BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:A spectrum of physics-informed machine learning approaches for pro
 blems in structural dynamics - Professor Lizzy Cross\, University of Sheff
 ield
DTSTART:20230120T160000Z
DTEND:20230120T170000Z
UID:TALK192740@talks.cam.ac.uk
CONTACT:46601
DESCRIPTION:As monitoring data from our critical systems and structures be
 come more abundant\, engineers (should) naturally wish to benefit from the
  learning available from them. Indeed\, many elements of structural assess
 ment and\, in particular\, those relying on a dynamic signature\, are now 
 evolving to take advantage of this\, leading to the creation and adoption 
 of\na wealth of data-driven approaches. The use of machine learning in str
 uctural health monitoring\, for example\, is common\, as many of the inher
 ent tasks (such as regression and classification) in developing condition-
 based assessment fall naturally into its remit.\n\nA significant challenge
  here\, that is not often acknowledged\, however\, is that we commonly lac
 k representative data from across the range of environmental and operation
 al conditions structures will undergo\, limiting the usability of an entir
 ely data-based approach.\n\nThis talk will present a number of ways of inc
 orporating the physical insight an engineer will often have of the structu
 re they are attempting to model or assess into a machine learning approach
  through a Gaussian process regression framework. The talk will demonstrat
 e how grey-box models\, that combine simple physics-based models with data
 -driven ones\, can improve predictive capability for structural assessment
  and system identification tasks. A particular strength of the approaches 
 demonstrated here is the capacity of the models to generalise\, with enhan
 ced predictive capability in different regimes\, increasing applicability 
 in light of the aforementioned challenge.
LOCATION:JDB Seminar Room\, CUED
END:VEVENT
END:VCALENDAR