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

This work addresses the data-driven forecasting of extreme events in theairfoil flow. These events may be seen as examples of the kind of unsteady andintermittent dynamics relevant to the flow around airfoils and wings in avariety of laboratory and real-world applications. W investigate theinstability mechanisms at the heart of these extreme events, and how knowledgethereof may be harnessed for efficient data driven forecasting. Through awavelet and spectral analysis of the flow we find that the extreme events arisedue to the instability of a specific frequency component distinct from thevortex shedding mode. During these events this extreme event manifold drawsenergy from the energetically dominant vortex shedding flow and undergoes anabrupt energy transfer from small to large scales. We also investigate thespatial dependence of the temporal correlation and mutual information betweenthe surface pressure and the aerodynamic forces, with the aim of identifyingregions of the airfoil amenable to sparse sensing and the efficient forecastingof extremes. Building on previous work, we show that relying solely on themutual information for optimal sensor placement fails to improve modelprediction over uniform or random sensor placement. However, we show that byisolating the extreme event frequency component offline through a wavelettransform we are able to circumvent the requirement for a recursive long-shortterm memory (LSTM) network -- resulting in a significant reduction incomputational complexity over the previous state of the art. Using the waveletpre-processed data in conjunction with an extreme event-tailored loss functionwe find that our model is capable of forecasting extreme events using onlythree pressure sensors. Furthermore, we find our model to be robust to sensorlocation -- showing promise for the use of our model in dynamically varyingapplications.

Harnessing the instability mechanisms in airfoil flow for the data-driven forecasting of extreme events