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

Fluid motion can be considered as point cloud transformation when adopted bya Lagrangian description. Compared to traditional numerical analysis methods,using machine learning techniques to learn physics simulations can achieve nearaccuracy, while significantly increasing efficiency. In this paper, we proposean innovative approach for 3D fluid simulations utilizing an Attention-basedDual-pipeline Network, which employs a dual-pipeline architecture, seamlesslyintegrated with an Attention-based Feature Fusion Module. Unlike previoussingle-pipeline approaches, we find that a well-designed dual-pipeline approachachieves a better balance between global fluid control and physical lawconstraints. Furthermore, we design a Type-aware Input Module to adaptivelyrecognize particles of different types and perform feature fusion afterward,such that fluid-solid coupling issues can be better dealt with. The experimentsshow that our approach significantly increases the accuracy of fluid simulationpredictions and enhances generalizability to previously unseen scenarios. Wedemonstrate its superior performance over the state-of-the-art approachesacross various metrics.

DualFluidNet: an Attention-based Dual-pipeline Network for Accurate and Generalizable Fluid-solid Coupled Simulation