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

Chemical Species Tomography (CST) has been widely used for in situ imaging ofcritical parameters, e.g. species concentration and temperature, in reactiveflows. However, even with state-of-the-art computational algorithms the methodis limited due to the inherently ill-posed and rank-deficient tomographic datainversion, and by high computational cost. These issues hinder its applicationfor real-time flow diagnosis. To address them, we present here a novelCST-based convolutional neural Network (CSTNet) for high-fidelity, rapid, andsimultaneous imaging of species concentration and temperature. CSTNetintroduces a shared feature extractor that incorporates the CST measurement andsensor layout into the learning network. In addition, a dual-brancharchitecture is proposed for image reconstruction with crosstalk decoders thatautomatically learn the naturally correlated distributions of speciesconcentration and temperature. The proposed CSTNet is validated both withsimulated datasets, and with measured data from real flames in experimentsusing an industry-oriented sensor. Superior performance is found relative toprevious approaches, in terms of robustness to measurement noise andmillisecond-level computing time. This is the first time, to the best of ourknowledge, that a deep learning-based algorithm for CST has been experimentallyvalidated for simultaneous imaging of multiple critical parameters in reactiveflows using a low-complexity optical sensor with severely limited number oflaser beams.

CSTNet: A Dual-Branch Convolutional Network for Imaging of Reactive Flows using Chemical Species Tomography