BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//talks.cam.ac.uk//v3//EN
BEGIN:VTIMEZONE
TZID:Europe/London
BEGIN:DAYLIGHT
TZOFFSETFROM:+0000
TZOFFSETTO:+0100
TZNAME:BST
DTSTART:19700329T010000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=-1SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0100
TZOFFSETTO:+0000
TZNAME:GMT
DTSTART:19701025T020000
RRULE:FREQ=YEARLY;BYMONTH=10;BYDAY=-1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
CATEGORIES:Engineering - Mechanics and Materials Seminar Seri
 es
SUMMARY:Strength prediction of polymer composite laminates
  under uncertainties using theory-guided machine l
 earning - Prof Pedro Camanho\, Mechanical Engineer
 ing Department\, University of Porto
DTSTART;TZID=Europe/London:20230224T140000
DTEND;TZID=Europe/London:20230224T150000
UID:TALK193579AThttp://talks.cam.ac.uk
URL:http://talks.cam.ac.uk/talk/index/193579
DESCRIPTION:This work represents a first study towards the app
 lication of theory-guided machine learning techniq
 ues in the prediction of design allowables of notc
 hed polymer composite laminates accounting for mat
 erial and geometric uncertainties. Building on dat
 a generated analytically\, using either phase-fiel
 d methods or finite fracture mechanics\, and reduc
 ed representations of composite lay-ups\, four mac
 hine learning algorithms are used to predict the s
 trength of composite laminates with notches of sev
 eral geometries and the corresponding statistical 
 distribution\, associated to material and geometri
 cal variability.\n \nExcellent representations of 
 the design space (relative errors of around ±10%) 
 and very accurate representations of the distribut
 ions of notched strengths and of the corresponding
  B-basis allowables used in aircraft structural de
 sign are obtained. Gaussian-based models proved to
  be the most reliable approach as a result of its 
 continuous nature\, accuracy\, and fast training p
 rocess. This work serves as basis for the predicti
 on of first-ply failure\, ultimate strength and fa
 ilure mode of composite laminates based on non-lin
 ear finite element simulations across different le
 ngth scales\, providing significant reductions of 
 the computational time required to virtually certi
 fy composite aircraft structures.
LOCATION:Oatley Seminar Room\, Department of Engineering
CONTACT:Hilde Hambro
END:VEVENT
END:VCALENDAR