Open AccessPerformance of CFD and ANN modeling of heat transfer enhancement in a circular tube with artificial roughness
Author(s) -
N V Kuzmenkov,
M S Frantcuzov,
А П Королева
Publication year - 2021
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1891/1/012063
Subject(s) - computational fluid dynamics , nusselt number , artificial neural network , turbulence , heat transfer , surface finish , airflow , flow (mathematics) , computer science , mechanics , artificial intelligence , mechanical engineering , engineering , reynolds number , physics
This paper presents a comparison of three different approaches for modeling enhanced heat transfer characteristics of turbulent airflow in a circular tube with artificial roughness of transverse ribs. A number of CFD simulations are carried out forming the first dataset as well as the second dataset extracted from a number of classical works. A deep feed-forward neural network is developed to predict Nusselt number and friction factor for a variety of rib roughness and flow parameters. The ANN is trained by the first dataset (the CFD and ANN approach) and the second dataset (the experiment and ANN approach) independently and by a combination of datasets (the hybrid approach) showing good quality predictions in all the cases. All results are compared with experimental data and CFD modelled values showing the best results of the experiment and ANN approach.