Deep learning based prediction of fibrous microstructure permeability

Baris Caglar, G.C. Broggi, Muhammad A. Ali, Laurent Orgéas, Véronique Michaud

Research output: Chapter in Book/Conference proceedings/Edited volumeConference contributionScientificpeer-review

18 Downloads (Pure)


Knowledge of permeability of fibrous microstructures is crucial for predicting the mold fill times and resin flow path in composite manufacturing. Herein we report a method to rapidly predict the permeability of 3D fibrous microstructures. Our method relies on predicting the permeability of 2D cross-sections via deep neural networks and extending this capability to 3D microstructures via circuit analogy as a means of reduced order modeling. Approximately 50% of the permeability predictions of 2D cross-sections have 10% or less deviation from the permeability results obtained via flow simulations in Geodict. Computational time required for predicting the permeability of 3D microstructures is reduced from hours to less than 10 seconds. This framework enables fast and accurate prediction of micro-permeability and serves as the first building block towards prediction of fabric mesostructures’ permeability via deep learning based methods.
Original languageEnglish
Title of host publicationProceedings of the 20th European Conference on Composite Materials: Composites Meet Sustainability
Subtitle of host publicationVol 4 – Modeling and Prediction
EditorsAnastasios P. Vassilopoulos , Véronique Michaud
Place of PublicationLausanne
PublisherEPFL Lausanne, Composite Construction Laboratory
Number of pages8
ISBN (Electronic)978-2-9701614-0-0
Publication statusPublished - 2022
Event20th European Conference on Composite Materials: Composites Meet Sustainability - Lausanne, Switzerland
Duration: 26 Jun 202230 Jun 2022
Conference number: 20


Conference20th European Conference on Composite Materials
Abbreviated titleECCM20


  • Deep Learning
  • Permeability
  • Microstructures
  • Numerical analysis


Dive into the research topics of 'Deep learning based prediction of fibrous microstructure permeability'. Together they form a unique fingerprint.

Cite this