A pre-training model based on CFD for open-channel velocity field prediction with small sample data
Accurately obtaining the distribution of the open-channel velocity field in hydraulic engineering is extremely important, which is helpful for better calculation of open-channel flow and analysis of open-channel water flow characteristics. In recent years, machine learning has been used for open-cha...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IWA Publishing
2023-03-01
|
Series: | Journal of Hydroinformatics |
Subjects: | |
Online Access: | http://jhydro.iwaponline.com/content/25/2/396 |
_version_ | 1797200758416867328 |
---|---|
author | Ruixiang Lin Xinzhi Zhou Bo Li Xin He |
author_facet | Ruixiang Lin Xinzhi Zhou Bo Li Xin He |
author_sort | Ruixiang Lin |
collection | DOAJ |
description | Accurately obtaining the distribution of the open-channel velocity field in hydraulic engineering is extremely important, which is helpful for better calculation of open-channel flow and analysis of open-channel water flow characteristics. In recent years, machine learning has been used for open-channel velocity field prediction. However, effective training of data-driven models in machine learning heavily depends on the diversity and quantity of data. In this paper, a CFD-based pre-training neural network model (CFD–PNN) is proposed for accurate open-channel velocity field prediction, allowing the adaption to the task with small sample data. Also, a cross-sectional velocity field prediction method combining the computational fluid dynamics (CFD) and machine learning is established. By comparing CFD–PNN with six other neural network algorithm models and the CFD model, the results show that, in the case of small sample data, the CFD–PNN model can predict a more reasonable open-channel velocity field with higher prediction accuracy than other models. The average error of the velocity calculation for the trapezoidal open-channel cross-section is about 3.62%. Compared with other models, the accuracy is improved by 0.3–2.8%.
HIGHLIGHTS
A velocity field prediction model based on CFD and machine learning.;
The model adapts to tasks with small sample data.;
Experimental verification using the measured data of trapezoidal open channels.; |
first_indexed | 2024-04-09T19:05:10Z |
format | Article |
id | doaj.art-d065d967b7cb4729a7ada9ab6c220a37 |
institution | Directory Open Access Journal |
issn | 1464-7141 1465-1734 |
language | English |
last_indexed | 2024-04-24T07:36:44Z |
publishDate | 2023-03-01 |
publisher | IWA Publishing |
record_format | Article |
series | Journal of Hydroinformatics |
spelling | doaj.art-d065d967b7cb4729a7ada9ab6c220a372024-04-20T06:20:07ZengIWA PublishingJournal of Hydroinformatics1464-71411465-17342023-03-0125239641410.2166/hydro.2023.121121A pre-training model based on CFD for open-channel velocity field prediction with small sample dataRuixiang Lin0Xinzhi Zhou1Bo Li2Xin He3 College of Electronics and Information Engineering, Sichuan University, Chengdu, China College of Electronics and Information Engineering, Sichuan University, Chengdu, China College of Water Resources and Hydropower, Sichuan University, Chengdu, China Wan Jiang Gang-li Technology Joint Stock Company, Chengdu, China Accurately obtaining the distribution of the open-channel velocity field in hydraulic engineering is extremely important, which is helpful for better calculation of open-channel flow and analysis of open-channel water flow characteristics. In recent years, machine learning has been used for open-channel velocity field prediction. However, effective training of data-driven models in machine learning heavily depends on the diversity and quantity of data. In this paper, a CFD-based pre-training neural network model (CFD–PNN) is proposed for accurate open-channel velocity field prediction, allowing the adaption to the task with small sample data. Also, a cross-sectional velocity field prediction method combining the computational fluid dynamics (CFD) and machine learning is established. By comparing CFD–PNN with six other neural network algorithm models and the CFD model, the results show that, in the case of small sample data, the CFD–PNN model can predict a more reasonable open-channel velocity field with higher prediction accuracy than other models. The average error of the velocity calculation for the trapezoidal open-channel cross-section is about 3.62%. Compared with other models, the accuracy is improved by 0.3–2.8%. HIGHLIGHTS A velocity field prediction model based on CFD and machine learning.; The model adapts to tasks with small sample data.; Experimental verification using the measured data of trapezoidal open channels.;http://jhydro.iwaponline.com/content/25/2/396cfdmachine learningopen-channel flowsmall sample datavelocity field |
spellingShingle | Ruixiang Lin Xinzhi Zhou Bo Li Xin He A pre-training model based on CFD for open-channel velocity field prediction with small sample data Journal of Hydroinformatics cfd machine learning open-channel flow small sample data velocity field |
title | A pre-training model based on CFD for open-channel velocity field prediction with small sample data |
title_full | A pre-training model based on CFD for open-channel velocity field prediction with small sample data |
title_fullStr | A pre-training model based on CFD for open-channel velocity field prediction with small sample data |
title_full_unstemmed | A pre-training model based on CFD for open-channel velocity field prediction with small sample data |
title_short | A pre-training model based on CFD for open-channel velocity field prediction with small sample data |
title_sort | pre training model based on cfd for open channel velocity field prediction with small sample data |
topic | cfd machine learning open-channel flow small sample data velocity field |
url | http://jhydro.iwaponline.com/content/25/2/396 |
work_keys_str_mv | AT ruixianglin apretrainingmodelbasedoncfdforopenchannelvelocityfieldpredictionwithsmallsampledata AT xinzhizhou apretrainingmodelbasedoncfdforopenchannelvelocityfieldpredictionwithsmallsampledata AT boli apretrainingmodelbasedoncfdforopenchannelvelocityfieldpredictionwithsmallsampledata AT xinhe apretrainingmodelbasedoncfdforopenchannelvelocityfieldpredictionwithsmallsampledata AT ruixianglin pretrainingmodelbasedoncfdforopenchannelvelocityfieldpredictionwithsmallsampledata AT xinzhizhou pretrainingmodelbasedoncfdforopenchannelvelocityfieldpredictionwithsmallsampledata AT boli pretrainingmodelbasedoncfdforopenchannelvelocityfieldpredictionwithsmallsampledata AT xinhe pretrainingmodelbasedoncfdforopenchannelvelocityfieldpredictionwithsmallsampledata |