., Baaijens F., 2001, An approach to micro-macro medelling of heterogeneous materials, Comp. Mech., 27, 37-48
• 15. Kroner E., 1978, Self-consistent scheme and graded disorder in poly crystal elasticity, J. Phys., 8, 22-61
• 16. Lefik M., 1997, Use of artificial neural network to define a non-linear effective constitutive law for a composite, Proc. 13th Polish Conf. Computer Methods in Mechanics PCCMM’97, Poznań, 725-732
• 17. Lefik M., 2001, Modified BP artificial neural network as an incremental nonlinear constitutive model, Proceedings of European Conference on Computational Mechanics, ECCM-2001, on CD
• 18. Lefik M., Schrefler B.A., 2002a, Artificial neural network for parameter identifications for an elasto-plastic model of super-conducting cable under cyclic loading, Computers and Structures, 80, 22, 1699-1713
• 19. Lefik M., Schrefler B.A., 2002b, One-dimensional model of cable-inconduit superconductors under cyclic loading using artificial neural networks, Fusion Engineering and Design, 60, 2, 105-117
• 20. Lefik M., Schrefler B.A., 2003, Artificial neural network as an incremental non-linear constitutive model for a finite element code, Computer Methods in Applied Mechanics and Engineering, Elsevier, Volume/Issue 192/28-30, 3265- 3283
• 21. Mucha G., Waszczyszyn Z., 1997, Hybrid neural-network/computational program for bending analysis of elastoplastic beams, Proc. of the XIII Polish Conf. on Computer Methods in Mechanics, 949-956
• 22. Nijuhuis A., Noordman N.H.W., Ten Kate H.H.J., 1998, Mechanical and Electrical testing of an ITER CS1 Model Coil Conductor under Transverse Loading in a Cryogenic Press, Preliminary Report, University of Twente
• 23. Osowski S., 1996, Sieci neuronowe w ujęciu algorytmicznym, Wydawnictwo Naukowo Techniczne, Warszawa
• 24. Penumadu D., Zhao R., 1999, Triaxial compression behaviour of sand and gravel using artificial neural networks (ANN), Computers and Geotechnics, 24, 207-230
• 25. Pichler B., Mang H., 2001, Parameter identification for sophisticated material models by means of iterative back analyses on soft computing, ECCM-2001, Cracow, Poland
• 26. Shin H.S., Pande G.N., 2000, On self-learning finite element codes based on monitored response of structues, Computers and Geotechnics,
• 27, 161-178 27. Shin H.S., Pande G.N., 2001, ”Intelligent” Finite Elements, in: Computational Mechanics – New Frontiers for New Millenium, S. Valliappan and N. Khalili (Edit.), Elsevier Science
• 28. Sanchez-Palencia E., 1980, Non-Homogeneous Media and Vibration Theory, Springer V.
• 29. Sikora Z., Ossowski R., Ichikawa Y., Tkacz K., 1998, Neural networks as a tool for constitutive modelling, in: Oka and Yashima, Edit., Localization and Bifurcation Theory for Soils and Rocks, Balkema, Rotterdam
• 30. Suquet P.M., 1985, Elements of Homogenisation for Inelastic Solid Mechanics, in: Lecture Notes in Physics, 272, Springer Verlag
• 31. Tadeusiewicz R., 1993, Sieci Neuronowe, Akademicka Oficyna Wydawnicza
• 32. Waszczyszyn Z., 1998, Some new results in applications of backpropagation neural networks in structural and civil engineering, in: Advances in Engineering Computational Technology, Civil-Comp Press, Edinburgh, 173-187
• 33. Waszczyszyn Z., 2000, Neural networks in plasticity: some new results and prospects of applications, European Congress on Computational Methods in Applied Sciences and Engineering ECCOMAS 2000, on CD
• 34. Wriggers P., Lohnert S., 2002, Virtual testing of composite materials, WCCM V, Vienna, Austria
• 35. Yagawa G., Okuda H., 1996, Neural networks in computational mechanics, Archives of Computational Methods in Engineering, 3, 4, 435-512
• 36. Zaoui A., 1997, Structural morphology and constitutive behaviour of heterogeneous materials, in: Continuum Micromechanics, P. Suquet (Edit.), Springer, 291-347