Preferencje help
Widoczny [Schowaj] Abstrakt
Liczba wyników
Tytuł artykułu

Neurocomputing in the analysis of selected inverse problems of mechanics of structures and materials

Wybrane pełne teksty z tego czasopisma
Warianty tytułu
Języki publikacji
The main goal of the paper is to show great potential of Artificial Neural Networks (ANNs) as a new tool in the identification analysis of various problems in mechanics of structures and materials. The basics of ANNs are briefly written focusing on the Back Propagation Neural Networks (BPNNs) and their features and possibilities in the analysis of inverse problems. Two groups of problems are analyzed: I) BPNNs are used in five problems as independent tools for the parametric identification and implicit modelling of physical relations, II) BPNNs are parts or procedures in three hybrid FEM/ANN systems or programs. Using measured eigenfrequencies the following problems are discussed: 1) identification of damage parameters of a steel beam, 2) attachment of an additional mass to increase the accuracy of prediction of damage parameters in a beam, 3) identification of location an additional mass attached to a steel plate. Implicit simulation of physical relations is discussed on two problems: 1) concrete fatigue durability of concrete as a function of concrete strength and characteristics of fatigue cycles (besides BPNN also the Fuzzy Weight NN was applied), 2) soil-structure interaction of displacement response spectra of a real building subjected to paraseismic excitations (besides BPNN the application of Kalman filtering is discussed for the NN learning). The following problems of Group II are investigated: 1) using BPNN in the hybrid Monte Carlo method for the reliability analysis of a steel girder, 2) application of BPNN to the calibration of control parameters in the updating of a FE program for dynamic analysis of a plane frame, 3) on-line methods for the NN constitutive model formulation basing on measurements of structural displacements.
Opis fizyczny
Bibliogr. 53 poz., il., rys., tab.
  • Institute of Computer Methods in Civil Engineering, Cracow University of Technology, Warszawska 24, 31-155 Kraków, Poland
  • [1] ADINA, Theory and Modelling Guide. Adina R&D Inc., 1992.
  • [2] A. Borowiec, L. Ziemiański. Identification of stiffness reduction in beams using parameter dependent frequency changes and neural networks. In: K.J. Bathe, ed., Computational Fluid and Solid Mechanics 2005, Proc. 3rd MIT Conf., June 1Ą-17, 2005, 97-100. Elsevier, Amsterdam, 2005.
  • [3] COSMOS/M, Finite element analysis system, Version 2.5. Structural Research and Analysis Corp., Los Angeles, California, 1999.
  • [4] Coupling of FEM and ANNs in the Analysis of Solids with Micro Structure and Structures of Unknown Constitutiue Equations, Polish Ministry of Scientific Research and Information Technology, Grant No. 4T07E 060 29, Institute of Computer Meth. in Civil Eng., Cracow, Poland, 2005-2007.
  • [5] Eurocode 8. Design Provisions for Earthquake Resistance of Structures, European Prestandard. European Committee for Standardization, Brussels, 1994.
  • [6] D.J. Ewins. Modal Testing: Theory, Practice and Applications. 2nd Ed. Research Studies Press, Baldock, Hertfordshire, 2000.
  • [7] M.I. Friswell, J.E. Motterhead. Finite Element Model Updating in Structural Mechanics. Kluwer Academic Publishers, Dordrecht, 1996.
  • [8] K. Furtak. Strength of concrete subjected to multiple repeat loadings (in Polish). Archives of Civil Engineering, 30: 677-698, 1984.
  • [9] T. Furukawa, G. Yagawa. Implicit constitutive modelling for viscoplasticity using neural networks. Int. J. Num. Meth. Eng., 43: 195-219, 1998.
  • [10] J. Ghaboussi, D.A. Pecknold, M. Zhang, R.M. Haj-Ali. Autoprogressive training of neural network constitutive models. Int. J. Num. Meth. Eng., 42: 105-126, 1998.
  • [11] R. Haj-Ali, D.A. Pecknold, J. Ghaboussi, G.Z. Voyiadjis. Simulated micromechanical model using artificial neural networks. J. Eng. Mech., 127: 730-738, 2001.
  • [12] Y.M.A. Hashash, S. Jung, J. Ghaboussi. Numerical implementation of a neurally based material model in finite element analysis. Int. J. Num. Meth. Eng., 59: 989-1005, 2004.
  • [13] S. Haykin. Neural Networks - Comprehensible Foundation, 2nd edition. Prentice-Hall. Upper Saddle River NJ, 1999.
  • [14] S. Haykin. Kalman Filtering and Neural Networks. John Wiley and Sons, New York, 2001.
  • [15] J.E. Hurtado. Neural network in stochastic mechanics. Archives of Comp. Meth. Eng., 8: 303-342, 2001.
  • [16] M. Jakubek, Z. Waszczyszyn. Analysis of concrete fatigue durability by the neuro-fuzzy network FWNN. Archives of Civil Engineering, 52, 2006 (in print).
  • [17] J.-Sh.R. Jang, Ch-T. Sun., E. Mizutani. Neuro-Fuzzy and Soft Computing. Prentice-Hall, Upper Saddle River NJ, 1997.
  • [18] J. Kaliszuk. Reliability Analysis of Structures and Structural Elements by Artificial Neural Networks (in Polish). Ph.D. Thesis. Dept. of Civil and Environmental Eng., Univ. of Zielona Góra, Poland, 2005.
  • [19] J. Kaliszuk, A. Urbańska, Z. Waszczyszyn, K. Furtak. Neural analysis of concrete fatigue durability on the basis of experimental evidence. Archives of Civil Engineering, 47: 327-339, 2001.
  • [20] J. Kaliszuk, Z. Waszczyszyn. Reliability analysis of structures by neural network supported Monte Carlo methods. In: L. Rutkowski, J. Kacprzyk, eds., Neural Networks and Soft Computing. Proc. 6th Int. Conf., Zakopane, 754-759. Springer, Berlin-Heidelberg, Germany, 2003.
  • [21] J. Kaliszuk, Z. Waszczyszyn. Reliability analysis of a steel girder by the hybrid Monte Carlo method. Proc. XI Intern. Conf. on Metal Structures ICMS-2006. A.A. Balkema, Leiden, The Netherlanads, 2006 (in print).
  • [22] A. Krok, Z. Waszczyszyn. Neural prediction of response spectra from mining tremors using reccurent layered networks and Kalman filtering. In: K.J. Bathe, ed., Computational Fluid and Solid Mechanics 2005, Proc. 3rd MIT Conf., June 1Ą-17, 2005, 302-305. Elsevier, Amsterdam, 2005.
  • [23] A. Krok, Z. Waszczyszyn. Application of neural networks and Kalman filtering to simulation of displacement response spectra on buildings subjected to paraseismic excitations. In: Z. Waszczyszyn, M. Słoński, eds, Proc. Int. Symposium on Neural Networks and Soft Computing in Structural Engineering NNSC-2005, ECCOMAS Thematic Conferences, Cracow, Poland, June 30-July 2, 2005, CD-ROM, 7 pages. Cracow Univ. of Technology, Cracow, 2005.
  • [24] M. Królak. Postcritical behaviour and load carrying capacity of thin-walled girders (in Polish). PWN, Warszawa-Łódź, Poland, 1990.
  • [25] K. Kuźniar. Analysis of Vibrations of Medium-Height Buildings with Load Bearing Walls Subjected to Mining Tremors Using Neural Networks (in Polish). Monograph 310, Series of Civil Eng., Cracow Univ. of Technology, Cracow, Poland, 2004.
  • [26] K. Kuźniar, E. Maciąg. Neural analysis of soil-structure interaction in case pf mining tremors. In: D. Doolin, A. Kammerer, T. Nogami, R.B. Seed, I. Towhata, eds., 11th Intern. Conf. on Soil Dynamics and Earthquake Engineering and 3rd Intern. Conf. on Earthquake Geotechnical Engineering, Vol. 2: 829-83. Berkeley, USA, 2004.
  • [27] W. Łakota. Detection and Location of Damage in Beam Structures (in Polish). Ofic. Wyd. Polit. Reszowskiej, Rzeszów, 1999.
  • [28] P. Marek, J. Brozetti, M. Gustar. Probabilistic Assessment of Structures using Monte Carlo Simulation: Background, Exercises and Software. Institute of Theoretical and Applied Mechanics, Academy of Sci. of the Czech Republic, Praha, 2001.
  • [29] B. Miller. Updating of Mathematical Model of Structure to Physical Model (in Polish). Ph.D. Thesis. Dept. of Building and Environmental Eng., Rzeszów Univ. of Technology, Rzeszów, Poland, 2001.
  • [30] B. Miller, L. Ziemiański: Neural networks in updating of dynamic models with experimental verification. In: L. Rutkowski, J. Kacprzyk, eds., Neural Networks and Soft Computing. Proc. 6th Int. Conf., Zakopane, 766-771. Springer, Berlin-Heidelberg, Germany, 2003.
  • [31] Z. Mróz, K. Dems. Identification of damage in beam and plate strucutres using parameter depending modal changes and thermographic methods. In: Z. Mróz, G. Stavroulakis, eds., Parameter Identification of Materials and Structures, CISM Courses and Lectures No. 469, 95-137. Springer, Wien-New York, 2005.
  • [32] J. Murzewski. Reliability of Engineering Structures (in Polish). Arkady, Warsaw, Poland, 1989.
  • [33] Neural Network Toolbox for Use with MATLAB. User's Guide Version 3. The MathWorks Inc., Natick, MA, 1998.
  • [34] S.H. Ni, P.C. Lu, C.H. Yang. A fuzzy neural network approach to evaluation of slope failure potential. Microcomputers in Civil Engineering, 11: 59-66, 1996.
  • [35] A.K. Noor. Computational structures technology: leap frogging into the twenty-first century. Computers and Structures, 73: 1-31, 1999.
  • [36] A.S. Nowak, K.R. Collins. Reliability of structures. McGraw-Hill, 2000.
  • [37] E. Pabisek. Hybrid FEM/ANN identification of a model of equivalent material basing on measurements of structure displacements (in Polish). Proc. 50th Polish Civil Eng. Conf, Krynica, Poland, September 12-17, 2005, Vol. 2: 81-88. Gdańsk, 2005.
  • [38] E. Pabisek. On-line training of neural network based constitutive models (in Polish). Report on current research in grant [4], paper in preparation for publishing. Cracow Univ. of Technology, 2005.
  • [39] E. Pabisek, M. Jakubek, Z. Waszczyszyn. A fuzzy network for the analysis of experimental structural engineering problems. In: L. Rutkowski, J. Kacprzyk, eds., Neural Networks and Soft Computing. Proc. 6th Int. Conf., Zakopane, 771-777. Springer. Berlin-Heidelberg, Germany, 2003.
  • [40] Th.L. Paez. Neural networks in mechanical system simulation, identification and assessment. Shock and Vibration, 1: 177-199, 1993.
  • [41] M. Papadrakakis, V. Papadopoulos, N.D. Lagaros. Structural reliability analysis of elastic-plastic structures using neural networks and Monte Carlo simulation. Comp. Meth. Appl. Mech. Eng., 136: 145-163, 1996.
  • [42] G. Piątkowski. Detection of Damage in Structural Elements Using Artificial Neural Networks (in Polish). Ph.D. Thesis. Dept. of Building and Environmental Eng., Rzeszów Univ. of Technology, Rzeszów, Poland, 2003.
  • [43] G. Piątkowski, L. Ziemiański, The solution of an inverse problem in plates by means of artificial neural networks. In: L. Rutkowski et al., eds., Lecture Notes on Artificial Intelligence, LNAI 3070, Artificial Intelligence and Soft Computing - ICAISC 2004, 7th Intern. Conf, Zakopane, Poland, June 2004, 1081-1086. Springer-Verlag, Berlin-Heidelberg, 2004.
  • [44] J.E. Pulido, T.L. Jacobs, E.C. Prates de Lima. Structural reliability using Monte Carlo simulation with variance reduction techniques on elastic-plastic structures. Computers and Structures, 43: 419-430, 1992.
  • [45] P. Rojas. Neural Networks - A Systematic Introduction. Springer Verlag, Berlin-Heidelberg, 1996.
  • [46] H.S. Shin, G.N. Pande. On self-learning finite element codes based on monitored response of structures. Computers and Geotechniques, 27: 161-178, 2000.
  • [47] Z. Waszczyszyn, ed. Neural Networks in the Analysis and Design of Structures. CISM Courses and Lectures No. 404, Springer, Wien-New York, 1999.
  • [48] Z. Waszczyszyn. Neurocomputing and finite element method. In: T. Burczyński, P. Fedeliński, E. Majchrzak, eds., Computer Methods in Mechanics, Proc. 1st CE ACM Conf. and 15th Intern. Conf. CMM-2003, Gliwice/Wisła, Poland, June 3-6, 2003. CD-ROM, 10 pages. Silesian Univ. of Technology, Gliwice, 2003.
  • [49] Z. Waszczyszyn, Cz. Cichoń, M. Radwańska. Stability of Structures by Finite Element Methods. Elsevier, Amsterdam, 1999.
  • [50] Z. Waszczyszyn, E. Pabisek. Hybrid NN/FEM analysis of the elastoplastic plane stress problem. Computer Assisted Mechanics and Engineering Sciences, 6: 177-188, 1999.
  • [51] Z. Waszczyszyn, L. Ziemiański. Neural networks in mechanics of structures and materials - new results and prospects of applications. Computers and Structures, 79: 2261-76, 2003.
  • [52] Z. Waszczyszyn, L. Ziemiański. Neural networks in the identification analysis of structural mechanics problems. In: Z. Mróz and G. Stavroulakis, eds., Parameter Identification of Materials and Structures, CISM Courses and Lectures No. 469, 265-340. Springer, Wien-New York, 2005.
  • [53] E. Zelle. SNNS - Stuttgart Neural Network Simulator. User's Manuał, Version 4-1- Univ. Stuttgart, 1995.
Typ dokumentu
Identyfikator YADDA
JavaScript jest wyłączony w Twojej przeglądarce internetowej. Włącz go, a następnie odśwież stronę, aby móc w pełni z niej korzystać.