Engineering neutron diffraction data analysis with inverse neural network modeling

Baris Denizer, Ersan Üstündag, Halil Ceylan, Li Li, Seung Yub Lee

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Citation (Scopus)

Abstract

Integration of engineering neutron diffraction data analysis and solid mechanics modeling is a powerful method to deduce in-situ constitutive behavior of materials. Since diffraction data originates from spatially discrete subsets of the material volume, extrapolation of the data to the behavior of the overall sample is non-trivial. The finite element modelhas been widely used for interpreting diffraction data by optimizing model parameters via iterative processes. In order to maximize the rigor of such analysis and to increase fitting efficiency and accuracy, we have developed an optimization algorithm based on the neural network architecture.Theinverse neural network modelreveals parameter sensitivity quantitatively during a training process, and yieldsmore accurate phase specific constitutive laws of the composite materials compared to the conventional method, once networks are successfully trained.

Original languageEnglish
Title of host publicationMechanical Stress Evaluation by Neutrons and Synchrotron Radiation VI
PublisherTrans Tech Publications Ltd
Pages39-44
Number of pages6
ISBN (Print)9783037859117
DOIs
Publication statusPublished - 2014
Externally publishedYes
Event6th International Conference on Mechanical Stress Evaluation by Neutrons and Synchrotron Radiation, MECA SENS VI 2011 - Hamburg, Germany
Duration: 7 Sept 20119 Sept 2011

Publication series

NameMaterials Science Forum
Volume772
ISSN (Print)0255-5476
ISSN (Electronic)1662-9752

Conference

Conference6th International Conference on Mechanical Stress Evaluation by Neutrons and Synchrotron Radiation, MECA SENS VI 2011
Country/TerritoryGermany
CityHamburg
Period7/09/119/09/11

Keywords

  • Constitutive law
  • Finite element
  • Inverse analysis
  • Neural network
  • Neutron diffraction

Fingerprint

Dive into the research topics of 'Engineering neutron diffraction data analysis with inverse neural network modeling'. Together they form a unique fingerprint.

Cite this