Neural network-based surrogate model for a bifurcating structural fracture response

Bram Pieter van de Weg*, Lars Greve, Michael Andres, Tom Eller, Bojana Rosic

*Corresponding author for this work

Research output: Contribution to journalArticleAcademicpeer-review

13 Citations (Scopus)
74 Downloads (Pure)


A finite element model of a tapered tensile specimen with a hardness transition zone in the gauge section and a varying width parameter is used for creating corresponding solution snapshots. Subsequently, a long short-term memory (LSTM) recurrent neural network (RNN) is trained on the selected snapshots, providing a parametrized solution model for a computationally efficient prediction of the structural response, allowing real-time model evaluation. In addition to a parametrized solution of the fracture localization, the model also captures the bifurcating local mesh deformation. The internal solution strategy of the RNN for predicting the bifurcation phenomenon is investigated and visualized.
Original languageEnglish
Article number107424
JournalEngineering fracture mechanics
Early online date27 Nov 2020
Publication statusPublished - Jan 2021


  • UT-Hybrid-D


Dive into the research topics of 'Neural network-based surrogate model for a bifurcating structural fracture response'. Together they form a unique fingerprint.

Cite this