Title: Deep Neural Network-based View factor Modelling of Radiative Heat Transfer between Particles
Authors: Tausendschön, Josef 
Radl, Stefan 
Keywords: Radiative Heat Transfer; data-driven modelling; machine learning; deep neural networks
Issue Date: Dec-2020
Book Title: Proceedings of the 16th Minisymposium Verfahrenstechnik and 7th Partikelforum (TU Wien, Sept. 21/22, 2020) 
Abstract: 
We present a Deep Neural Network (DNN)-based view factor model to calculate radiative heat transfer between particles. Different neural net model parameters like: the number of hidden layers, the number of nodes per layer, optimization algorithms and techniques to prevent overfitting of the DNN are investigated. Using a simple regressor showed that one input marker, namely the surface distance between the interacting particles, cannot accurately predict the widespread view factors for increasing surface distance. Therefore, the effect of additional input markers like the solid angle between particles or a derivate of a local particle volume fraction is examined. The outcome of the DNN-model is compared to literature models and a simple regression analysis. It is demonstrated that the pretrained DNN-model can model view factors at higher accuracy and with significantly less computational effort than other literature models.
URI: http://hdl.handle.net/20.500.12708/16658
http://dx.doi.org/10.34726/601
DOI: 10.34726/601
Organisation: E166-02-2 - Forschungsgruppe Fluiddynamische Simulation (CFD) 
License: CC BY 4.0 CC BY 4.0
Publication Type: Inproceedings
Konferenzbeitrag
Appears in Collections:Conference Paper

Files in this item:

File Description SizeFormat
MoV5_03.pdf753.43 kBAdobe PDFThumbnail
 View/Open
Show full item record

Page view(s)

21
checked on Feb 26, 2021

Download(s)

16
checked on Feb 26, 2021

Google ScholarTM

Check


This item is licensed under a Creative Commons License Creative Commons