Neural network aided stochastic computations and earthquake engineering

• Autorzy: Lagaros N. D. , Papadrakakis M. , Fragiadakis M. , Stefanou G. , Tsompanakis Y.
• Konferencja: Neural Networks and Soft Computing/International Symposium (30.06-02.07.2005 ; Cracow, Poland)
• Języki publikacji: EN

Abstrakty

EN

This article presents recent developments in the field of stochastic finite element analysis of structures and earthquake engineering aided by neural computations. The incorporation of Neural Networks (NN) in this type of problems is crucial since it leads to substantial reduction of the excessive computational cost. In particular, a hybrid method is presented for the simulation of homogeneous non-Gaussian stochastic fields with prescribed target marginal distribution and spectral density function. The presented method constitutes an efficient blending of the Deodatis-Micaletti method with a NN based function approximation. Earthquake-resistant design of structures using Probabilistic Safety Analysis (PSA) is an emerging field in structural engineering. It is investigated the efficiency of soft computing methods when incorporated into the solution of computationally intensive earthquake engineering problems.

Słowa kluczowe

EN

neural network; computation aids; stochastic computation; earthquake engineering

PL

sieci neuronowe; środki obliczeniowe; rachunek stochastyczny

• Wydawca: Instytut Podstawowych Problemów Techniki PAN
• Czasopismo: Computer Assisted Mechanics and Engineering Sciences
• Rocznik: 2007
• Tom: Vol. 14, No. 2
• Strony: 251--275
• Opis fizyczny: Bibliogr. 31 poz., rys., tab., wykr.

Twórcy

autor

Lagaros N. D.

autor

Papadrakakis M.

autor

Fragiadakis M.

autor

Stefanou G.

autor

Tsompanakis Y.

• Institute of Structural Analysis and Seismic Research, School of Civil Engineering National Technical University Zografou Campus, Athens 15780, Greece

Bibliografia

• [1] G. Deodatis, R.C. Micaletti. Simulation of.highly skewed non-Gaussian stochastic processes. J. Engrg. Mech. (ASCE) 127: 1284-1295, 2001.
• [2] S. Fahlman. An Empirical Study of Learning Speed in Back-Propagation Networks. Carnegie Mellon: CMU-CS-88-162, 1988.
• [3] M. Grigoriu. Crossings of non-Gaussian translation processes. J. Engrg. Mech. (ASCE), 110: 610-620, 1984.
• [4] M. Grigoriu. Simulation of stationary non-Gaussian translation processes. J. Engrg. Mech. (ASCE), 124: 121-126, 1998.
• [5] K.R. Gurley, M. Tognarelli, A. Kareem. Analysis and simulation tools for wind engineering. Prób. Engrg. Mech., 12: 9-31, 1997.
• [6] M. Fragiadakis, N.D. Lagaros, M. Papadrakakis, Risk assessment of structures using neural networks. Proceedings of the 5th International Congress on Computational Mechanics (GRACM 05), Limassol, Cyprus, June 29 - July 1, 2005.
• [7] J.E. Hurtado, D.A. Alvarez. Neural-network-based reliability analysis: a comparative study. Comp. Meth. Appl. Mech. Engrg., 191: 113-132, 2002.
• [8] J.E. Hurtado, Neural network in stochastic mechanics. Arch. Comp. Meth. Engrg. (State of the Art Reviews), 8(3): 303-342, 2001.
• [9] S.L. Kramer, Geotechnical Earthquake Engineering. Prentice-Hall, Englewood Cliffs, NJ, 1996.
• [10] N.D. Lagaros, M. Papadrakakis. Learning improvement of neural networks used in structural optimization. Adv. Engrg. Software, 35: 9-25, 2004.
• [11] N.D. Lagaros, G. Stefanou, M. Papadrakakis. An enhanced hybrid method for the simulation of highly skewed non-Gaussian stochastic fields. Comp. Meth. Appl. Mech. Engrg., 194(45-47): 4824-4844, 2005.
• [12] F. Masters, K.R. Gurley. Non-Gaussian simulation: Cumulative distribution function map-based spectral correction. J. Engrg. Mech. (ASCE), 129: 1418-1428, 2003.
• [13] D.S. McCorkle, K.M. Bryden, C.G. Carmichael. A new methodology for evolutionary optimization of energy systems. Comp. Meth. Appl. Mech. Engrg., 192: 5021-5036, 2003.
• [14] J. Nie, B.R. Ellingwood. A new directional simulation method for system reliability. Part II: application of neural networks. Prób. Engrg. Mech., 19(4): 437-447, 2004.
• [15] M. Papadrakakis, N.D. Lagaros. Reliability-based structural optimization using neural networks and Monte Carlo simulation. Comp. Methods Appl. Mech. Engrg., 191: 3491-3507, 2002.
• [16] 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. Engrg., 136: 145-163, 1996.
• [17] I. Papaioannou, M. Fragiadakis, M. Papadrakakis. Inelastic analysis of framed structures using the fiber approach. Proceedings of the 5th International Congress on Computational Mechanics (GRACM 05), Limassol, Cyprus, June 29 - July 1, 2005.
• [18] K.K. Phoon, S.P. Huang, S.T. Quek. Simulation of second-order processes using Karhunen-Loeve expansion.Comp. Struct., 80: 1049-1060, 2002.
• [19] R. Popescu, G. Deodatis, J. H. Prevost. Simulation of non-Gaussian stochastic fields with applications to soil liquefaction: Two case studies. in: Proc. of the 12th ASCE Engrg. Mech. Spec. Conference, Reston, Va., 1998.
• [20] K.A. Porter, J.L. Beck, R.V. Shaikhutdinov. Sensitivity of Building Loss Estimates to Major Uncertain Variables. Earthquake Spectra, 18: 719-743, 2002.
• [21] M. Riedmiller, H. Braun. A direct adaptive method for faster back-propagation learning: The RPROP algorithm. In: H. Ruspini, ed., Proc. of the IEEE International Conference on Neural Networks (ICNN), San Francisco, USA, pp. 586-591, 1993.
• [22] M. Riedmiller. Advanced Supervised Learning in Multi-layer Perceptrons: From Back-propagation to Adaptive Learning Algorithms. University of Karlsruhe, 1994.
• [23] W. Schiffmann, M. Joost, R. Werner. Optimization of the back-propagation algorithm for training multi-layer perceptrons. Technical report, Institute of Physics, University of Koblenz, 1993.
• [24] G.I. Schueller, ed. Computational methods in stochastic mechanics and reliability analysis. Comp. Meth. Appl. Mech. Engrg., special issue 194(12-16): 1251-1795, 2005.
• [25] N. Shome, CA. Cornell. Probabilistic seismic demand analysis of non-linear structures. Report No. RMS-35, RMS Program, Stanford University, Stanford, USA, 1999.
• [26] Y. Tsompanakis, N.D. Lagaros, G.E. Stavroulakis, Efficient neural network models for structural reliability analysis and identification problems. 8th International Conference on the Application of Artificial Intelligence to Civil, Structural and Environmental Engineering (AICC 2005), Rome, Italy, August 30 - September 2, 2005.
• [27] D. Vamvatsikos, CA. Cornell. Incremental dynamic analysis. Earth Engrg. Struct. Dyn., 31: 491-514, 2002.
• [28] F. Yamazaki, M. Shinozuka. Digital generation of non-Gaussian stochastic fields. J. Engrg. Mech. (ASCE), 114:1183-1197, 1988.
• [29] J. Zacharias, C Hartmann, A. Delgado. Damage detection on crates of beverages by artificial neural networks trained with finite-element data. Comp. Meth. Appl. Mech. Engrg., 193: 561-574, 2004.
• [30] Z. Waszczyszyn, M. Bartczak. Neural prediction of buckling loads of cylindrical shells with geometrical imperfections. Int. J. Nonhnear Mech., 37(4): 763-776, 2002.
• [31] A. Zerva. Seismic ground motion simulations from a class of spatial variability models. Earth Engrg. Str. Dyn., 21: 351-361, 1992.