Browse

Inverse quantification of epistemic uncertainty under scarce data: Bayesian or Interval approach?

Cited 0 time in Web of Science Cited 0 time in Scopus
Authors
Faes, Matthias; Broggi, Matteo; Patelli, Edoardo; Govers, Yves; Mottershead, John; Beer, Michael; Moens, David
Issue Date
2019-05-26
Citation
13th International Conference on Applications of Statistics and Probability in Civil Engineering(ICASP13), Seoul, South Korea, May 26-30, 2019
Abstract
This paper introduces a practical comparison of a newly introduced inverse method for the quantification of epistemically uncertain model parameters with the well-established probabilistic framework of Bayesian model updating via Transitional Markov Chain Monte Carlo. The paper gives a concise overview of both techniques, and both methods are applied to the quantification of a set of parameters in the well-known DLR Airmod test structure. Specifically, the case where only a very scarce set of experimentally obtained eigenfrequencies and eigenmodes are available is considered. It is shown that for such scarce data, the interval method provides more objective and robust bounds on the uncertain parameters than the Bayesian method, since no prior definition of the uncertainty is required, albeit at the cost that less information on parameter dependency or relative plausibility of different parameter values is obtained.
Language
English
URI
https://hdl.handle.net/10371/153281
DOI
https://doi.org/10.22725/ICASP13.060
Files in This Item:
Appears in Collections:
College of Engineering/Engineering Practice School (공과대학/대학원)Dept. of Civil & Environmental Engineering (건설환경공학부)ICASP13
  • mendeley

Items in S-Space are protected by copyright, with all rights reserved, unless otherwise indicated.

Browse