Advertisement

Bayesian Inference and RJMCMC in Structural Dynamics: On Experimental Data

  • D. TiboacaEmail author
  • P. L. Green
  • R. J. Barthorpe
  • I. Antoniadou
  • K. Worden
Conference paper
Part of the Conference Proceedings of the Society for Experimental Mechanics Series book series (CPSEMS)

Abstract

This paper is concerned with applying the Reversible Jump Markov Chain Monte Carlo (RJMCMC) algorithm on an MDOF system, within a Bayesian framework, in order to identify its parameters and do model selection simultaneously. Bayesian Inference has been widely used in the area of System Identification (SID) on issues of parameter estimation as well as model selection, due to its advantages of using prior knowledge and penalising model complexity, the Bayesian probability framework has been employed on issues of parameter estimation as well as model selection. Even though the posterior probabilities of parameters are often complex, the use of Markov Chain Monte Carlo (MCMC) sampling methods has made the application of the approach significantly more straightforward in structural dynamics. The most commonly applied MCMC sampling algorithm used within a Bayesian framework in the area of structural dynamics is probably the Metropolis-Hastings method. However, the MH algorithm cannot cover model selection in cases where competing model structures have different number of parameters, as it is not capable of moving between spaces of differing dimension. Hence, a new MCMC algorithm, the Reversible Jump Markov Chain Monte Carlo (RJMCMC), has surfaced in 1995. The RJMCMC sampling algorithm is capable of simultaneously covering both parameter estimation and model selection, while jumping between spaces in which the dimension of the parameter vector varies. Using a Bayesian approach, the RJMCMC method ensures that overfitting is prevented. This work focuses on using the RJMCMC algorithm for System Identification (SID) on experimental time data gathered from an MDOF ‘bookshelf’ type structure. The major issue addressed is that of noise variance. Two models are used, the first one using a single noise variance for the entire structure and the second one employing three different noise variances for the three different levels of the structure. The results presented in the last section show the capabilities of the RJMCMC algorithm as a powerful tool in the SID of dynamical structures.

Keywords

RJMCMC Bayesian inference Structural dynamics MCMC System identification 

Notes

Acknowledgements

The authors would like to acknowledge ‘Engineering Nonlinearity’ EP/K003836/1, an EPSRC funded Programme Grant, for supporting their research (http://www.engineeringnonlinearity.ac.uk/).

References

  1. 1.
    Beck, L.J.: Bayesian updating, model selection and robust stochastic predictions of structural response. In: Proceedings of the 8th International Conference on Structural Dynamics, EURODYN, Leuven (2011)Google Scholar
  2. 2.
    Worden, K., Hensman, J.J.: Parameter estimation and model selection for a class of hysteretic systems using Bayesian inference. Mech. Syst. Signal Process. 32, 153–169 (2012)CrossRefGoogle Scholar
  3. 3.
    Green, P.J.: Reversible jump Markov chain Monte Carlo computation and Bayesian model determination. Biometrika 82, 711–732 (1995)MathSciNetCrossRefzbMATHGoogle Scholar
  4. 4.
    Beck, L.J., Au, S-K.: Bayesian updating of structural models and reliability using Markov chain Monte Carlo simulation. J. Eng. Mech. 391, 128–380 (2002)Google Scholar
  5. 5.
    Tiboaca, D., Green, P.L., Barthorpe, R.J.: Bayesian system identification of dynamical systems using reversible jump Markov chain Monte Carlo. In: Proceedings of IMAC XXXII, Conference and Exposition on Structural Dynamics, Orlando (2014)CrossRefGoogle Scholar
  6. 6.
    Beck, L.J., Muto, M.: Bayesian updating and model class selection for Hysteretic structural models using stochastic simulation. J. Vib. Control 14, 7–34 (2008)CrossRefzbMATHGoogle Scholar
  7. 7.
    Ching, J., Chen, Y.: Transitional Markov Chain Monte Carlo method for Bayesian model updating, model class selection, and model averaging. J. Eng. Mech. 133, 816–832 (2007)CrossRefGoogle Scholar
  8. 8.
    Green, P.L.: Bayesian system identification of nonlinear dynamical systems using a fast MCMC algorithm. In: Proceedings of 8th European Nonlinear Dynamics Conference, ENOC, Vienna (2014)Google Scholar
  9. 9.
    Green, P.L.: Bayesian system identification of a nonlinear dynamical system using a novel variant of simulated annealing. J. Mech. Syst. Signal Process. 52–53, 133–146 (2015)CrossRefGoogle Scholar
  10. 10.
    Green, P.L., Cross, E.J., Worden, K. Bayesian system identification of dynamical systems using highly informative training data. J. Mech. Syst. Signal Process. 56–57, 109–122 (2014)Google Scholar
  11. 11.
    MacKay, D.J.C.: Information Theory, Inference, and Learning Algorithms. Cambridge University Press, Cambridge (2003)zbMATHGoogle Scholar
  12. 12.
    Doucet, A., Andrieu, C.: Joint Bayesian model selection and estimation of noisy sinusoids via reversible jump MCMC. IEEE Trans. Signal Process. (1999)Google Scholar
  13. 13.
    Doucet, A., Djuric, P.M., Andrieu, C.: Model selection by MCMC computation. J. Signal Process. 81, 19–37Google Scholar
  14. 14.
    Razul, S.G., Fitzgerald, W.J., Andrieu, C.: Bayesian model selection and parameter estimation of nuclear emission spectra using RJMCMC. J. Nucl. Instrum. Methods Phys. Res. 497, 492–510 (2003)CrossRefGoogle Scholar
  15. 15.
    Liu, R.Y., Tao, J., Shi, N.Z., He, X.: Bayesian analysis of the patterns of biological susceptibility via reversible jump MCMC sampling. Comput. Stat. Data Anal. 55, 1498–1508 (2011)MathSciNetCrossRefzbMATHGoogle Scholar
  16. 16.
    Baldacchino, T., Anderson, S.R., Kadirkamanathan, V.: Computational system identification for Bayesian NARMAX modelling. Automatica 49, 2641–2651 (2013)MathSciNetCrossRefGoogle Scholar
  17. 17.
    Damen, D., Hogg, S.: Recognizing linked events: searching the space of feasible explanations. In: Proceedings of IEEE Computer Science and Pattern Recognition, Miami, pp. 927–934 (2009)Google Scholar
  18. 18.
    Tiboaca, D., Green, P.L., Barthorpe, R.J.: Bayesian parameter estimation and model selection of a nonlinear dynamical system using reversible jump Markov chain Monte Carlo. In: Proceedings of ISMA International Conference on Noise and Vibration Engineering, Leuven (2014)Google Scholar
  19. 19.
    Schutz, B.: Geometrical Methods of Mathematical Physics. Cambridge University Press, Cambridge (1980)CrossRefzbMATHGoogle Scholar
  20. 20.
    Sisson, S.A.: Transdimensional Markov Chains: A decade of progress and future perspectives. J. Am. Stat. Assoc. 100 (471), 1077–1089 (2005)MathSciNetCrossRefzbMATHGoogle Scholar

Copyright information

© The Society for Experimental Mechanics, Inc. 2016

Authors and Affiliations

  • D. Tiboaca
    • 1
    Email author
  • P. L. Green
    • 2
  • R. J. Barthorpe
    • 1
  • I. Antoniadou
    • 1
  • K. Worden
    • 1
  1. 1.Dynamics Research Group, Department of Mechanical EngineeringThe University of SheffieldSheffieldUK
  2. 2.Institute for Risk and Uncertainty, School of EngineeringUniversity of LiverpoolLiverpoolUK

Personalised recommendations