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

The inverse approach is computationally efficient in aerodynamic design asthe desired target performance distribution is prespecified. However, it hassome significant limitations that prevent it from achieving full efficiency.First, the iterative procedure should be repeated whenever the specified targetdistribution changes. Target distribution optimization can be performed toclarify the ambiguity in specifying this distribution, but several additionalproblems arise in this process such as loss of the representation capacity dueto parameterization of the distribution, excessive constraints for a realisticdistribution, inaccuracy of quantities of interest due to theoretical/empiricalpredictions, and the impossibility of explicitly imposing geometricconstraints. To deal with these issues, a novel inverse design optimizationframework with a two-step deep learning approach is proposed. A variationalautoencoder and multi-layer perceptron are used to generate a realistic targetdistribution and predict the quantities of interest and shape parameters fromthe generated distribution, respectively. Then, target distributionoptimization is performed as the inverse design optimization. The proposedframework applies active learning and transfer learning techniques to improveaccuracy and efficiency. Finally, the framework is validated throughaerodynamic shape optimizations of the wind turbine airfoil. Their results showthat this framework is accurate, efficient, and flexible to be applied to otherinverse design engineering applications.

Inverse design optimization framework via a two-step deep learning approach: application to a wind turbine airfoil