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

In this work, a new hybrid predictive Reduced Order Model (ROM) is proposedto solve reacting flow problems. This algorithm is based on a dimensionalityreduction using Proper Orthogonal Decomposition (POD) combined with deeplearning architectures. The number of degrees of freedom is reduced fromthousands of temporal points to a few POD modes with their correspondingtemporal coefficients. Two different deep learning architectures have beentested to predict the temporal coefficients, based on recursive (RNN) andconvolutional (CNN) neural networks. From each architecture, different modelshave been created to understand the behavior of each parameter of the neuralnetwork. Results show that these architectures are able to predict the temporalcoefficients of the POD modes, as well as the whole snapshots. The RNN showslower prediction error for all the variables analyzed. The model was also foundcapable of predicting more complex simulations showing transfer learningcapabilities.

A predictive physics-aware hybrid reduced order model for reacting flows