Structural Engineering and Mechanics

Techno-Press (테크노프레스)
권호 표지
DOI QR코드

DOI QR Code

A neural network approach for simulating stationary stochastic processes

  • Beer, Michael (Department of Civil Engineering, National University of Singapore) ;
  • Spanos, Pol D. (Ryon Endowed Chair in Engineering, Rice University)
  • Received : 2008.06.11
  • Accepted : 2008.10.08
  • Published : 2009.05.10
⟨ Previous Next ⟩

Abstract

In this paper a procedure for Monte Carlo simulation of univariate stationary stochastic processes with the aid of neural networks is presented. Neural networks operate model-free and, thus, circumvent the need of specifying a priori statistical properties of the process, as needed traditionally. This is particularly advantageous when only limited data are available. A neural network can capture the "pattern" of a short observed time series. Afterwards, it can directly generate stochastic process realizations which capture the properties of the underlying data. In the present study a simple feed-forward network with focused time-memory is utilized. The proposed procedure is demonstrated by examples of Monte Carlo simulation, by synthesis of future values of an initially short single process record.

Keywords

References

  1. Bishop, Ch.M. (1995), Neural Networks for Pattern Recognition. Oxford: Clarendon Press
  2. Govindaraju, R.S. (2000), Artificial Neural Networks in Hydrology I: Preliminary Concepts. ASCE Task Committee on Application of Artificial Neural Networks in Hydrology. J. Hydrologic Eng., ASCE, 5(2), 115-123 https://doi.org/10.1061/(ASCE)1084-0699(2000)5:2(115)
  3. Toth, E., Brath, A. and Montanari, A. (2000), "Comparison of short-term rainfall prediction models for real-time flood forecasting", J. Hydrology, 239(1-4), 132-147 https://doi.org/10.1016/S0022-1694(00)00344-9
  4. Belli, M.R., Conti, M., Crippa, P. and Turchetti, C. (1999), "Artificial neural networks as approximators of stochastic processes", Neural Networ., 12(4-5), 647-658 https://doi.org/10.1016/S0893-6080(99)00017-9
  5. Cai, G.Q. and Wu, C. (2004), "Modeling of bounded stochastic processes", Probabilist. Eng. Mech., 19(3), 197-203 https://doi.org/10.1016/j.probengmech.2004.02.002
  6. Cao, L.J. and Tay, F.E.H. (2003), "Support vector machine with adaptive parameters in financial time series forecasting", IEEE T. Neural Networ., 14(6), 1506-1518 https://doi.org/10.1109/TNN.2003.820556
  7. Cimino, G., Del Duce, G., Kadonaga, L.K., Rotundo, G., Sisani, A., Stabile, G., Tirozzi, B. and Whiticar, M. (1999), "Time series analysis of geological data", Chemical Geology, 161(1-3), 253-270 https://doi.org/10.1016/S0009-2541(99)00091-1
  8. Du, S., Ellingwood, B.R. and Cox, J.V. (2005), "Solution methods and initialization techniques in SFE analysis of structural stability", Probabilist. Eng. Mech., 20(2), 179-187 https://doi.org/10.1016/j.probengmech.2005.05.002
  9. Field, Jr. R.V. and Grigoriu, M. (2004), "On the accuracy of the polynomial chaos approximation", Probabilist. Eng. Mech., 19(1-2), 65-80 https://doi.org/10.1016/j.probengmech.2003.11.017
  10. Furundzic, D. (1998), "Application example of neural networks for time series analysis: Rainfall-runoff modeling", Signal Process., 64(3), 383-396 https://doi.org/10.1016/S0165-1684(97)00203-X
  11. Ghanem, R. and Spanos, P.D. (2003), Stochastic Finite Elements: A Spectral Approach. New York Berlin Heidelberg: Springer, 1991. Mineola, New York: Dover Publications, Revised Edition
  12. Giles, C.L., Lawrence, S. and Tsoi, A.C. (2001), "Noisy time series prediction using a recurrent neural network and grammatical inference", Mach. Learn., 44, 161-183 https://doi.org/10.1023/A:1010884214864
  13. Govindaraju, R.S. (2000), Artificial Neural Networks in Hydrology I: Hydrologic Applications. ASCE Task Committee on Application of Artificial Neural Networks in Hydrology. J. Hydrologic Eng., ASCE, 5(2), 124-137 https://doi.org/10.1061/(ASCE)1084-0699(2000)5:2(124)
  14. Grigoriu, M., Ditlevsen, O. and Arwade, S.R. (2003), "A Monte Carlo simulation model for stationary non-Gaussian processes", Probabilist. Eng. Mech., 18(1), 87-95 https://doi.org/10.1016/S0266-8920(02)00052-8
  15. Haykin, S. (1999), Neural Networks: A Comprehensive Foundation. Upper Saddle River, NJ: Prentice Hall
  16. Hirasawa, K., Mabu, S. and Hu, J. (2006), "Propagation and control of stochastic signals through universal learning networks", Neural Networks, 19(4), 487-499 https://doi.org/10.1016/j.neunet.2005.10.005
  17. Iwan, W.D. and Jensen, H. (1993), "On the dynamic-response of continuous systems including model uncertainty", J. Appl. Mech., Trans., ASME, 60(2), 484-490 https://doi.org/10.1115/1.2900819
  18. Jiang, X. and Adeli, H. (2005), "Dynamic wavelet neural network model for traffic flow forecasting", J. Transp. Eng., 131(10), 771-779 https://doi.org/10.1061/(ASCE)0733-947X(2005)131:10(771)
  19. Lee, S.-C. (2003), "Prediction of concrete strength using artificial neural networks", Eng. Struct., 25, 849-857 https://doi.org/10.1016/S0141-0296(03)00004-X
  20. Li, H. and Kozma, R. (2003), A Dynamical Neural Network Method for Time Series Prediction Using the KIII Model. In: Proceedings of the International Joint Conference on Neural Networks, IJCNN 2003. Portland, OR;2003: IEEE press, 347-352
  21. More, A. and Deo, M.C. (2003), "Forecasting wind with neural networks", Marine Structures, 16, 35-49 https://doi.org/10.1016/S0951-8339(02)00053-9
  22. Ochoa-Rivera, J.C. (2008), "Prospecting droughts with stochastic artificial neural networks", J. Hydrology, 352(1-2), 174-180 https://doi.org/10.1016/j.jhydrol.2008.01.006
  23. Phoon, K.K., Huang, S.P. and Quek, S.T. (2002), "Implementation of Karhunen-Loeve Expansion for simulation using a wavelet-Galerkin scheme", Probabilist. Eng. Mech., 17(3), 293-303 https://doi.org/10.1016/S0266-8920(02)00013-9
  24. Qi, M. and Zhang, G.P. (2008), "Trend time-series modeling and forecasting with neural networks", IEEE T. Neural Networ., 19(5), 808-816 https://doi.org/10.1109/TNN.2007.912308
  25. Sakamoto, S. and Ghanem, R. (2002), "Simulation of multi-dimensional non-gaussian non-stationary random fields", Probabilist. Eng. Mech., 17(2), 167-176 https://doi.org/10.1016/S0266-8920(01)00037-6
  26. Sanchez, M.S. and Sarabia, L.A. (2002), "A stochastic trained neural network for nonparametric hypothesis testing", Chemometr. Intell. Lab. Syst., 63(2), 169-187 https://doi.org/10.1016/S0169-7439(02)00047-3
  27. Schenk, C.A. and Schu$\ddot{e}$ller, G.I. (2005), Uncertainty Assessment of Large Finite Element Systems. Berlin Heidelberg: Springer
  28. Schenk, C.A., Pradlwarter, H.J. and Schu$\ddot{e}$ller, G.I. (2005), "Non-stationary response of large, non-linear finite element systems under stochastic loading", Comput. Struct., 83(14), 1086-1102 https://doi.org/10.1016/j.compstruc.2004.11.018
  29. Schu$\ddot{e}$ller, G.I. (2001), "Computational stochastic mechanics – recent advances", Comput. Struct., 79(22-25), 2225-2234 https://doi.org/10.1016/S0045-7949(01)00078-5
  30. Schu$\ddot{e}$ller, G.I. (2003), On Computational Procedures for Processing Uncertainties in Structural Mechanics. In:Waszczyszyn, Z., Pamin, J., editors. 2nd European Conference on Computational Mechanics, ECCM 2001, Cracow; 2003: CD-ROM, Doc 608, 1-24
  31. Schu$\ddot{e}$ller, G.I., Spanos, P.D. editors. (2001), Monte Carlo simulation: Proceedings of the International Conference on Monte Carlo Simulation 2000. Lisse, Exton, PA: A.A. Balkema
  32. Shi, Z. and Han, M. (2007), "Support vector echo-state machine for chaotic time-series prediction", IEEE T. Neural Networ., 18(2), 359-372 https://doi.org/10.1109/TNN.2006.885113
  33. Spanos, P.D. and Zeldin, B.A. (1998), "Monte Carlo treatment of random fields: A broad perspective", Appl. Mech. Rev., 51, 219-237 https://doi.org/10.1115/1.3098999
  34. Spanos, P.D., Beer, M. and Red-Horse, J. (2007), "Karhunen-Loéve expansion of stochastic processes with a modified exponential covariance kernel", J. Eng. Mech., ASCE, 133(7), 773-779 https://doi.org/10.1061/(ASCE)0733-9399(2007)133:7(773)
  35. Su, M.C. and Chang, H.T. (2001), "A new model of self-organizing neural networks and its application in data projection", IEEE T. Neural Networ., 12(1), 153-158 https://doi.org/10.1109/72.896805
  36. Teoh, E.J., Tan, K.C. and Xiang, C. (2006), "Estimating the number of hidden neurons in a feedforward network using the singular value decomposition", IEEE T. Neural Networ., 17(6), 1623-1629 https://doi.org/10.1109/TNN.2006.880582
  37. Turchetti, C., Conti, M., Crippa, P. and Orcioni, S. (1998), "On the approximation of stochastic processes by approximate identity neural networks", IEEE T. Neural Networ., 9(6), 1069-1085 https://doi.org/10.1109/72.728353
  38. Turchetti, C., Crippa, P., Pirani, M. and Biagetti, G. (2008), "representation of nonlinear random transformations by non-gaussian stochastic neural networks", IEEE T. Neural Networ., 19(6), 1033-1060 https://doi.org/10.1109/TNN.2007.2000055
  39. Vanmarcke, E.H. (1983), Random Fields. Cambridge, MA: MIT Press
  40. Yuen, K.-V., Katafygiotis, L.S. and Beck, J.L. (2002), "Spectral density estimation of stochastic vector processes", Probabilist. Eng. Mech., 17(3), 265-272 https://doi.org/10.1016/S0266-8920(02)00011-5
  41. Zhang, G.P. and Kline, D.M. (2007), "Quarterly time-series forecasting with neural networks", IEEE T. Neural Networ., 18(6), 1800-1814 https://doi.org/10.1109/TNN.2007.896859

Cited by

  1. A Multiwavelet Neural Network-Based Response Surface Method for Structural Reliability Analysis vol.30, pp.2, 2015, https://doi.org/10.1111/mice.12086
  2. A Wavelet Support Vector Machine-Based Neural Network Metamodel for Structural Reliability Assessment vol.32, pp.4, 2017, https://doi.org/10.1111/mice.12257
  3. Bootstrapped Artificial Neural Networks for the seismic analysis of structural systems vol.67, 2017, https://doi.org/10.1016/j.strusafe.2017.03.003
  4. An artificial neural network approach for stochastic process power spectrum estimation subject to missing data vol.52, 2015, https://doi.org/10.1016/j.strusafe.2014.10.001
  5. Polynomial Correlated Function Expansion for Nonlinear Stochastic Dynamic Analysis vol.141, pp.3, 2015, https://doi.org/10.1061/(ASCE)EM.1943-7889.0000855
  6. An Adaptive Wavelet Frame Neural Network Method for Efficient Reliability Analysis vol.29, pp.10, 2014, https://doi.org/10.1111/mice.12117
  7. Non-Stationary Wind Pressure Prediction Based on A Hybrid Decomposition Algorithm of Wavelet Packet Decomposition and Variational Mode Decomposition vol.189, pp.1755-1315, 2018, https://doi.org/10.1088/1755-1315/189/5/052038
  8. Lifetime prediction using accelerated test data and neural networks vol.87, pp.19, 2009, https://doi.org/10.1016/j.compstruc.2008.12.007
  9. A homogenization approach for uncertainty quantification of deflection in reinforced concrete beams considering microstructural variability vol.38, pp.4, 2009, https://doi.org/10.12989/sem.2011.38.4.503
  10. An efficient reliability analysis strategy for low failure probability problems vol.78, pp.2, 2021, https://doi.org/10.12989/sem.2021.78.2.209
  11. Efficient long-term fatigue analysis of deepwater risers in the time domain including wave directionality vol.78, pp.None, 2021, https://doi.org/10.1016/j.marstruc.2021.103002