BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:CESS seminar series: From conventional aerospace structures to cyb
 er-physical structural assets: Introducing the digital siblings concept
DTSTART:20221028T121500
DTEND:20221028T130000
DTSTAMP:20260511T104145Z
UID:4f1d33747217c237cf3ff057385bbebb092a71157918418356b229c8
CATEGORIES:Conferences - Seminars
DESCRIPTION:Prof. Dimitrios Zarouchas\, TUDELFT\nAbstract:\nThe progress i
 n key-technologies such as Artificial Intelligence and Internet of Things 
 opens new horizons for developing the lightweight structures of the future
 \, where the structures will be able to perform self-diagnostic checks of 
 their integrity\, self-estimate their lifetime and communicate with each o
 ther valuable information.  This lecture delivers the vision of the Pythi
 a team on how to design cyber-physical systems from sensing to health indi
 cators’ extraction and from diagnosis and prognosis to decision making p
 rotocols. Technical details on the concept of digital siblings\, essential
  tool for physics-informed diagnosis\, will be presented\; the digital sib
 lings are designed using stochastic finite elements\, Artificial Neural Ne
 twork and SHM data. A demonstration of the feasibility and efficiency of d
 igital siblings will be given for the real-time strength estimation of com
 posite structures while being tested under static loading.\n\nBiography:\n
 Dimitrios Zarouchas is an Associate professor and the Director of the Cent
 er of Excellence in Artificial Intelligence at the Aerospace Engineering F
 aculty of Delft University of Technology. He leads the Pythia team – Art
 ificial Intelligence for Structures\, Health Management and Prognostics\, 
 with his vision being the research\, development and deployment of intelli
 gent cyber-physical systems for enabling real-time data extraction for the
  purpose of health management of systems and structures used in aerospace\
 , automotive\, wind energy and maritime sectors. The team is developing ma
 chine learning algorithms for data-driven and physics-based diagnostics an
 d prognostics and employs reinforcement learning for decision making proto
 cols.  Emphasis is given to self-learning (development of learning agents
 )\, learn-how-to learn prototypes and transfer learning. Dimitrios has bee
 n leading multi-millionaire research and innovation projects\, funded by E
 U and National schemes and he has been the author of more than 70 journal 
 publications.\n 
LOCATION:GC B3 30 https://plan.epfl.ch/?room==GC%20B3%2030
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR