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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Efficiently predicting the flowfield and load in aerodynamic shapeoptimisation remains a highly challenging and relevant task. Deep learningmethods have been of particular interest for such problems, due to theirsuccess for solving inverse problems in other fields. In the present study,U-net based deep neural network (DNN) models are trained with high-fidelitydatasets to infer flow fields, and then employed as surrogate models to carryout the shape optimisation problem, i.e. to find a drag minimal profile with afixed cross-section area subjected to a two-dimensional steady laminar flow. Alevel-set method as well as Bezier-curve method are used to parameterise theshape, while trained neural networks in conjunction with automaticdifferentiation are utilized to calculate the gradient flow in the optimisationframework. The optimised shapes and drag force values calculated from theflowfields predicted by DNN models agree well with reference data obtained viaa Navier-Stokes solver and from the literature, which demonstrates that the DNNmodels are capable of predicting not only flowfield but also yield satisfactoryaerodynamic forces. This is particularly promising as the DNNs were notspecifically trained to infer aerodynamic forces. In conjunction with the fastruntime, the DNN-based optimisation framework shows promise for generalaerodynamic design problems.

Numerical investigation of minimum drag profiles in laminar flow using deep learning surrogates