Summary
A state of art on the application of neural networks in Stochastic Mechanics is presented. The use of these Artificial Intelligence numerical devices is almost exclusively carried out in combination with Monte Carlo simulation for calculating the probability distributions of response variables, specific failure probabilities or statistical quantities. To that purpose the neural networks are trained with a few samples obtained by conventional Monte Carlo techniques and used henceforth to obtain the responses for the rest of samples. The advantage of this approach over standard Monte Carlo techniques lies in the fast computation of the output samples which is characteristic of neural networks in comparison to the lengthy calculation required by finite element solvers. The paper considers this combined method as applied to three categories of stochastic mechanics problems, namely those modelled with random variables, random fields and random processes. While the first class is suitable to the analysis of static problems under the effect of values of loads and resistances independent from time and space, the second is useful for describing the spatial variability of material properties and the third for dynamic loads producing random vibration. The applicability of some classical and special neural network types are discussed from the points of view of the type of input/output map**, the accuracy and the numerical efficiency.
Similar content being viewed by others
References
Atkinson, K.E. (1997),The Numerical Solution of Integral Equations of the Second Kind, Cambridge University Press, Cambridge.
Ayyub, B. and McCuen R.H. (1995), “Simulation-based reliability methods,” In Sundararajan, C. (Ed.),Probabilistic Structural Mechanics Handbook, Chapman and Hall, New York.
Bender, A.M. and Orszag, S.A. (1978),Advanced Mathematical Methods for Scientific and Engineers, McGraw-Hill, New York.
Binh, T.T. and Korn, U. (1997),Scalar Optimization with Linear and Nonlinear Constraints using Erolution Strategies, In Reusch, B. (Ed.),Lecture Notes in Computer Science, Springer Verlag, Berlin.
Box, G.E.P. and Draper, N.R. (1987),Empirical Model Building and Response Surfaces, John Wiley and Sons, New York.
Brockwell, P.J. and Davies, R.A. (1996),Introduction to Time Series and Forecasting, Springer Verlag, New York.
Cabral, S.V.S. and Katafygiotis, L.S. (2001), “Neural network based response surface method and adaptive importance sampling for reliability analysis of large structural systems,” In:Structural Safety and Reliability-ICOSSAR 01. Edited by R.B. Corotis, G.I. Schuëller, M. Shinozuka, pg 46 (abstract), CD-ROM (paper), A.A. Balkema Publishers, Lisse, The Netherlands.
Chapman, O.J. and Crossland, A.D. (1995), “Neural networks in probabilistic structural mechanics,” In Sundararajan, C. (Ed.),Probabilistic Structural Mechanics Handbook, Chapman and Hall, New York.
Chen, H., Qi, G., Yang, J. and Amini, F. (1995), “Neural network for dynamic model identification,”Journal of Engineering Mechanics,121, 1377–1381.
Cichocki, A. and Unbehauen, R. (1993),Neural Networks for Optimization and Signal Processing, John Wiley and Sons, Chichester.
Cressie, N.A.C. (1993),Statistics for Spatial Data, John Wiley and Sons, New York.
Ditlevsen, O. and Madsen, H.O. (1999),Structural Reliability Methods, John Wiley and Sons, Chichester.
Faravelli, L. (1989), “Response-surface approach for reliability analysis,”Journal of Engineering Mechanics,115, 2763–2781.
Fenton, G.A. and Vanmarcke, E.H. (1990), “Simulation of random fields via local average subdivision,”Journal of Engineering Mechanics,116, 1733–1749.
Ghanem, R.G. and Spanos, P.D. (1991),Stochastic Finite Elements: A Spectral Approach, Springer Verlag, New York.
Ghanem, R.G. and Spanos, P.D. (1997), “Spectral techniques for stochastic finite elements”,Archives of Computational Methods in Engineering,4, 63–100.
Hartman, E. J., Keeler, J. D. and Kowalski, J. M. (1990), “Layered neural networks with Gaussian hidden units as universal approximations,”Neural Computation,2, 210–215.
Hernández, D.B. (1995),Lectures on Probability and Second Order Random Fields, World Scientific, Singapore.
Hornik, K.M., Stinchcommbe, M. and White, H (1989), “Multilayer feedforward networks are universal approximators,”Neural Networks,2, 359–366.
Hurtado, J.E. (2001a), “Stochastic finite element analysis using point estimates”Proceedings of the European Conference on Computational Mechanics ECCM-01 (CD-ROM), Cracow, Poland.
Hurtado, J.E. (2001b), “Analysis of one-dimensional stochastic finite elements using neural networks,”Probabilistic Engineering Mechanics (to appear).
Hurtado, J.E. and Barbat, A.H. (1998), “Monte Carlo techniques in computational stochastic mechanics,”Archives of Computational Methods in Engineering,5, 3–30.
Hurtado, J.E. and Alvarez, D.A. (2000), “Reliability assessment of structural systems using neural networks,” InProceedings of the European Congress on Computational Methods in Applied Sciences and Engineering ECCOMAS-2000 (CD-ROM), ECCOMAS, Barcelona.
Hurtado, J.E. and Alvarez, D.A. (2001), “Neural network-based reliability analysis: A comparative study”,Computational Methods in Applied Mechanics and Engineering (to appear).
Hurtado, J.E., Alvarez, D.A. and Barbat, A.H. (2001a), “Monte Carlo analysis of structural systems using neural networks,” InMonte Carlo Simulation, edited by Schuëller, G.I. and Spanos, P.D., pg. 265–271, A.A. Balkema, Publishers, Lisse, The Netherlands.
Hurtado, J.E. and Barbat, A.H. (2001), “Analysis of stochastic finite elements via neural classifiers”, InStructural Safety and Reliability-ICOSSAR 01, edited by R.B. Corotis, G.I., Schuëller, M. Shinozuka, pg 132 (abstract), CD-ROM (paper), A.A. Balkema Publishers, Lisse, The Netherlands.
Hurtado, J.E., Londoño, J.M. and Meza, M.A. (2001b), “On the applicability of neural networks for soil dynamics amplification analysis,”Soil Dynamics and Earthquake Engineering,21, 619–631.
Idriss, I.M. and Sun, J. (1992),User's Manual for SHAKE-91, University of California, Richmond.
Ishibuchi, H. and Tanaka, H. (1987), “Fuzzy regression analysis using neural networks,”Fuzzy Sets and Systems,50, 257–265.
Jang, J.S.R., Sun, C.T. and Mizutani, E. (1997),Neuro-Fuzzy and Soft Computing, Prentice Hall, Upper Saddle River.
Kleiber, M. and Hien, T.D. (1992),The Stochastic Finite Element Method, John Wiley and Sons, Chichester.
Lin, C.T. and Lee, C.S.G. (1996),Neural Fuzzy Systems, Prentice Hall, Upper Saddle River.
Luo, F.L. and Unbehauen, R. (1998),Applied Neural Networks for Signal Processing, Cambridge University Press, Cambridge.
Mantoglu, A. (1987), “Digital simulation of multivariate two- and three-dimensional stochastic processes with a spectral turning bands method,”Mathematical Geology,19, 129–149.
McCulloch, W.S. and Pitts, W. (1943), “A logical calculus of ideas immanent in nervous activity,”Bulletin of Mathematical Biophysics,5, 115–133.
Melchers, R.E. (1999),Structural Reliability: Analysis and Prediction, 2nd Edition, John Wiley and Sons, Chichester.
Noble, B. (1958),Methods based on the Wiener-Hopf Technique for the Solution of Partial Differential Equations, Chelsea Publishing Company, New York.
Papadrakakis, M., Papadopoulos, V., Lagaros, N.D. (1996), “Structural reliability analysis of elastic-plastic structures using neural networks and Monte Carlo simulation”,Computer Methods in Applied Mechanics and Engineering, 145–163.
Pollock, D.S.G. (1999),A Handbook of Time-Series analysis, Signal Processing and Dynamics, Academic Press, San Diego.
Press, W.H., Teukolsky, S.A., Vetterling, W.T. and Flannery, B.P. (1992),Numerical Recipes in FORTRAN, 2nd edition. Cambridge University Press, Cambridge.
Resnikoff, H.L. and Wells, R.O. (1998),Wavelet Analysis, Springer Verlag, New York.
Ripley, B.D. (1996),Pattern Recognition and Neural Networks, Cambridge University Press, Cambridge.
Rubinstein, R.Y. (1992),Monte Carlo Optimization, Simulation and Sensitivity of Queuing Networks, Krieger Publishing Company, Malabar, FL.
Saraiva, J.M.F. and Ebecken, N.F.F. (1998), “Application of neural networks in structural reliability analysis,”Revista Internacional de Métodos Numéricos para Cálculo y Diseño en Ingeniería,14, 167–180. (In Portuguese).
Sasaki, T. (2001), “A neural network-based response surface approach for computing failure probabilities,” InStructural Safety and Reliability-ICOSSAR 01, edited by R.B. Corotis, G.I. Schuëller, M. Shinozuka, pg 257 (abstract), CD-ROM (paper), A.A. Balkema Publishers, Lisse, The Netherlands.
Schuëller, G.I. and Stix, R. (1987), “A critical appraisa of methods to determine failure probabilities”,Structural Safety 4, 293–309.
Shinozuka, M. and Sato, Y. (1967), “Simulation of nonstationary random processes,”Journal of the Engineering Mechanics Division ASCE,93, 11–40.
Shinozuka, M. and Nomoto, T. (1980),Response Variability due to Spatial Randomness of Material Properties, Technical Report, Dept. of Civil Engineering, Columbia University, New York.
Shinozuka, M. (1987), “Stochastic fields and their digital simulation”, In Schuëller, G.I. and Shinozuka, M. (Eds.),Stochastic Methods in Structural Dynamics, Martinus Nijhoff Publishers, Dordrecht.
Soong, T.T. and Grigoriu, M. (1993),Random Vibration of Mechanical and Structural Systems, Prentice Hall, Upper Saddler River.
Szidarovszky, F. and Bahill, A.T. (1992),Linear System Theory, CRC Press, Boca Ratón.
Tajimi, H. (1960), “A statistical method of determining the maximum response of a building structure during an earthquake”,Proc. of the Second World Conference on Earthquake Engineering, Vol.2, 781–797, Tokio.
Theodoridis, S. and Koutroumbas, K. (1999),Pattern Recognition, Academic Press, London.
Wan, E.A. (1993),Finite Impulse Response Neural Networks With Applications in Time Series Prediction, Ph.D. Thesis, Stanford University.
Wacszczyszyn, Z. (Ed.) (1999),Neural Networks in the Analysis and Design of Structures, Springer Verlag, Wien.
Yagawa, G. and Okuda, H. (1996), “Neural networks in computational mechanics”,Archives of Computational Methods in Engineering,3, 435–512.
Youla, D.C. (1957), “The solution of a homogeneous Wiener-Hopf Integral equation occurring in the expansion of second-order random functions,”IRE Transactions on Information Theory, September, 187–193.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Hurtado, J.E. Neural networks in stochastic mechanics. ARCO 8, 303–342 (2001). https://doi.org/10.1007/BF02736646
Received:
Issue Date:
DOI: https://doi.org/10.1007/BF02736646