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 Tools annual

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 monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Pool fires are canonical representations of many accidental fires, which canexhibit an unstable unsteady behaviour, known as puffing, which involves astrong coupling between the temperature and velocity fields. Despite theirpractical relevance to fire research, their experimental study can be limiteddue to the complexity of measuring relevant quantities in parallel. In thiswork, we analyse the use of a recent physics-informed machine learningapproach, called Hidden Fluid Mechanics (HFM), to reconstruct unmeasuredquantities in a puffing pool fire from measured quantities. The HFM frameworkrelies on a Physics-Informed Neural Network (PINN) for this task. A PINN is aneural network that uses both the available data, here the measured quantities,and the physical equations governing the system, here the reactingNavier-Stokes equations, to infer the full fluid dynamic state. This frameworkis used to infer the velocity field in a puffing pool fire from measurements ofdensity, pressure and temperature. In this work, the dataset used for this testwas generated from numerical simulations. It is shown that the PINN is able toreconstruct the velocity field accurately and to infer most features of thevelocity field. In addition, it is shown that the reconstruction accuracy isrobust with respect to noisy data, and a reduction in the number of measuredquantities is explored and discussed. This study opens up the possibility ofusing PINNs for the reconstruction of unmeasured quantities from measured ones,providing the potential groundwork for their use in experiments for fireresearch.

Velocity Reconstruction in Puffing Pool Fires with Physics-Informed Neural Networks