.png){kind=icon}
.png){kind=icon}
Return
One-step SelfSim algorithm: Formulating material models from measured strain fields with machine learning
.png){kind=icon}
OA
AI
DOI：10.1016/j.compstruc.2025.107944.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• Introduced One-Step SelfSim, a novel machine learning-based approach to derive material models from measured strain fields, bypassing displacement-driven simulations. • Demonstrated the algorithm’s effectiveness in modelling elastoplastic behaviour, utilising recurrent neural networks for history-dependent material responses. • Extended the application of the SelfSim algorithm from finite element methods to the finite volume framework, implemented via OpenFOAM. • Verified the method through test cases, including elastoplastic deformation of a steel plate and its generalisation to a plate with a hole. • Showed significant computational efficiency and improved accuracy over traditional SelfSim, enabling direct integration of modern experimental strain data.
Keywords:
Material model
Constitutive law
Autoprogressive algorithm
SelfSim algorithm
One-step SelfSim algorithm
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
C
IF:
4.8
Papers:
6.2K
Citations:
1.7W
Organization
No organization information available