Please use this identifier to cite or link to this item: http://dx.doi.org/10.18419/opus-12125
Authors: Schneider, Yanling
Prabhu, Vighnesh
Höss, Kai
Wasserbäch, Werner
Zhou, Zhangjian
Schmauder, Siegfried
Title: Many-scale investigations of the deformation behavior of polycrystalline composites: I - machine learning applied for image segmentation
Issue Date: 2022
metadata.ubs.publikation.typ: Zeitschriftenartikel
metadata.ubs.publikation.seiten: 20
metadata.ubs.publikation.source: Materials 15 (2022), No. 2486
URI: http://nbn-resolving.de/urn:nbn:de:bsz:93-opus-ds-121425
http://elib.uni-stuttgart.de/handle/11682/12142
http://dx.doi.org/10.18419/opus-12125
ISSN: 1996-1944
Abstract: Our work investigates the polycrystalline composite deformation behavior through multiscale simulations with experimental data at hand. Since deformation mechanisms on the micro-level link the ones on the macro-level and the nanoscale, it is preferable to perform micromechanical finite element simulations based on real microstructures. The image segmentation is a necessary step for the meshing. Our 2D EBSD images contain at least a few hundred grains. Machine learning (ML) was adopted to automatically identify subregions, i.e., individual grains, to improve local feature extraction efficiency and accuracy. Denoising in preprocessing and postprocessing before and after ML, respectively, is beneficial in high quality feature identification. The ML algorithms used were self-developed with the usage of inherent code packages (Python). The performances of the three supervised ML models - decision tree, random forest, and support vector machine - are compared herein; the latter two achieved accuracies of up to 99.8%. Calculations took about 0.5 h from the original input dataset (EBSD image) to the final output (segmented image) running on a personal computer (CPU: 3.6 GHz). For a realizable manual pixel sortation, the original image was firstly scaled from the initial resolution 1080x1080 pixels down to 300x300. After ML, some manual work was necessary due to the remaining noises to achieve the final image status ready for meshing. The ML process, including this manual work time, improved efficiency by a factor of about 24 compared to a purely manual process. Simultaneously, ML minimized the geometrical deviation between the identified and original features, since it used the original resolution. For serial work, the time efficiency would be enhanced multiplicatively.
Appears in Collections:04 Fakultät Energie-, Verfahrens- und Biotechnik

Files in This Item:
File Description SizeFormat 
N017-AgSnO2-ML-materials-15-02486.pdf8,24 MBAdobe PDFView/Open


Items in OPUS are protected by copyright, with all rights reserved, unless otherwise indicated.