Bayesian System Identification of Dynamical Systems Using Reversible Jump Markov Chain Monte Carlo

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


The purpose of this contribution is to illustrate the potential of Reversible Jump Markov Chain Monte Carlo (RJMCMC) methods for nonlinear system identification. Markov Chain Monte Carlo (MCMC) sampling methods have come to be viewed as a standard tool for tackling the issue of parameter estimation using Bayesian inference. A limitation of standard MCMC approaches is that they are not suited to tackling the issue of model selection. RJMCMC offers a powerful extension to standard MCMC approaches in that it allows parameter estimation and model selection to be addressed simultaneously. This is made possible by the fact that the RJMCMC algorithm is able to “jump” between parameter spaces of varying dimension. In this paper the background theory to the RJMCMC algorithm is introduced. Comparison is made to a standard MCMC approach.


Nonlinear dynamics System identification Bayesian inference MCMC RJMCMC 


  1. 1.
    Beck LJ, Au S-K (2002) Bayesian updating of structural models and reliability using markov chain monte carlo simulation. J Eng Mech 391:128–380Google Scholar
  2. 2.
    Worden K, Hensman JJ (2012) Parameter estimation and model selection for a class of hysteretic systems using bayesian inference. Mech Syst Signal Process 32:153–169Google Scholar
  3. 3.
    Green PL, Worden K (2013) Modelling friction in a nonlinear dynamic system via bayesian inference. In: IMAC XXXI ProceedingsGoogle Scholar
  4. 4.
    Carlin BP, Chib S (1995) Bayesian model choice via markov chain monte carlo methods. J Roy Stat Soc Ser B (Methodological) 57:473–484zbMATHGoogle Scholar
  5. 5.
    Green PJ (1995) Reversible jump markov chain monte carlo computation and bayesian model determination. Biometrika 82:711–732zbMATHMathSciNetGoogle Scholar
  6. 6.
    Dellaportas P, Ntzoufras I, Forster JJ (2002) On bayesian model and variable selection using mcmc. Stat Comput 36:12–27Google Scholar
  7. 7.
    Baldacchino T, Kadirkamanathan V, Anderson SR (2013) Computational system identification for bayesian narmax modelling. Automatica 49:2641–2651MathSciNetGoogle Scholar
  8. 8.
    Green PJ, Hastie DI (2012) Model choice using reversible jump markov chain monte carlo. Statistica Neerlandica 309–338Google Scholar
  9. 9.
    Andrieu C, Doucet A (1999) Joint bayesian model selection and estimation of noisy sinusoids via reversible jump mcmc. IEEE Trans Signal ProcessGoogle Scholar
  10. 10.
    Andrieu C, Doucet A, Djuric PM (2001) Model selection by mcmc computation. Signal Process 81:19–37zbMATHGoogle Scholar
  11. 11.
    Geinitz S (2009) Prior covariance choices and the g prior.Google Scholar
  12. 12.
    MacKay DJC (2003) Information theory, inference, and learning algorithms. Cambridge University Press, CambridgezbMATHGoogle Scholar
  13. 13.
    Chib S, Greenberg E (1995) Understanding the metropolis-hastings algorithm. Am StatGoogle Scholar
  14. 14.
    Schutz B (1980) Geometrical methods of mathematical physics. Cambridge University Press, CambridgezbMATHGoogle Scholar

Copyright information

© The Society for Experimental Mechanics, Inc. 2014

Authors and Affiliations

  • D. Tiboaca
    • 1
  • P. L. Green
    • 1
  • R. J. Barthorpe
    • 1
  • K. Worden
    • 1
  1. 1.Department of Mechanical EngineeringUniversity of SheffieldSheffieldUK

Personalised recommendations