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

Mesh generation remains a key technology in many areas where numericalsimulations are required. As numerical algorithms become more efficient andcomputers become more powerful, the percentage of time devoted to meshgeneration becomes higher. In this paper, we present an improved structuredmesh generation method. The method formulates the meshing problem as a globaloptimization problem related to a physics-informed neural network. The mesh isobtained by intelligently solving the physical boundary-constrained partialdifferential equations. To improve the prediction accuracy of the neuralnetwork, we also introduce a novel auxiliary line strategy and an efficientnetwork model during meshing. The strategy first employs a priori auxiliarylines to provide ground truth data and then uses these data to construct a lossterm to better constrain the convergence of the subsequent training. Theexperimental results indicate that the proposed method is effective and robust.It can accurately approximate the mapping (transformation) from thecomputational domain to the physical domain and enable fast high-qualitystructured mesh generation.

An Improved Structured Mesh Generation Method Based on Physics-informed Neural Networks