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

Estimating the spatially varying microstructures of heterogeneous and locallyanisotropic media non-destructively is necessary for the accurate detection offlaws and reliable monitoring of manufacturing processes. Conventionalalgorithms used for solving this inverse problem come with significantcomputational cost, particularly in the case of high dimensional non-lineartomographic problems. In this paper, we propose a framework which uses deepneural networks (DNNs) with full aperture, pitch-catch and pulse-echotransducer configurations to reconstruct material maps of crystallographicorientation. We also present the first ever application of generativeadversarial networks (GANs) to achieve super resolution of ultrasonictomographic images, providing a factor-four increase in image resolution and upto a 50% increase in structural similarity. The importance of includingappropriate prior knowledge in the GAN training dataset to increase inversionaccuracy is highlighted; known information about the material's structureshould be present in the training data. We show that after a computationallyexpensive training process, the DNNs and GANs can be used in less that onesecond (0.9 seconds on a standard desktop computer) to provide a highresolution map of the material's grain orientations.

Real-time super-resolution mapping of locally anisotropic grain orientations for ultrasonic non-destructive evaluation of crystalline material