BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Surrogate modelling for uncertainty quantification  in engineering
  applications
DTSTART:20180522T161500
DTSTAMP:20260407T125324Z
UID:b63f6e8e2fc8b8a536f784ee120848287f5364ca0854c4437f896872
CATEGORIES:Conferences - Seminars
DESCRIPTION:Prof. Bruno SUDRET\, Institute of Structural Engineering\, ETH
  Zürich\nAbstract:\nComputational models are used nowadays in virtually a
 ll fields of applied sciences and engineering to predict the behaviour of 
 complex natural or man-made systems. Those simulators allow the analyst to
  assess the performance of systems before actual manufacturing. They usual
 ly feature dozens of parameters and are expensive to run\, even when takin
 g full advantage of the available computer power. In this respect\, uncert
 ainty quantification techniques used to solve reliability\, sensitivity or
  optimal design problems usually require thousands to millions of runs wit
 h different values of the model input parameters\, which is not affordable
  with high-fidelity\, costly simulators. This has led to the development o
 f surrogate models in the last decade. Surrogate models can be  considere
 d as accurate approximations of the underlying simulator built from a limi
 ted number of runs at selected values (the experimental design) and some l
 earning algorithm. In this talk\, an overview of the most efficient non-in
 trusive techniques for surrogate modelling will be given\, namely polynomi
 al chaos expansions (including sparse approaches for high-dimensional prob
 lems)\, Kriging (a.k.a. Gaussian process modelling)\, their combination in
 to PC-Kriging\, as well as low-rank tensor approximations. Recent extensio
 ns to dynamics problems will be addressed. Various applications in model c
 alibration (Bayesian inversion)\, sensitivity and reliability analysis in 
 civil and mechanical engineering will be presented as an illustration.\n 
LOCATION:MA A3 31 https://plan.epfl.ch/?room=MAA331
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR