Statistical inverse identification for nonlinear train dynamics using a surrogate model in a Bayesian framework

David Lebel 1, 2 Christian Soize 1 Christine Fünfschilling 2 Guillaume Perrin 3
1 MSME - Laboratoire de Modélisation et Simulation Multi Echelle
2 SNCF : Innovation & Recherche
3 DAM/DIF - DAM Île-de-France
Abstract : This paper presents a Bayesian calibration method for a simulation-based model with stochastic functional input and output. The originality of the method lies in an adaptation involving the representation of the likelihood function by a Gaussian process surrogate model, to cope with the high computational cost of the simulation, while avoiding the surrogate modeling of the functional output. The adaptation focuses on taking into account the uncertainty introduced by the use of a surrogate model when estimating the parameters posterior probability distribution by MCMC. To this end, trajectories of the random surrogate model of the likelihood function are drawn and injected in the MCMC algorithm. An application on a train suspension monitoring case is presented.
Keywords : Statistical inverse problem Bayesian calibration Surrogate model High-speed train dynamics Uncertainty quantification
Document type :
Journal articles
Complete list of metadatas

Cited literature [28 references]  Display  Hide  Download
https://hal-upec-upem.archives-ouvertes.fr/hal-02175507
Contributor : Christian Soize <>
Submitted on : Friday, July 5, 2019 - 5:58:08 PM
Last modification on : Friday, October 4, 2019 - 1:36:25 AM

File

publi-2019-JSV-458()158-176-le...
Files produced by the author(s)

Identifiers

Collections

UPEC-UPEM | INSMI | CEA | DAM | MSME_MECA | MSME | MSME_TCM | UPEC

Citation

David Lebel, Christian Soize, Christine Fünfschilling, Guillaume Perrin. Statistical inverse identification for nonlinear train dynamics using a surrogate model in a Bayesian framework. Journal of Sound and Vibration, Elsevier, 2019, 458, pp.158-176. ⟨10.1016/j.jsv.2019.06.024⟩. ⟨hal-02175507⟩

Export

BibTeX TEI DC DCterms EndNote

Share

Metrics

Record views

38

Files downloads

252

Contact

CCSD