English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

The microstructure analyses of porous media have considerable research valuefor the study of macroscopic properties. As the premise of conducting theseanalyses, the accurate reconstruction of microstructure digital model is alsoan important component of the research. Computational reconstruction algorithmsof microstructure have attracted much attention due to their low cost andexcellent performance. However, it is still a challenge for computationalreconstruction algorithms to achieve faster and more efficient reconstruction.The bottleneck lies in computational reconstruction algorithms, they are eithertoo slow (traditional reconstruction algorithms) or not flexible to thetraining process (deep learning reconstruction algorithms). To address theselimitations, we proposed a fast and flexible computational reconstructionalgorithm, neural networks based on improved simulated annealing framework(ISAF-NN). The proposed algorithm is flexible and can complete training andreconstruction in a short time with only one two-dimensional image. Byadjusting the size of input, it can also achieve reconstruction of arbitrarysize. Finally, the proposed algorithm is experimentally performed on a varietyof isotropic and anisotropic materials to verify the effectiveness andgeneralization.

A fast and flexible algorithm for microstructure reconstruction combining simulated annealing and deep learning