Identification of characteristic length of microstructure for second order continuum multiscale model by Bayesian neural networks

• Autorzy: Kaczmarczyk Ł. , Waszczyszyn Z.
• Konferencja: Neural Networks and Soft Computing/International Symposium (30.06-02.07.2005 ; Cracow, Poland)
• Języki publikacji: EN

Abstrakty

EN

This-paper deals with the second-order CH of a heterogeneous material undergoing small displacements. Typically, in this approach an RVE of a heterogeneous material is investigated. A given discretized microstructure is determined a priori, without focusing on details of specific discretization techniques. Application of BNN as a tool for identification of characteristic length of a microstructure is discussed. An indentation test was analyzed under plane strain constraints for generating pseudo-experimental patterns by means of FEM. A single input of BNN was formulated due to the application of PCA. The BNN of structure 1-16-1 with sigmoid hidden neurons was designed. The Bayesian inference approach was applied to obtain pdf of the characteristic length. Numerical efficiency of the proposed approach is demonstrated in the paper.

Słowa kluczowe

EN

micro- and macrolevels; second order continuum; computational homogenization; representative volume element; finite element method; Bayesian neural; probability density function; principal component analysis; indentation test

• Wydawca: Instytut Podstawowych Problemów Techniki PAN
• Czasopismo: Computer Assisted Mechanics and Engineering Sciences
• Rocznik: 2007
• Tom: Vol. 14, No. 2
• Strony: 183--196
• Opis fizyczny: Bibliogr. 14 poz., rys., wykr.

Twórcy

autor

Kaczmarczyk Ł.

autor

Waszczyszyn Z.

• Civil Engineering Department, University of Glasgow Rankine Building, Oakfield Avenue, Glasgow G12 8LT, UK

Bibliografia

• [1] D. Barberd CM. Bishop. Neural networks and machine learning. In: Ensemble Learning in Bayesian Neural Networks, pp. 215-237. Springer, 1998.
• [2] M.C. Bishop. Neural Networks for Pattern Recognition. Clarendon Press, Oxford, 1996.
• [3] J.L. Bucaille, S. Stauss, E. Felder, J. Michler. Determination of plastic properties of metals by instrumented indentation using different sharp indentors. Acta Materialia, 51: 1663-1678, 2003.
• [4] F. Feyel. A multilevel finite element method (FE2) to describe the response of highly non-linear structures using generalized continua. Comput. Methods Appl. Mech. Engrg., 192: 3233-3244, 2003.
• [5] S. Haykin. Neural Networks. A Comprehensive Foundation. Prentice Hall, 1999.
• [6] Ł. Kaczmarczyk. Numerical Analysis of Multiscale Problems in Mechanics of Heterogeneous Media (in Polish). PhD thesis, Cracow University of Technology, http://www.l5.pk.edu.pl/~likask/phd.html, 2006.
• [7] Ł. Kaczmarczyk. Thin layer shear and second order homogenization method. Comput. Assisted Mech. Engrg. Sci., 13: 537-546, 2006.
• [8] V.G Kouznetsova. Computational Homogenization for the Multi-Scale Analysis of Multi-Phase Materials. PhD thesis, Technische Universiteit Eindhoven, 2002.
• [9] J. Lampinen, A. Vehtari. Bayesian approach for neural networks. Neural Networks, 14(3): 7-24, 2001.
• [10] M.E. Tipping. Advanced Lectures on Machine Learning, chapter 'Bayesian inference: an introduction to principles and practice in machine learning', pp. 41-62. Springer, 2004.
• [11] R. Neal. Software for Flexible Bayesian Modeling and Markov Chain Sampling. http://www.cs.toronto.edu/ radford/fbm.software.html, 2004.
• [12] J.Y. Shu, W.E. King, N.A. Fleck. Finite element for materials with strain gradient effects. Int. J. Num. Meth. Engrg., 44: 373-391, 1999.
• [13] A. Truty. On certain classes of mixed and stabilized mixed finite elements formulations for single and two-phase geomaterials. Zesz. Nauk. Polit. Krak., Inż. Śród. No. 48. Cracow Univ. of Technology, Cracow, 2002.
• [14] Z. Waszczyszyn, L. Ziemiański. Neural networks in the identification analysis of structural mechanics problems. In: Z. Mróz, G. Stavroulakis, eds., Parameter Identification of Materials and Structures, CISM Lecture Notes No. 469, Chapter 7, pp. 265-340. Springer, Wien-New York, 2005.