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

Meshing is a critical, but user-intensive process necessary for stable andaccurate simulations in computational fluid dynamics (CFD). Mesh generation isoften a bottleneck in CFD pipelines. Adaptive meshing techniques allow the meshto be updated automatically to produce an accurate solution for the problem athand. Existing classical techniques for adaptive meshing require eitheradditional functionality out of solvers, many training simulations, or both.Current machine learning techniques often require substantial computationalcost for training data generation, and are restricted in scope to the trainingdata flow regime. MeshDQN is developed as a general purpose deep reinforcementlearning framework to iteratively coarsen meshes while preserving targetproperty calculation. A graph neural network based deep Q network is used toselect mesh vertices for removal and solution interpolation is used to bypassexpensive simulations at each step in the improvement process. MeshDQN requiresa single simulation prior to mesh coarsening, while making no assumptions aboutflow regime, mesh type, or solver, only requiring the ability to modify meshesdirectly in a CFD pipeline. MeshDQN successfully improves meshes for two 2Dairfoils.

MeshDQN: A Deep Reinforcement Learning Framework for Improving Meshes in Computational Fluid Dynamics