Premium
Deep learning phase‐field model for brittle fractures
Author(s) -
Ghaffari Motlagh Yousef,
Jimack Peter K.,
Borst René
Publication year - 2022
Publication title -
international journal for numerical methods in engineering
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.421
H-Index - 168
eISSN - 1097-0207
pISSN - 0029-5981
DOI - 10.1002/nme.7135
Subject(s) - brittleness , phase field models , field (mathematics) , artificial neural network , brittle fracture , deep learning , phase (matter) , computer science , variety (cybernetics) , fracture (geology) , boundary (topology) , artificial intelligence , fracture mechanics , scale (ratio) , machine learning , mathematics , geology , structural engineering , engineering , physics , geotechnical engineering , mathematical analysis , quantum mechanics , pure mathematics , thermodynamics
Abstract We present deep learning phase‐field models for brittle fracture. A variety of physics‐informed neural networks (PINNs) techniques, for example, original PINNs, variational PINNs (VPINNs), and variational energy PINNs (VE‐PINNs) are utilized to solve brittle phase‐field problems. The performance of the different versions is investigated in detail. Also, different ways of imposing boundary conditions are examined and are compared with a self‐adaptive PINNs approach in terms of computational cost. Furthermore, the data‐driven discovery of the phase‐field length scale is examined. Finally, several numerical experiments are conducted to assess the accuracy and the limitations of the discussed deep learning schemes for crack propagation in two dimensions. We show that results can be highly sensitive to parameter choices within the neural network.