An intelligent computing technique in identification problems

• Autorzy: Orantek P.
• Języki publikacji: EN

Abstrakty

EN

The paper is devoted to the application of the evolutionary algorithms, gradient methods and artificial neural networks to identification problems in mechanical structures. The special intelligent computing technique (ICT) of global optimization is proposed. The ICT is based on the two-stage strategy. In the first stage the evolutionary algorithm is used as the global optimization method. In the second stage the special local method which combines the gradient method and the artificial neural network is applied. The presented technique has many advantages: (i) it can be applied to problems in which the sensitivity is very hard to compute, (ii) it allows shortening the computing time. The key problem of the presented approach is the application of the artificial neural network to compute the sensitivity analysis. Several numerical tests and examples are presented.

Słowa kluczowe

EN

intelligent computing; artificial neural networks; mechanical structure; optimization method

PL

sieci neuronowe; struktura mechaniczna; metoda optymalizacyjna

• Wydawca: Instytut Podstawowych Problemów Techniki PAN
• Czasopismo: Computer Assisted Mechanics and Engineering Sciences
• Rocznik: 2006
• Tom: Vol. 13, No. 2
• Strony: 351--364
• Opis fizyczny: Bibliogr. 15 poz., rys., tab.

Twórcy

autor

Orantek P.

• Department for Strength of Materials and Computational Mechanics, Silesian University of Technology, Konarskiego 18a, 44-100 Gliwice, Poland

Bibliografia

• [1] J. Arabas. Evolutionary Algorithms Lectures (in Polish). WNT, 2001.
• [2] H.D. Bui. Inverse Problems in the Mechanics of Materials: An Introduction. CRC Press, Bocca Raton, 1994.
• [3] T. Burczyński. Boundary Elements Method in Mechanics (in Polish). WNT, Warszawa 1995.
• [4] T. Burczyński, W. Beluch, A. Długosz, P. Orantek, M. Nowakowski. Evolutionary methods in inverse problems of engineering mechanics. In: M. Tanaka and G. S. Dulikravich, eds., Inverse Problems in Engineering Mechanics II, pp. 553-562, Elsevier, 2000.
• [5] T. Burczyński, W. Beluch, A. Długosz, W. Kuś, M. Nowakowski, P. Orantek. Evolutionary computation in optimization and identification. Computer Assisted Mechanics and Engineering Sciences, 9: 3-20, 2002.
• [6] T. Burczyński, E. Majchrzak, W. Kuś, P. Orantek, M. Dziewoński. Evolutionary computation in inverse problems. In: T. Burczyński and A. Osyczka, eds., Evolutionary Methods in Mechanics, pp. 33-46, Kluwer, 2004.
• [7] T. Burczyński, P. Orantek. Evolutionary algorithms aided by sensitivity information. Artificial Neural Nets and Genetic Algorithms. V. Kurkowa, N. Stelle, R. Neruda, M. Karny, eds., Springer Computer Science, pp. 272-275, Wien, 2001.
• [8] T. Burczyński, P. Orantek. Application of Neural Networks in Controlling of Evolutionary Algorithms. Computational Mechanics. S. Valliappan, N. Khalili, eds., Elsevier, pp. 1271-1276, London 2001.
• [9] T. Burczyński, P. Orantek. Application of Artificial Neutal Network in Computational sensitivity analysis. Recent Developments In: Artificial Intelligence Methods, T. Burczyński, W. Cholewa, W. Moczulski, AI-METH Series pp. 37-38, Gliwice, November, 2004.
• [10] W. Duch, J. Korbicz, L. Rutkowski, R. Tadeusiewicz. Neural Networks (in Polish), vol. 6, Exit, Warsaw 2000.
• [11] M. Kleiber et al. Parameter Sensitiuity in Nonlinear Mechanics: Theory and Finite Element Computations. J. Wiley&Sons, New York, 1997.
• [12] J. J. Montano, A. Palmer, Numeric sensitivity analysis applied to feedforward neural networks. Neural Computing & Application, 12: 119-125, Springer-Verlag, London, 2003.
• [13] R. Schaefer. The basis of the genetic global optimization (in Polish). Wydawnictwo Uniwersytetu Jagiellońskiego, Kraków, 2002.
• [14] J. Seidler, A. Badach, W. Molisz. The methods of solving the optimization problems (in Polish.) WNT, Warszawa, 1980.
• [15] Xiaotong Wang, Chih-Chen Chang, Fang Du. Achieving a more robust neural network model for control of a MR damper by signal sensitivity analysis. Neural Computing & Application, 10: 330-338, Springer-Verlag, London, 2002.