BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Data-driven homogenisation of the mechanical response of solids - 
 Dr Mirac Onur Bozkurt\, CUED 
DTSTART:20250214T143000Z
DTEND:20250214T150000Z
UID:TALK227887@talks.cam.ac.uk
CONTACT:46601
DESCRIPTION:As engineering materials becomes increasingly complex\, accura
 tely predicting their mechanical behaviour under diverse loading condition
 s presents a significant challenge. Multiscale models offer a robust solu
 tion by bridging micro- and macroscales\; however\, they remain impractica
 l due to the substantial computational demand of performing microscale com
 putations across a macroscale domain. This study explores data-driven stra
 tegies integrated with machine learning techniques to enable the efficient
  homogenisation of the microscopic mechanical response of porous elastomer
 s. A micromechanical finite element model of a porous unit cell is develop
 ed within a computational homogenisation framework to generate training da
 ta. Initially\, neural network-based macroscopic surrogate models are esta
 blished to predict the nonlinear elastic response of a hyperelastic porous
  unit cell using data from micromechanical simulations. The data-driven fr
 amework is then extended to capture the time- and path-dependent response 
 of a viscoelastic porous unit cell. In this case\, a knowledge-based data-
 driven approach is compared to the purely data-driven strategy and demonst
 rates improved efficiency while maintaining accuracy in homogenising the i
 nelastic mechanical response.
LOCATION:Oatley 1 Meeting Room\, Department of Engineering
END:VEVENT
END:VCALENDAR