2023
DOI: 10.1063/5.0149750
|View full text |Cite
|
Sign up to set email alerts
|

A divide-and-conquer machine learning approach for modeling turbulent flows

Abstract: In this paper, a novel zonal machine learning (ML) approach for Reynolds-averaged Navier–Stokes (RANS) turbulence modeling based on the divide-and-conquer technique is introduced. This approach involves partitioning the flow domain into regions of flow physics called zones, training one ML model in each zone, then validating and testing them on their respective zones. The approach was demonstrated with the tensor basis neural network (TBNN) and another neural net called the turbulent kinetic energy neural netw… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2

Citation Types

0
2
0

Year Published

2023
2023
2025
2025

Publication Types

Select...
5

Relationship

0
5

Authors

Journals

citations
Cited by 5 publications
(2 citation statements)
references
References 50 publications
0
2
0
Order By: Relevance
“…This issue primarily occurs when a small input feature set is used, such as the 5 invariants (several of which are zero for 2D flows) used in Ling et al's original TBNN [8]. Several strategies have been proposed to address the issue of a non-unique mapping, including incorporation of additional input features [16], and ensembling through a divide and conquer approach by Man et al [17]. In the present investigation, we address the issue related to non-uniqueness of the mapping via use of a rich input feature set.…”
Section: Introductionmentioning
confidence: 99%
See 1 more Smart Citation
“…This issue primarily occurs when a small input feature set is used, such as the 5 invariants (several of which are zero for 2D flows) used in Ling et al's original TBNN [8]. Several strategies have been proposed to address the issue of a non-unique mapping, including incorporation of additional input features [16], and ensembling through a divide and conquer approach by Man et al [17]. In the present investigation, we address the issue related to non-uniqueness of the mapping via use of a rich input feature set.…”
Section: Introductionmentioning
confidence: 99%
“…The present work is the first to unite TBNN-type frameworks (e.g. Ling et al [8], Kaandorp [9], Kaandorp and Dwight [10], Man et al [17]) with optimal eddy viscosity frameworks (e.g. Wu et al [16], Brener et al [27], and McConkey et al [18]).…”
Section: Introductionmentioning
confidence: 99%