Machine Learning for heat radiation modeling of bi- and polydisperse particle systems including walls (Open Access)--颗粒学报PARTICUOLOGY

Tausendschön, J., Stöckl, G., & Radl, S. (2023). Machine Learning for heat radiation modeling of bi- and polydisperse particle systems including walls. Particuology, 74, 119-140. https://doi.org/10.1016/j.partic.2022.05.011

Machine Learning for heat radiation modeling of bi- and polydisperse particle systems including walls (Open Access)

Josef Tausendschön ^*, Gero Stöckl, Stefan Radl

Institute of Process and Particle Engineering, Graz University of Technology, Inffeldgasse 13/III, 8010, Graz, Austria

10.1016/j.partic.2022.05.011

Volume 74, March 2023, Pages 119-140

Received 23 February 2022, Revised 10 May 2022, Accepted 23 May 2022, Available online 8 June 2022, Version of Record 27 June 2022.

E-mail: josef.tausendschoen@tugraz.at

Highlights

• Investigation of four Machine Learning methods in terms of their ability to model view factors.

• Analysis of markers available in DEM simulations with respect to their view factor correlation.

• DNN- and RFR-based models exceed the quality standards for predictions in monodisperse systems.

• Adding particle size information allows models to change from mono-to polydisperse systems.

Abstract

We investigated the ability of four popular Machine Learning methods i.e., Deep Neural Networks (DNNs), Random Forest-based regressors (RFRs), Extreme Gradient Boosting-based regressors (XGBs), and stacked ensembles of DNNs, to model the radiative heat transfer based on view factors in bi- and polydisperse particle beds including walls. Before training and analyzing the predictive capability of each method, an adjustment of markers used in monodisperse systems, as well as an evaluation of new markers was performed. On the basis of our dataset that considers a wide range of particle radii ratios, system sizes, particle volume fractions, as well as different particle-species volume fractions, we found that (i) the addition of particle size information allows the transition from monodisperse to bi- and polydisperse beds, and (ii) the addition of particle volume fraction information as the fourth marker leads to very accurate predictions. In terms of the overall performance, DNNs and RFRs should be preferred compared to the other two options. For particle–particle view factors, DNN and RFR are on par, while for particle–wall the RFR is superior. We demonstrate that DNNs and RFRs can be built to meet or even exceed the prediction quality standards achieved in a monodisperse system.

Graphical abstract

Keywords

Discrete element method (DEM); Heat radiation modeling; Machine learning; View factors; Wall radiation; Polydisperse particles

文章导读