Skip to main content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.


The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Assessment of Radiation Solver of Fire Simulation Models Using RADNNET-ZM



Wai Cheong Tam, Walter W. Yuen


The paper presents a neural-network based zonal method (RADNNET-ZM) for the analysis of radiative heat transfer in an arbitrary Cartesian enclosure with an isothermal, inhomogeneous, non-gray medium. The model accounts for the non-gray effect of absorbing species in a combustion environment and the geometric effect of any three-dimensional enclosures. The model is verified against benchmark solutions. Maximum local error is observed to be less than 4 %. Prediction accuracy of an existing zonal radiation solver is assessed. Results demonstrate that RADNNET-ZM can provide substantial improvement to zone fire simulation models for the prediction of radiative heat transfer without a significant increase in computation cost.
Proceedings Title
11th Asia-Oceania Symposium on Fire Science and Technology (AOSFST)
Conference Dates
October 21-25, 2018
Conference Location
Taipei, -1


Neural network, zonal method, non-gray, multi-dimensional, fire simulation model
Created September 13, 2019, Updated September 23, 2019