Application of neural networks for structure updating

• Autorzy: Miller B.
• Języki publikacji: EN

Abstrakty

EN

The paper presents the application of Artificial Neural Networks (ANNs) for finite element (FE) models updating. The investigated structures are beams and frames, their models are updated by ANNs with input vectors composed of dynamic characteristics of structures measured on laboratory models. The ANNs (multi layer feed-forward networks and Bayesian neural networks) are trained on numerical data disturbed by an artificial noise. The responses of the structures are measured on laboratory models. The updating procedure is also applied in identification of defects or additional masses attached to the structure.

Słowa kluczowe

EN

artificial neural networks; updating; dynamics; vibrations; identification

PL

sztuczne sieci neuronowe; aktualizacja; dynamika; drgania; identyfikacja

• Wydawca: Instytut Podstawowych Problemów Techniki PAN
• Czasopismo: Computer Assisted Mechanics and Engineering Sciences
• Rocznik: 2011
• Tom: Vol. 18, no. 3
• Strony: 191--203
• Opis fizyczny: Bibliogr. 19 poz., rys., tab., wykr.

Twórcy

autor

Miller B.

• Department of Structural Mechanics, Rzeszów University of Technology W. Pola 2, 35-959 Rzeszów, Poland,

Bibliografia

• [1] C.M. Bishop. Pattern Recognition and Machine Learning, Heidelberg: Springer, 2006.
• [2] H. Demuth, M. Beale. Neural Network Toolbox User’s Guide, Version 3.0, The MathWorks Inc., Natick MA, USA, 1998.
• [3] D.J. Ewins. Modal Testing: Theory and Practice, Letchworth: Research Studies Press, 1984.
• [4] M.I. Friswell, J.R. Mottershead. Finite Element Model Updating in Structural Dynamics, Kluwer Academic Publishers, Dordrecht, 1996.
• [5] S. Haykin. Neural Networks: a Comprehensive Foundation, Prentice Hall International, Inc., 2nd ed., 1999.
• [6] M. Kłos, Z. Waszczyszyn. Modal analysis and modified cascade neural networks in identification of geometrical parameters of circular arches, Computers&Structures. 89(7–8): 581–589, 2011.
• [7] R.I. Levin, N.A.J. Lieven. Dynamic Finite Element Model Updating Using Neural Networks, Journal of Sound and Vibration, 210(5): 593–607, 1998.
• [8] R.I. Levin, N.A.J. Lieven. Dynamic Finite Element Model Updating Using Simulated Annealing and Genetic Algorithms, Mechanical systems and signals processing, 12(1): 91–120, 1998.
• [9] B. Miller. Updating of Mathematical Models of Engineering Structures (in Polish), PhD dissertation, Rzeszow University of Technology, Rzeszow, 2002.
• [10] J.E. Mottershead, M.I. Friswell. Model Updating in Structural Dynamics: a Survey, Journal of Sound and Vibration, 167(2): 347–375, 1993.
• [11] I.T. Nabney. NETLAB Algorithms for Pattern Recognition, London-Berlin-Heidelberg: Springer, 4th print, 2004.
• [12] H.G. Natke. Problems of Model Updating Procedures: a Perspective Resumptions, Mechanical systems and signals processing, 12(1): 65–74, 1998.
• [13] J. Vanhatalo, A. Vehtari. MCMC Methods for MLP-network and Gaussian Process and Stuff – A documentation for Matlab Toolbox MCMCstuff, Helsinki University of Technology, Espoo, Finland, 2006.
• [14] Z. Waszczyszyn, L. Ziemiański. Neural Networks in Mechanics of Structures and Materials – New Results and Prospects of Applications, Computers&Structures, 79: 2261–2276, 2001.
• [15] Z. Waszczyszyn, L. Ziemiański. Parameter Identification of Materials and Structures. In: Mroz Z. Stavroulakis GE, ed. Neural Networks in the Identification Analysis of Structural Mechanics Problems. CISM Lecture Notes. Wien, New York: Springer, 2004.
• [16] Z. Waszczyszyn, M. Słoński. Maximum of marginal likelihood criterion instead of cross-validation for designing, In: Rutkowski L. et al., [Ed.] Artificial Intelligence and Soft Computing ICAISC2008, Berlin-Heidelberg-New York: Springer, 2008.
• [17] Z. Waszczyszyn editor. Advances of Soft Computing in Engineering. CISM Courses and Lectures, Udine, vol. 512. Wien-New York: Springer, 2009.
• [18] L. Ziemiański, B. Miller. Dynamic Model Updating Using Neural Networks. Computer Assisted Mechanics & Engineering Sciences, 4: 68–86, 2000.
• [19] L. Ziemiański, B. Miller, G. Piatkowski. Application of neurocomputing in the parametric identification using dynamic responses of structural elements-selected problems. Journal Of Theoretical And Applied Mechanics, 42: 667–693, 2004.