BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:A Bayesian methodology for hybrid degradation prognostics - Edgar 
 Jaber (ENS Paris-Saclay)
DTSTART:20250604T112500Z
DTEND:20250604T114500Z
UID:TALK230812@talks.cam.ac.uk
DESCRIPTION:Degradation prognostics of industrial assets involves estimati
 ng their remaining useful life (RUL) by projecting their current health an
 d operating conditions and assessing the associated uncertainties. This is
  usually done using physics-based simulations or data-driven models. While
  each approach has strengths\, they can fall short especially when the num
 erical code is time-consuming and when the available degradation data is s
 parse. To address these issues\, we developed an offline data fusion metho
 d that combines kernel-based sensitivity analysis with an iterative Bayesi
 an update of influential computer model inputs. To reduce the computationa
 l cost\, we use a field surrogate modeling strategy and an aggregation met
 hod to reduce the metamodeling bias in the posterior distributions. After 
 presenting the method\, I will show how it reduces the RUL prediction unce
 rtainties on a clogging prognostics problem for steam generators in nuclea
 r power plants. &nbsp\;\nJoint work with: Vincent Chabridon (EDF R&D)\, Em
 manuel Remy (EDF R&D)\, Mathilde Mougeot (ENS Paris-Saclay)\, Didier Lucor
  (LISN)\, Merlin Keller (EDF R&D)\, Julien Pelamatti (EDF R&D)\, Micha&eum
 l\;l Baudin (EDF R&D).
LOCATION:Seminar Room 1\, Newton Institute
END:VEVENT
END:VCALENDAR