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

We report significantly improved accuracy of grain boundary segmentationusing Convolutional Neural Networks (CNN) trained on a combination of real andgenerated data. Manual segmentation is accurate but time-consuming, andexisting computational methods are faster but often inaccurate. To combat thisdilemma, machine learning models can be used to achieve the accuracy of manualsegmentation and have the efficiency of a computational method. An extensivedataset of from 316L stainless steel samples is additively manufactured,prepared, polished, etched, and then microstructure grain images weresystematically collected. Grain segmentation via existing computational methodsand manual (by-hand) were conducted, to create "real" training data. A Voronoitessellation pattern combined with random synthetic noise and simulateddefects, is developed to create a novel artificial grain image fabricationmethod. This provided training data supplementation for data-intensive machinelearning methods. The accuracy of the grain measurements from microstructureimages segmented via computational methods and machine learning methodsproposed in this work are calculated and compared to provide much benchmarks ingrain segmentation. Over 400 images of the microstructure of stainless steelsamples were manually segmented for machine learning training applications.This data and the artificial data is available on Kaggle.

Grain and Grain Boundary Segmentation using Machine Learning with Real and Generated Datasets