Toward Neural Network Models to Model Multi-phase Solids

Maysam B. Gorji*, Julian N. Heidenreich, Mojtaba Mozaffar, Dirk Mohr

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contribution


In this study, a neural network model is developed to describe the large deformation response of a multi-phase material, i.e., a two-dimensional perforated plate. Using the finite element, virtual experiments are performed to generate stress–strain data for monotonic biaxial loading paths. Subsequently, a combination of fully connected and recurrent neural network models are trained and validated using the results from the virtual experiments. The predictions of a network show a remarkable good agreement with all the experimental data. The suggested neural network-based constitutive model does provide a robust solution to the problem at hand, providing a fully anisotropic, three-dimensional material model capable of covering all physical material properties. The suggested procedure promises to be generally applicable to any material class and can be paired with any numerical method.

Original languageEnglish (US)
Title of host publicationForming the Future - Proceedings of the 13th International Conference on the Technology of Plasticity
EditorsGlenn Daehn, Jian Cao, Brad Kinsey, Erman Tekkaya, Anupam Vivek, Yoshinori Yoshida
PublisherSpringer Science and Business Media Deutschland GmbH
Number of pages10
ISBN (Print)9783030753801
StatePublished - 2021
Event13th International Conference on the Technology of Plasticity, ICTP 2021 - Virtual, Online
Duration: Jul 25 2021Jul 30 2021

Publication series

NameMinerals, Metals and Materials Series
ISSN (Print)2367-1181
ISSN (Electronic)2367-1696


Conference13th International Conference on the Technology of Plasticity, ICTP 2021
CityVirtual, Online


  • Artificial intelligence
  • Fully connected neural network
  • Multi-phase material
  • Plasticity
  • Recurrent neural network

ASJC Scopus subject areas

  • Electronic, Optical and Magnetic Materials
  • Energy Engineering and Power Technology
  • Mechanics of Materials
  • Metals and Alloys
  • Materials Chemistry


Dive into the research topics of 'Toward Neural Network Models to Model Multi-phase Solids'. Together they form a unique fingerprint.

Cite this