Advertisement

Neural Computing and Applications

, Volume 18, Issue 7, pp 821–832 | Cite as

Improved hybrid wavelet neural network methodology for time-varying behavior prediction of engineering structures

  • Maosen Cao
  • Pizhong Qiao
  • Qingwen Ren
Original Article

Abstract

An improved neuro-wavelet modeling (NWM) methodology is presented, and it aims at improving prediction precision of time-varying behavior of engineering structures. The proposed methodology distinguishes from the existing NWM methodology by featuring the distinctive capabilities of constructing optimally uncoupled dynamic subsystems in light of the redundant Haar wavelet transform (RHWT) and optimizing neural network. In particular, two techniques of imitating wavelet packet transform of RHWT and reconstructing the major crests of power spectrum of analyzed data are developed with the aim of constructing the optimally uncoupled dynamic subsystems from time-varying data. The resulting uncoupled dynamic subsystems make the underlying dynamic law of time-varying behavior more tractable than the raw scale subwaves arose from the RHWT, and they provide a platform for multiscale modeling via individual modeling at the uncoupled dynamic subsystem level. Furthermore, on each uncoupled dynamic subsystem, the technique of optimal brain surgeon in conjunction with a new dynamic mechanism refreshing is employed to optimize the neural network, and the recombination of the modeling outcomes on every subsystem constitutes the overall modeling of time-varying behavior. The improved NMW methodology offers a feasible framework of multiscale modeling due to its flexibility, adaptability and rationality, and it is particularly useful for prediction applications of time-varying behavior of engineering structures. As an illustrative example, the improved NWM methodology is applied to model and forecast dam deformation, and the results show that the methodology possesses positive advantages over the existing multiscale and single scale modeling techniques. The improved NMW methodology is promising and valuable for the safety monitoring and extreme event warning of engineering structures.

Keywords

Prediction of time-varying behavior Wavelet Neural networks Neuro-wavelet modeling Nonlinear analysis Optimization models Subsystems Structural safety Deformation 

Notes

Acknowledgments

This study is partially supported by the National Natural Science Foundations of China (NSFC) (Grant Numbers: 50539030 and 50608027) and the Science & Technology Foundation of Shandong Provincial Education Department (Grant Number: J07YE04-32426). The support provided by the Wood Materials and Engineering Laboratory (WMEL) at Washington State University to the first author is gratefully acknowledged.

References

  1. 1.
    Dascal O (1987) Postconstruction deformations of rockfill dams. J Geotech Eng Div 113(1):46–59. doi: 10.1061/(ASCE)0733-9410(1987)113:1(46) CrossRefGoogle Scholar
  2. 2.
    Habibagahi G (2002) Post-construction settlement of rockfill dams analyzed via adaptive network-based fuzzy inference systems. Comput Geotech 29(3):211–233. doi: 10.1016/S0266-352X(01)00025-8 CrossRefGoogle Scholar
  3. 3.
    Touileb BN, Bonnelli S, Anthiniac P, Carrere A, Debordes D, La Barbera G, Bani A, Mazza G (2000) Settlement by wetting of the upstream rockfills of large dams. In: Proceedings of the 53rd Canadian geotechnical conference, Montreal, vol 1, pp 263–270Google Scholar
  4. 4.
    Szostak-Chrzanowski A, Chrzanowski A, Massiera M (2005) Use of deformation monitoring results in solving geomechanical problems––case studies. Eng Geol 79(1–2):3–12. doi: 10.1016/j.enggeo.2004.10.014 CrossRefGoogle Scholar
  5. 5.
    Trifunac MD, Hudson DE (1971) Analysis of the Pacoima dam accelerogram—San Fernando, California, earthquake of 1971. Bull Seismol Soc Am 61(5):1393–1411Google Scholar
  6. 6.
    Wu WM, Wang SS (2007) One-dimensional modeling of dam-break flow over movable beds. J Hydraul Eng 133(1):48–58. doi: 10.1061/(ASCE)0733-9429(2007)133:1(48) CrossRefGoogle Scholar
  7. 7.
    Bayrak T (2007) Modeling the relationship between water level and vertical displacements on the Yamula Dam, Turkey. Nat Hazards Earth Syst Sci 7(2):289–297CrossRefGoogle Scholar
  8. 8.
    Hudnut K, Behr J (1998) Continuous GPS monitoring of structural deformation at Pacoima dam, California. Seismol Res Lett 69(4):299–308Google Scholar
  9. 9.
    ICOLD (1988) World registers of dams. International Commission on Large Dams, ParisGoogle Scholar
  10. 10.
    Szostak-Chrzanowski A, Massiéra M, Chrzanowski A, Le Hoan F, Whitaker C (2002) Verification of material parameters of earthen dams at diamond valley lake using geodetic measurements. In: Proceedings of the XXII FIG international congress, WashingtonGoogle Scholar
  11. 11.
    Pytharouli SI, Stiros SC (2005) Ladon dam (Greece) deformation and reservoir level fluctuations, evidence for a causative relationship from the spectral analysis of a geodetic monitoring record. Eng Struct 27(3):361–370. doi: 10.1016/j.engstruct.2004.10.012 CrossRefGoogle Scholar
  12. 12.
    De Sortisa A, Paoliani P (2007) Statistical analysis and structural identification in concrete dam monitoring. Eng Struct 29(1):110–120. doi: 10.1016/j.engstruct.2006.04.022 CrossRefGoogle Scholar
  13. 13.
    Hudnut K (1996) Continuous GPS monitoring of dam deformation. Eos Trans AGU 77(46):F139Google Scholar
  14. 14.
    Wu ZR, Su HZ (2005) Dam health diagnosis and evaluation. Smart Mater Struct 14:S130–S136. doi: 10.1088/0964-1726/14/3/016 CrossRefGoogle Scholar
  15. 15.
    ICOLD (2000) Bulletin 118, automated dam monitoring systems––guidelines and case histories. International Commission on Large Dams, ParisGoogle Scholar
  16. 16.
    Cao ZX, Pender G, Wallis S, Carling P (2004) Computational dam-break hydraulics over erodible sediment bed. J Hydraul Eng 130(7):689–703. doi: 10.1061/(ASCE)0733-9429(2004)130:7(689) CrossRefGoogle Scholar
  17. 17.
    Barnaba C, Priolo1 E, Vuan1 A, Romanelli M (2007) Site effect of the strong-motion site at Tolmezzo-Ambiesta dam in northeastern Italy. Bull Seismol Soc Am 97(1B):339–346Google Scholar
  18. 18.
    Fedele R, Maier G, Miller B (2006) Health assessment of concrete dams by overall inverse analyses and neural networks. Int J Fract 137(1–4):151–172. doi: 10.1007/s10704-006-6582-7 CrossRefGoogle Scholar
  19. 19.
    Tayfur G, Swiatek D, Wita A, Singh VP (2005) Case study, finite element method and artificial neural network models for flow through Jeziorsko Earthfill dam in Poland. J Hydraul Eng 131(6):431–440. doi: 10.1061/(ASCE)0733-9429(2005)131:6(431) CrossRefGoogle Scholar
  20. 20.
    Waszczyszyn Z, Ziemiański L (2001) Neural networks in mechanics of structures and materials–new results and prospects of applications. Comput Struct 79:2261–2276. doi: 10.1016/S0045-7949(01)00083-9 CrossRefGoogle Scholar
  21. 21.
    Deng XS, Wang XZ (2004) A neural network methodology for dam deformation predictions using historical displacements. Chin J Hydropower Autom Dam Monit 28(2):51–53Google Scholar
  22. 22.
    Li SJ, Liu YX, Liu YJ (2003) Dam deformation prediction by evolving artificial neural network. Chin J Rock Soil Mech 24(4):635–638Google Scholar
  23. 23.
    Mata J, Portela E, Dias J (2007) Application of neural networks to dam safety control. In: Pina C, Portela E, Gomes JP (eds) Proceedings of 5th international conference on dam engineering. LNEC, Lisbon, pp 315–324Google Scholar
  24. 24.
    Yang J, Wu ZR, Gu CS (2001) Dam deformation monitoring model and forecast based on BP algorithm of artificial neural networks. Chin J Xi’an Univ Technol 17(1):25–29. doi: 10.1016/S1006-1266(07)60006-6 CrossRefMathSciNetGoogle Scholar
  25. 25.
    Aussem A, Murtagh F (1997) Combining neural network forecasts on wavelet-transformed time series. Connect Sci 9(1):113–121. doi: 10.1080/095400997116766 CrossRefGoogle Scholar
  26. 26.
    Geva AB (1998) ScaleNet-Multiscale neural-network architecture for time series prediction. IEEE Trans Neural Netw 9(5):1471–1482. doi: 10.1109/72.728396 CrossRefGoogle Scholar
  27. 27.
    Aussem A, Murtagh F (2001) Wed traffic demand prediction using wavelet-based multiscale decomposition. Int J Intell Syst 16:215–236. doi: 10.1002/1098-111X(200102)16:2<215::AID-INT50>3.0.CO;2-# zbMATHCrossRefGoogle Scholar
  28. 28.
    Zhang BL, Coggins R, Jabri MA et al (2001) Multiresolution prediction for futures trading using wavelet decompositions. Trans Neural Netw 12:765–775. doi: 10.1109/72.935090 CrossRefGoogle Scholar
  29. 29.
    Zheng G, Strack JK, Campbell JG, Murtath F (1999) Multiscale transforms for filtering financial data streams. J Comput Intell Finance 7:18–35Google Scholar
  30. 30.
    Holschneider M, Kronland-Martinet R, Morlet J, Tchamitchian P (1989) Wavelets, time-frequency methods and phase space. In: A real-time algorithm for signal analysis with the help of the wavelet transform. Springer, Berlin, pp 289–297Google Scholar
  31. 31.
    Shensa MJ (1992) Discrete wavelet transforms, wedding the à trous and Mallat algorithms. Trans Signal Process 40(10):2464–2482. doi: 10.1109/78.157290 zbMATHCrossRefGoogle Scholar
  32. 32.
    Cao M, Qiao P (2008) Neural network committee-based sensitivity analysis strategy for geotechnical engineering problems. Neural Comput Appl 17(5–6):509–519. doi: 10.1007/s00521-007-0143-5 Google Scholar
  33. 33.
    Hassibi B, Stork DG (1993) Second-order derivatives for network pruning, optimal brain surgeon. Adv Neural Inf Process Syst 5:164–171Google Scholar
  34. 34.
    Valsakumar MC, Satyanarayana SVM, Sridhar V (1997) Signature of chaos in power spectrum. Pramana 48(1):69–85. doi: 10.1007/BF02845623 CrossRefGoogle Scholar
  35. 35.
    Jang J-SR, Sun C-T, Mizutani E (1997) Neuro-fuzzy and soft computing, a computational approach to learning and machine intelligence. Prentice-Hall, Upper Saddle RiverGoogle Scholar
  36. 36.
    Nørgaard M, Ravn O, Poulsen NK, Hansen LK (2000) Neural networks for modeling and control of dynamic systems. Springer, LondonGoogle Scholar
  37. 37.
    Zhang S, Liu HX, Gao DT, Du SD (2003) Determining the input dimension of a neural network for nonlinear time series prediction. Chin Phys 12(6):594–598. doi: 10.1088/1009-1963/12/6/304 CrossRefGoogle Scholar
  38. 38.
    Sragner L, Horvath G (2003) Improved model order estimation for nonlinear dynamic systems.In: Proceedings of the second IEEE international workshop on intelligent data acquisition and advanced computing systems, technology and applications, Lviv, pp 266–271Google Scholar
  39. 39.
    MacKay D (1996) Bayesian non-linear modeling for the 1993 energy prediction competition in maximum entropy and Bayesian methods. In: Heidbreder G (ed) Kluwer, Dordrecht, pp 221–234Google Scholar
  40. 40.
    Maier HR, Dandy GC (2001) Neural network based modelling of environmental variables: a systematic approach. Math Comput Model 33:669–682. doi: 10.1016/S0895-7177(00)00271-5 zbMATHCrossRefGoogle Scholar
  41. 41.
    Duffy M, Hill C, Whitaker C, Chrzanowski A, Lutes J, Bastin G (2001) An automated and integrated monitoring program for Diamond Valley Lake in California. In: Proceedings of the 10th FIG international symposium on deformation measurements, Orange, pp K-1–K-23Google Scholar

Copyright information

© Springer-Verlag London Limited 2009

Authors and Affiliations

  1. 1.Department of Engineering Mechanics, College of Civil EngineeringHohai UniversityNanjingPeople’s Republic of China
  2. 2.Department of Civil and Environmental EngineeringWashington State UniversityPullmanUSA
  3. 3.M. Cao College of Hydraulic and Civil EngineeringShandong Agricultural UniversityTaianPeople’s Republic of China

Personalised recommendations