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

A novel hybrid deep neural network architecture is designed to capture thespatial-temporal features of unsteady flows around moving boundaries directlyfrom high-dimensional unsteady flow fields data. The hybrid deep neural networkis constituted by the convolutional neural network (CNN), improvedconvolutional Long-Short Term Memory neural network (ConvLSTM) anddeconvolutional neural network (DeCNN). Flow fields at future time step can bepredicted through flow fields by previous time steps and boundary positions atthose steps by the novel hybrid deep neural network. Unsteady wake flows arounda forced oscillation cylinder with various amplitudes are calculated toestablish the datasets as training samples for training the hybrid deep neuralnetworks. The trained hybrid deep neural networks are then tested by predictingthe unsteady flow fields around a forced oscillation cylinder with newamplitude. The effect of neural network structure parameters on predictionaccuracy was analyzed. The hybrid deep neural network, constituted by the bestparameter combination, is used to predict the flow fields in the future time.The predicted flow fields are in good agreement with those calculated directlyby computational fluid dynamic solver, which means that this kind of deepneural network can capture accurate spatial-temporal information from thespatial-temporal series of unsteady flows around moving boundaries. The resultshows the potential capability of this kind novel hybrid deep neural network inflow control for vibrating cylinder, where the fast calculation ofhigh-dimensional nonlinear unsteady flow around moving boundaries is needed.

Hybrid deep neural network based prediction method for unsteady flows with moving boundaries