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

Artificial intelligence-based three-dimensional(3D) fluid modeling has gainedsignificant attention in recent years. However, the accuracy of such models isoften limited by the processing of irregular flow data. In order to bolster thecredibility of near-wall flow prediction, this paper presents a deeplearning-based reduced order model for three-dimensional unsteady flow usingthe transformation and stitching of multi-block structured meshes. To beginwith, full-order flow data is provided by numerical simulations that rely onmulti-block structured meshes. A mesh transformation technique is applied toconvert each structured grid with data into a corresponding uniform andorthogonal grid, which is subsequently stitched and filled. The resultingsnapshots in the transformed domain contain accurate flow information formultiple meshes and can be directly fed into a structured neural networkwithout requiring any interpolation operation. Subsequently, a network modelbased on a fully convolutional neural network is constructed to predict flowdynamics accurately. To validate the strategy's feasibility, the flow around asphere with Re=300 was investigated, and the results obtained using traditionalCartesian interpolation were used as the baseline for comparison. All theresults demonstrate the preservation and accurate prediction of flow detailsnear the wall, with the pressure correlation coefficient on the wall achievingan impressive value of 0.9985. Moreover, the periodic behavior of flow fieldscan be faithfully predicted during long-term inference.

Deep learning-based reduced order model for three-dimensional unsteady flow using mesh transformation and stitching