Artificial neural networks in civil and structural engineering: Ten years of research in Poland

• Autorzy: Waszczyszyn Z.
• Konferencja: Polish Conference on Computer Methods in Mechanics (16 ; 21-24.06.2005 ; Częstochowa, Poland
• Języki publikacji: EN

Abstrakty

EN

This state-of-the-art paper reports the last ten year results, obtained by an informal research group completed of participants of some Polish universities at the Institute of Computer Methods in Civil Engineering (now Institute of Computational Civil Engineering) of the Cracow University of Technology, and supervised by the author of the paper. After a short introduction and brief discussion of ANNs basie ideas, the activities in five areas are described: i) ANNs as a new independent computational tool for the analysis of C&SE problems, ii) neural networks in FEM/ANN hybrid systems developed for the C&SE problems analysis, iii) various problems analyzed by ANNs, iv) modifications of BPNNs (Back-Propagation Neural Networks) and new learning methods, as well as other ANNs than those applied in problems mentioned above, v) promotion of ANNs. The representative six selected study cases are discussed: 1) conerete fatigue failure, 2) buckling of cylindrical shells with geometrical imperfections, 3) acceleration response spectra, 4) reliability of a piane frame, 5) hybrid updating of a thin-walled beam FE model, 6) hybrid identification of equivalent materiał in a perforated strip. Some generał conclusions on prospects of ANNs applications in C&SE are given at the end of the paper.

Słowa kluczowe

EN

artificial neural networks; back-propagation neural network; finite element method; hybrid FEM/ANN system; dvii and structural engineering; Cracow University of Technology; standing Seminar on Applications of ANNs in C&SE

PL

sztuczne sieci neuronowe; metoda elementów skończonych; Politechnika Krakowska

• Wydawca: Instytut Podstawowych Problemów Techniki PAN
• Czasopismo: Computer Assisted Mechanics and Engineering Sciences
• Rocznik: 2006
• Tom: Vol. 13, No. 4
• Strony: 489--512
• Opis fizyczny: Bibliogr. 88 poz., il., tab., wykr.

Twórcy

autor

Waszczyszyn Z.

• Institute of Computational Civil Engineering, Cracow University of Technology ul. Warszawska 2A, 31-155 Kraków, Poland

Bibliografia

• [1] J-Sh.R. Jang, Ch-T. Sun, E. Mizutani. Neuro-Fuzzy and Soft Computing. Prentice-Hall, Upper Saddle River, NJ, 1997.
• [2] S. Haykin. Neural Networks - A Comprehensive Foundation. Prentice-Hall, Upper Saddle River, NJ, 1999.
• [3] Ch.M. Bishop. Pattern Recognition and Machine Learning. Springer Science+Business Media, 2006.
• [4] H. Adeli, C. Yeh. Percerptron learning in engineering design. Microcomputers in Civil Engineering, 4: 247-256, 1989.
• [5] B.H.V. Topping, ed. Artificial Intelligence and Civil Engineering. Civil-Comp Press, Edinburgh, 1991.
• [6] H. Adeli. Neural networks in civil engineering: 1989-2000. Review Article. Computer-Aided Civil and Infrastructure Engineering, 16: 126-142, 2001.
• [7] P. Rojas. Neural Networks - A Systematic Introduction. Springer Verlag, Berlin-Heidelberg, 1996.
• [8] B.H.V. Topping, A. Bahreininejad. Neural Computing for Structural Mechanics. Saxe-Coburg Publications, Edinburgh, 1997.
• [9] K Kartam, I. Flood, J.H. Garrett, eds. Artificial Neural Networks - Fundamentals and Applications. ASCE, New York, 1997.
• [10] I. Flood, K. Kartam, eds. Artificial Neural Networks - Advanced Features and Applications. ASCE, New York, 1998.
• [11] Z. Waszczyszyn, ed. Neural Networks in the Analysis and Design of Structures. CISM Courses and Lectures No. 404, Springer, Wien-New York, 1999.
• [12] Z. Waszczyszyn. Applications of artificial neural networks in structural engineering (in Polish). Proc. 41lst Polish Civil Eng. Conf, Krynica, Poland, 2005, Vol. 9: 251-288. Krynica-Krakow, 1995.
• [13] Z. Waszczyszyn. Some new results in applications of back-propagation neural networks in structural and civil engineering. In: B.H.V. Topping, ed., Advances in Engineering Computational Technology, 173-187. Civil-Comp Ltd, Edinburgh, 1998.
• [14] Z. Waszczyszyn. Neural networks in structural engineering - some recent results and prospects for applications. In: B.H.V. Topping, ed., Computational Mechanics for the Twenty-First Century, Ch. 23, 479-515. Saxe-Coburg Publications, Edinburgh, UK, 2000.
• [15] Z. Waszczyszyn. Neural networks in plasticity. In: ECCOMAS 2000, Proc. European Congress on Comp. Methods in Appl. Sci., and Eng., Barcelona, 2000, Keynote Sessions, Book of Abstracts, p. 91; CD-ROM Proc, 32 pages. CIMNE, Barcelona, 2000.
• [16] Z. Waszczyszyn. Neural networks in structural engineering: some new results. In: S. Valliappan, N. Khalili, eds., Computational mechanics - New Frontiers for the New Millenium, Proc. 1st Asian-Pacific Congress Comp. Mech., Sydney, 2001, Vol. 2: 1311-1320. Elsevier, Amsterdam 2001.
• [17] Z. Waszczyszyn, L. Ziemianski. Neurocomputing and experimental structural mechanics: some new results. Computers and Structures, 79: 2261-2276, 2001.
• [18] Z. Waszczyszyn, L. Ziemianski. Neurocomputing and experimental structural mechanics: some new results, In: K.J. Bathe, ed., Computational Fluid and Solid Mechanics 2003, Proc. 2nd MIT Conference, Cambridge, MA, USA, Vol. 1: 737-741. Elsevier, 2003.
• [19] Z. Waszczyszyn. Neurocomputing and finite element method. In: T. Burczynski, P. Fedeliriski, E. Majchrzak, eds., CMM 2003 Computer Methods in Mechanics, Proc. 1st CEACM Conf. Comp. Mech., 15th Intern. Conf. Comp. Methods in Mech., Gliwice, Poland, 2003, Short Papers, Plenary papers: pp. 15-16; CD-ROM, 10 pages. Silesian TU, Gliwice, 2003.
• [20] Z. Waszczyszyn, L. Ziemianski. Implicit modelling and neural identification in structural engineering. In: M. Schnellenbach-Held, M. Hartman, eds., Next Generation Intelligent Systems in Engineering, Proc. 11th Intern. EG-ICE Workshop, Weimar, 2004, Fortschritt-Berichte, VDI Reihe 4, Bauingenieurwesen, Nr 199: 136-145. VDI Verlag, Diisseldorf, 2004.
• [21] Z. Waszczyszyn, L. Ziemianski. Neurocumputing in the analysis of selected inverse problems of mechanics of structures and materials, Computer Assisted Mechanics and Engineering Sciences, 13: 125-159, 2006.
• [22] Z. Waszczyszyn, L. Ziemianski. Neural networks - New results and prospects of applications in structural engineering, In: C.A. Mota Soares et al., eds., Computational Mechanics - Solids, Structures and Coupled Problems, Proc. Series Computational Mechanics in Appl. Sci., Vol. 6: 555-576. Springer, 2006.
• [23] W. Lakota. Detection and Location of Damage in Beam Structures (in Polish). Ofic. Wyd. Polit. Rzeszowskiej, Rzeszow, 1999.
• [24] L. Ziemianski. Neural Networks in Structural Dynamics - Selected Problems (in Polish). Oficyna Wyd. Politechniki Rzeszowskiej, Rzeszow, 1999.
• [25] G.E. Stavroulakis, G. Bolzon, Z. Waszczyszyn, L. Ziemianski. Inverse analysis, In: R. de Borst, H.A. Mang, eds., Comprehensive Structural Integrity, Vol. 3: Ch. 3.13: 685-717. Elsevier, 2003.
• [26] K. Kuzniar. Analysis of Vibrations of Medium-Height Buildings with Load Bearing Walls Subjected to Mining Tremors Using Neural Networks (in Polish), Civil Engineering Monograph 310. Cracow University of Technology, Cracow, 2004.
• [27] Z. Waszczyszyn, L. Ziemianski: Neural networks in the identification analysis of structural mechanics problems, In: Z. Mroz, G. Stavroulakis, eds., Parameter Identification of Materials and Structures, CISM Lecture Notes No. 469L: 265-340. Springer, Wien-New York, 2005.
• [28] B. Miller, G. Piątkowski, L. Ziemianski. Application of neurocomputing in the parametric identification using dynamic responses. In: N. Lagaros, ed., Intelligent Computational Paradigms in Earthquake Engineering, Ch. 9. Idea Group, Hershey, PA, USA, 2006, (in print).
• [29] K. Kuzniar, Z. Waszczyszyn. Neural networks for the simulation and identification analysis of buildings subjected to paraseismic excitations. In: N. Lagaros, ed., Intelligent Computational Paradigms in Earthquake Engineering, Ch. 11. Idea Group, Hershey, PA, USA, 2007, (in print).
• [30] Z. Waszczyszyn, coordinator. Applications of Artificial Neural Networks in the Analysis of Civil Engineering Problems. Polish Foundation for Science, Subsidy 2001/13. Institute of Comp. Meth. in Civil Eng., Cracow Univ. of Technology, 2001-2004.
• [31] Th.L. Paez. Neural networks in mechanical system simulation, identification and assessment. Shock and Vibration, 1: 177-199, 1993.
• [32] S. Haykin. Kalman Filtering and Neural Networks. John Wiley and Sons, New York, 2001
• [33] Ch.M. Bishop. Neural Networks for Pattern Recognition. Clarendon Press, Oxford, 1995.
• [34] E. Zell, ed. SNNS - Stuttgart Neural Network Simulator. User's Manual, Version 4.1, Univ. Stuttgart, 1995.
• [35] Neural Network Toolbox for Use with MATLAB. User's Guide Version 3. The Math Works Inc., Natick, MA, USA, 1998.
• [36] T. Furukawa, G. Yagawa. Implicit constitutive modelling for viscoplasticity using neural networks. International Journal of Numerical Methods in Engineering, 43: 195-219, 1998.
• [37] Z. Rawicki, R. Obiala, Z. Waszczyszyn. Identification of fracture parameters for dense concrete by means of neuro-fuzzy system ANFIS, Archives of Civil Engineering, 47: 445-461, 2001.
• [38] 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 Conf., Zakopane, 2002. Advances in Soft Computing, 112-117. A Physica-Verlag, Springer, Heidelberg, 2003.
• [39] K. Furtak. Strength of concrete subjected to multiple repeat loadings (in Polish). Archives of Civil Engineering, 30: 677-698, 1984.
• [40] J. Kaliszuk, A. Urbanska, Z. Waszczyszyn, K. Furtak. Neural analysis of concrete fatigue durability on the basis of experimental evidence. Archives of Civil Engineering, 47: 327-339, 2001.
• [41] M. Jakubek, Z. Waszczyszyn. Analysis of concrete failure by the neuro-fuzzy network FWNN. Archives of Civil Engineering, (in print).
• [42] A. Urbanska, Z. Waszczyszyn. Neural analysis of concrete shrinkage. In: L. Rutkowski, J. Kacprzyk, eds., Neural Networks and Soft Computing, Proc. 6th Conf., Zakopane, 2002. Advances in Soft Computing, 784-789. A Physica-Verlag, Springer, Heidelberg, 2003.
• [43] K. Schabowicz. Neural networks in NDT identification of the strength of concrete. Archives of Civil Engineering, 42: 447-469, 2005.
• [44] Z. Waszczyszyn, J. Petit. Identification of characteristics of semi-rigid steel connections by BP neural networks (in Polish). In: J. Brodka, J. Szlendak, eds., Semi-Rigid Connections in Steel Structures, Proc. of Workshop on Semi-Rigid Connections in Steel Structures, Bialystok, 1997, 53-59. Bialystok University of Technology, 1997.
• [45] A. Urbanska, J. Kaliszuk, Z. Waszczyszyn: Neural analysis of semi-rigid tube connections (in Polish). In: J. Ziolko, E. Supernak, eds., Proc. 10th Intern. Scientific-Technical Conf. uMetal Structures - Gdansk 2001", Vol. 2: 325- 334. Gdansk, Poland, 2001.
• [46] M.Jakubek, E. Pabisek, Z. Waszczyszyn. Estimation of parameters of semi-rigid steel connections by a fuzzy network (in Polish). Proc. 48th Polish Civil Eng. Conf., Krynica, Poland, 2002, Vol. 2: 69-76. Opole-Krynica, 2002.
• [47] R. Dancy, D. Jacobs. The Initial Imperfection Data Bank at the Delft University of Technology, P. II, Report LR-559. TU Delft, Faculty of Aerospace Engineering, Delft, The Netherlands, 1988.
• [48] Z. Waszczyszyn, M. Bartczak. Neural prediction of critical loads in compressed cylindrical shells with geometrical imperfections. Non-Linear Mechanics, 37: 2003, 763-775.
• [49] B. Miller, G. Piątkowski, L. Ziemianski. Beam yielding load identification by neural networks. Computer Assisted Mechanics and Engineering Sciences, 6: 449-467, 1999.
• [50] G. Piątkowski. Detection of Damage in Structural Elements by Artificial Neural Networks (in Polish), Ph.D. dissertation. Rzeszow University of Technology, Faculty of Civil and Environmental Engineering. Rzeszow, 2003.
• [51] L. Ziemianski, B. Miller, G. Piątkowski. Application of neurocomputing in the parametric identification using dynamic responses of structural elements - Selected problems. Journal of Theoretical and Applied Mechanics, 48: 667-693, 2004.
• [52] K. Kuzniar, Z. Waszczyszyn. Neural analysis of vibration problems of real flat buildings and data pre-processing. Engineering Structures, 24: 1327-1335, 2002.
• [53] K. Kuzniar, Z. Waszczyszyn. Neural simulation of dynamic response of prefabricated buildings subjected to paraseismic excitations. Computers and Structures, 81: 2353-2360, 2003.
• [54] A.K. Noor. Computational structures technology: leap frogging into the twenty-first century. Computers and Structures, 73: 1-31, 1999.
• [55] M. Papadrakakis, V.N.D. Papadopoulos. Structural reliability analysis of elastic-plastic structures using neural networks and Monte Carlo simulation. Computer Methods in Applied Mechanics and Engineering, 136: 145-163, 1996.
• [56] J. Kaliszuk. Analysis of Reliability of Structural Elements by Artificial Neural Networks (in Polish), Ph.D. dissertation. Zielona Gora University, Faculty of Civil and Environmental Engineering, Zielona Gora, 2005.
• [57] B. Miller. Updating of Mathematical Models to Physical Models (in Polish), Ph.D. dissertation. Rzeszow University of Technology, Faculty of Civil and Environmental Engineering. Rzeszow, 2001.
• [58] L. Ziemianski, B. Miller. Dynamic model updating using neural networks. Computer Assisted Mechanics and Engineering Scences, 7: 781-793, 2000.
• [59] Z. Waszczyszyn, E. Pabisek. Hybrid NN/FEM analysis of the elastoplastic plane stress problem. Computer Assisted Mechanics and Engineering Scences, 6: 177-188, 1999.
• [60] Z. Waszczyszyn, E. Pabisek: Neural network supported FEM analysis of elastoplastic plate bending, Special Issue of TUB Research News, 2000/4: 12-19, Budapest, 2001.
• [61] L. Kaczmarczyk, Z. Waszczyszyn. Neural procedures for the hybrid FEM/NN analysis of elastic plates, Computer Assisted Mechanics and Engineering Sciences, 12: 379-391, 2005.
• [62] J. Ghaboussi et al., Autoprogressive training of neural network constitutive models. International Journal for Numerical Methods in Engineering, 42: 105-126, 1998.
• [63] H.S. Shin, G.N. Pande. On self-learning finite element codes based on monitored response of structures. Computers and Geotechnics, 27: 161-178, 2000.
• [64] 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 2005", Krynica, Poland, 2005, Vol. 2: 81-88, Gdansk, 2005.
• [65] L. Ziemianski. Hybrid neural network/finite element modelling of wave propagation in infinite domains. Computers and Structures, 81: 1099-1109, 2003.
• [66] E. Pabisek, Z. Waszczyszyn. Hybrid FEM/NN analysis of nonmonotone contact of deformable bodies. In: V. Kompi§, J. Sladek and M. Zmindak, eds., Proc. 9th Intern. Conf. on Numerical Methods in Continuum Mechanics NMCM 2003, Zilina, Slovakia, 2003, CD-ROM, 12 pages.
• [67] M. Slonski, Z. Waszczyszyn. Neural prediction of water absorption in the sealing process of a dam ground curtain. In: T. Burczynski et al., eds., Methods of Artificial Intelligence, Proc. Symp. Meth. Artif. Intell. AI-METH 2002: 389-393, Silesian UT, Poland, Gliwice, 2002.
• [68] R. Fedele, G. Maier, B. Miller. Health assessment of concrete dams by overall inverse analyses and neural networks. International Journal of Fracture, 137: 151-172, 2006.
• [69] K. Kądziolka, M.J. Sulewska, Z. Waszczyszyn. Determination of dynamic deformation modulus for non-cohesive soils by artificial neural networks (in Polish). Proc. 48th Polish Civil Eng. Conf., Krynica, Poland, 2002, Vol. 3: 249-256, Opole-Krynica, 2002.
• [70] L. Ziemianski, R. Putanowicz, Z. Waszczyszyn. Neural estimation of proximal femur strength, In: W. Daich, ed., Engineering Applications of Neural Networks, 280-285. Wyd. A. Marszalek, Toruri, Poland, 1999.
• [71] M. Mrowczyńska. Analysis of Accuracy and Efficiency of Lie Land Mapping by Neural Networks (in'Polish), Ph.D. dissertation, Warsaw University of Technology, Faculty of Geodesy and Cartography. Warsaw, 2006
• [72] P. Urbanski, Z. Waszczyszyn. Neural prediction of the technological deterioration rate for flat buildings (in Polish). Proc. 48th Polish Civil Eng. Conf, Krynica, Poland, 2002, Vol. 3: 365-372. Opole-Krynica, 2002.
• [73] M. Jakubek, A. Tomana, L. Zajączkowski, Z. Waszczyszyn. Artificial neural networks in valuation of building lots (in Polish), Proc. 49th Polish Civil Eng. Conf., Krynica, Poland, 2003, Vol. 2: 73-80, Warszawa-Krynica, 2003.
• [74] A. Krok, Z. Waszczyszyn. Kalman filtering for neural prediction of response spectra from mining tremors. Computer and Structures (accepted for publication).
• [75] K. Kuzniar, Z. Waszczyszyn. Neural networks and Principal Component Analysis for identification of building natural periods, Journal of Computations in Civil Engineering, 20: 431-436, 2006.
• [76] L. Kaczmarczyk, Z. Waszczyszyn. Identification of characteristic length of microstructure for second order continuum multiscale model. Computer Assisted Mechanics and Engineering Sciences, 14, 2007 (accepted for publication).
• [77] Z. Waszczyszyn, M. Slonski. Analysis of some problems of experimental mechanics and biomechanics by means of the ANFIS neuro-fuzzy system, Journal of Theoretical and Applied Mechanics, 38: 429-445, 2000.
• [78] Z. Waszczyszyn, M. Slonski. Bayesian neural networks for prediction of response spectra. In: J. Rakowski, T. Lodygowski, eds., Foundations of Civil and Environmental Engineering, Volume dedicated to Prof. A. Garstecki, 7: 343-361. Publishing House of Poznan UT, Poznan, 2006.
• [79] M. Slonski. Baeysian regression approach to concrete fatigue durability prediction, Computer Assisted Mechanics and Engineering Sciences, 13: 655-668, 2006.
• [80] Z. Waszczyszyn. Introduction to artificial neural networks and their applications in structural mechanics, (in Polish). In: Neural Networks, Genetic Algorithms, Fuzzy Sets, 5-36. Polish Association for Computational Mechanics, Rzeszow, 1999.
• [81] K. Kuzniar, E. Mating, Z. Waszczyszyn. Computation of response spectra from mining tremors using neural networks, Soil Dynamics and Earthquake Engineering, 25: 331-339, 2005.
• [82] D.T. Pham, X. Liu, Neural Networks for Identification, Prediction and Control. Springer-Verlag, London, 1995.
• [83] U. Vogel. Calibrating frames. Stahlbau, 10: 295-301, 1985.
• [84] E. Pabisek, J. Kaliszuk, Z. Waszczyszyn. Neural and finite element analysis of a plane steel frame reliability by the Classical Monte Carlo method, In: L. Rutkowski et al., eds., Artificial Intelligence and Soft Computing -ICAISC 2004, Lecture Notes on Artificial Intelligence, LNAI 3070, Proc. 7th Intern. Conf., Zakopane, Poland, 2004, 1081-1086. Springer-Verlag, Berlin-Heidelberg, 2004.
• [85] Z. Waszczyszyn, E. Pabisek. Elastoplastic analysis of plane steel frames by a new superelement. Archives of Civil Engineering, 48: 159-181, 2002.
• [86] M.I. Priswell, J.E. Motterhead. Finite Element Model Updating in Structural Mechanics. Kluwer Academic Publishers, Dordrecht, 1996.
• [87] Y.M.A. Hashash, S. Jung, J. Ghaboussi. Numerical implementation of a neurally based material model in finite element analysis. International Journal for Numerical Methods in Engineering, 59: 989-1005, 2004.
• [88] M. Lefik. Applications of Artificial Neural Networks in Mechanics and Engineering (in Polish). Monograph No. 953. Lodz University of Technology, Lodz, 2005.