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

An unsupervised machine learning strategy is developed to automaticallycluster the vortex wakes of bio-inspired propulsors into groups of similarpropulsive thrust and efficiency metrics. A pitching and heaving foil issimulated via computational fluid dynamics with $121$ unique kinematics byvarying the frequency, heaving amplitude, and pitching amplitude. A Reynoldsaveraged Navier-Stokes (RANS) model is employed to simulate the flow over theoscillating foils at $Re=10^6$, computing the propulsive efficiency, thrustcoefficient and the unsteady vorticity wake signature. Using a pairwise Pearsoncorrelation it is found that the Strouhal number most strongly influences thethrust coefficient, whereas the relative angle of attack, defined by both themid-stroke and maximum have the most significant impact on propulsiveefficiency. Next, the various kinematics are automatically clustered intodistinct groups exclusively using the vorticity footprint in the wake. Aconvolutional autoencoder is developed to reduce vortex wake images to theirmost significant features, and a k-means++ algorithm performs the clustering.The results are assessed by comparing clusters to a thrust versus propulsiveefficiency map, which confirms that wakes of similar performance metrics aresuccessfully clustered together. This automated clustering has the potential toidentify complex vorticity patterns in the wake and modes of propulsion noteasily discerned from traditional classification methods.

Unsupervised Clustering and Performance Prediction of Vortex Wakes from Bio-inspired Propulsors