schliessen

Filtern

 

Bibliotheken

A hydrodynamic prediction model of throttle orifice plate using space filling and adaptive sampling method

The hydrodynamic prediction model improved design efficiency of the flow control application. A global sampling process with space filling method, adaptive sampling method, and neural network is proposed to generate a hydrodynamic prediction model for the flow control device. The optimized Latin hyp... Full description

Journal Title: Structural and multidisciplinary optimization 2020-04-05, Vol.62 (3), p.1563-1578
Main Author: Tang, Tengfei
Other Authors: Yang, Gang , Zhang, Dijia , Lei, Lei , Li, Baoren , Gao, Longlong
Format: Electronic Article Electronic Article
Language: English
Subjects:
Publisher: Berlin/Heidelberg: Springer Berlin Heidelberg
ID: ISSN: 1615-147X
Zum Text:
SendSend as email Add to Book BagAdd to Book Bag
Staff View
recordid: cdi_proquest_journals_2436218925
title: A hydrodynamic prediction model of throttle orifice plate using space filling and adaptive sampling method
format: Article
creator:
  • Tang, Tengfei
  • Yang, Gang
  • Zhang, Dijia
  • Lei, Lei
  • Li, Baoren
  • Gao, Longlong
subjects:
  • Adaptive control
  • Adaptive sampling
  • Analysis
  • Back propagation networks
  • Computational fluid dynamics
  • Computational Mathematics and Numerical Analysis
  • Design improvements
  • Dynamic tests
  • Engineering
  • Engineering Design
  • Flow control
  • Flow velocity
  • Fluid dynamics
  • Hypercubes
  • Industrial Application Paper
  • Latin hypercube sampling
  • Methods
  • Models
  • Neural networks
  • Orifice meters
  • Orifices
  • Prediction models
  • Sampling methods
  • Theoretical and Applied Mechanics
  • Throttles
ispartof: Structural and multidisciplinary optimization, 2020-04-05, Vol.62 (3), p.1563-1578
description: The hydrodynamic prediction model improved design efficiency of the flow control application. A global sampling process with space filling method, adaptive sampling method, and neural network is proposed to generate a hydrodynamic prediction model for the flow control device. The optimized Latin hypercube sampling method is applied to create a uniform set of initial sample points for analysis. An automatic computational fluid dynamics analysis process is developed to provide data for the hydrodynamic objective of the multi-stage throttle orifice plate. By self-learning from previous sample points, the new sample points placed in the region of interest are collected by the adaptive sampling method in several iterations. Two numerical examples and the flow rate modeling for the throttle orifice plate are provided to demonstrate the approximation capability of the proposed process. Ten prediction model cases are established by a back-propagation feed-forward neural network, and the test data show that the model constructed by optimized Latin hypercube sampling and adaptive sampling has 1% mean relative error and 4.85% maximum relative error, which is nearly 25% more accurate than the optimized Latin hypercube sampling model. The proposed global sampling process is efficient to build the hydrodynamic prediction model and shows potential in the flow control design area.
language: eng
source:
identifier: ISSN: 1615-147X
fulltext: no_fulltext
issn:
  • 1615-147X
  • 1615-1488
url: Link


@attributes
NO1
SEARCH_ENGINEprimo_central_multiple_fe
SEARCH_ENGINE_TYPEPrimo Central Search Engine
RANK2.531075
LOCALfalse
PrimoNMBib
record
control
sourceidgale_proqu
recordidTN_cdi_proquest_journals_2436218925
sourceformatXML
sourcesystemPC
galeidA638249094
sourcerecordidA638249094
originalsourceidFETCH-LOGICAL-c301t-ad7d1b06431cec1a18e6a7d2ceaff8246ff6f6f954d28db4c36bff853c2c68fe0
addsrcrecordideNp9kU1PAyEQhjdGE2v1D3gi8bwVWJayx6bxK2niRRNvhMLQ0uwuK1Cb_nvRNXozE8IwvA8DvEVxTfCMYDy_jRiTWpSY4jxqzsrDSTEhnNQlYUKc_ubzt_PiIsYdxlhg1kyK3QJtjyZ4c-xV5zQaAhink_M96ryBFnmL0jb4lFpAPjjrNKChVQnQPrp-g-KgcsW6tv1aqd4gZdSQ3AegqLrhu9pB2npzWZxZ1Ua4-pmnxev93cvysVw9PzwtF6tSV5ikUpm5IWvMWUU0aKKIAK7mhmpQ1grKuLU8R1MzQ4VZM13xdd6oK001FxbwtLgZzx2Cf99DTHLn96HPLSVlFadENLTOqtmo2qgWpOutT0HpHAbyP_ge8pNALniVWza4YRmgI6CDjzGAlUNwnQpHSbD8MkGOJshsgvw2QR4yVI1QzOJ-A-HvLv9Qn2VbjQA
sourcetypeAggregation Database
isCDItrue
recordtypearticle
pqid2436218925
display
typearticle
titleA hydrodynamic prediction model of throttle orifice plate using space filling and adaptive sampling method
creatorTang, Tengfei ; Yang, Gang ; Zhang, Dijia ; Lei, Lei ; Li, Baoren ; Gao, Longlong
creatorcontribTang, Tengfei ; Yang, Gang ; Zhang, Dijia ; Lei, Lei ; Li, Baoren ; Gao, Longlong
descriptionThe hydrodynamic prediction model improved design efficiency of the flow control application. A global sampling process with space filling method, adaptive sampling method, and neural network is proposed to generate a hydrodynamic prediction model for the flow control device. The optimized Latin hypercube sampling method is applied to create a uniform set of initial sample points for analysis. An automatic computational fluid dynamics analysis process is developed to provide data for the hydrodynamic objective of the multi-stage throttle orifice plate. By self-learning from previous sample points, the new sample points placed in the region of interest are collected by the adaptive sampling method in several iterations. Two numerical examples and the flow rate modeling for the throttle orifice plate are provided to demonstrate the approximation capability of the proposed process. Ten prediction model cases are established by a back-propagation feed-forward neural network, and the test data show that the model constructed by optimized Latin hypercube sampling and adaptive sampling has 1% mean relative error and 4.85% maximum relative error, which is nearly 25% more accurate than the optimized Latin hypercube sampling model. The proposed global sampling process is efficient to build the hydrodynamic prediction model and shows potential in the flow control design area.
identifier
0ISSN: 1615-147X
1EISSN: 1615-1488
2DOI: 10.1007/s00158-020-02564-w
languageeng
publisherBerlin/Heidelberg: Springer Berlin Heidelberg
subjectAdaptive control ; Adaptive sampling ; Analysis ; Back propagation networks ; Computational fluid dynamics ; Computational Mathematics and Numerical Analysis ; Design improvements ; Dynamic tests ; Engineering ; Engineering Design ; Flow control ; Flow velocity ; Fluid dynamics ; Hypercubes ; Industrial Application Paper ; Latin hypercube sampling ; Methods ; Models ; Neural networks ; Orifice meters ; Orifices ; Prediction models ; Sampling methods ; Theoretical and Applied Mechanics ; Throttles
ispartofStructural and multidisciplinary optimization, 2020-04-05, Vol.62 (3), p.1563-1578
rights
0Springer-Verlag GmbH Germany, part of Springer Nature 2020
1COPYRIGHT 2020 Springer
2Springer-Verlag GmbH Germany, part of Springer Nature 2020.
lds50peer_reviewed
citesFETCH-LOGICAL-c301t-ad7d1b06431cec1a18e6a7d2ceaff8246ff6f6f954d28db4c36bff853c2c68fe0
links
openurl$$Topenurl_article
thumbnail$$Usyndetics_thumb_exl
search
creatorcontrib
0Tang, Tengfei
1Yang, Gang
2Zhang, Dijia
3Lei, Lei
4Li, Baoren
5Gao, Longlong
title
0A hydrodynamic prediction model of throttle orifice plate using space filling and adaptive sampling method
1Structural and multidisciplinary optimization
addtitleStruct Multidisc Optim
descriptionThe hydrodynamic prediction model improved design efficiency of the flow control application. A global sampling process with space filling method, adaptive sampling method, and neural network is proposed to generate a hydrodynamic prediction model for the flow control device. The optimized Latin hypercube sampling method is applied to create a uniform set of initial sample points for analysis. An automatic computational fluid dynamics analysis process is developed to provide data for the hydrodynamic objective of the multi-stage throttle orifice plate. By self-learning from previous sample points, the new sample points placed in the region of interest are collected by the adaptive sampling method in several iterations. Two numerical examples and the flow rate modeling for the throttle orifice plate are provided to demonstrate the approximation capability of the proposed process. Ten prediction model cases are established by a back-propagation feed-forward neural network, and the test data show that the model constructed by optimized Latin hypercube sampling and adaptive sampling has 1% mean relative error and 4.85% maximum relative error, which is nearly 25% more accurate than the optimized Latin hypercube sampling model. The proposed global sampling process is efficient to build the hydrodynamic prediction model and shows potential in the flow control design area.
subject
0Adaptive control
1Adaptive sampling
2Analysis
3Back propagation networks
4Computational fluid dynamics
5Computational Mathematics and Numerical Analysis
6Design improvements
7Dynamic tests
8Engineering
9Engineering Design
10Flow control
11Flow velocity
12Fluid dynamics
13Hypercubes
14Industrial Application Paper
15Latin hypercube sampling
16Methods
17Models
18Neural networks
19Orifice meters
20Orifices
21Prediction models
22Sampling methods
23Theoretical and Applied Mechanics
24Throttles
issn
01615-147X
11615-1488
fulltextfalse
rsrctypearticle
creationdate2020
recordtypearticle
recordideNp9kU1PAyEQhjdGE2v1D3gi8bwVWJayx6bxK2niRRNvhMLQ0uwuK1Cb_nvRNXozE8IwvA8DvEVxTfCMYDy_jRiTWpSY4jxqzsrDSTEhnNQlYUKc_ubzt_PiIsYdxlhg1kyK3QJtjyZ4c-xV5zQaAhink_M96ryBFnmL0jb4lFpAPjjrNKChVQnQPrp-g-KgcsW6tv1aqd4gZdSQ3AegqLrhu9pB2npzWZxZ1Ua4-pmnxev93cvysVw9PzwtF6tSV5ikUpm5IWvMWUU0aKKIAK7mhmpQ1grKuLU8R1MzQ4VZM13xdd6oK001FxbwtLgZzx2Cf99DTHLn96HPLSVlFadENLTOqtmo2qgWpOutT0HpHAbyP_ge8pNALniVWza4YRmgI6CDjzGAlUNwnQpHSbD8MkGOJshsgvw2QR4yVI1QzOJ-A-HvLv9Qn2VbjQA
startdate20200405
enddate20200405
creator
0Tang, Tengfei
1Yang, Gang
2Zhang, Dijia
3Lei, Lei
4Li, Baoren
5Gao, Longlong
general
0Springer Berlin Heidelberg
1Springer
2Springer Nature B.V
scope
0AAYXX
1CITATION
2BSHEE
38FE
48FG
5ABJCF
6BENPR
7BGLVJ
8DWQXO
9HCIFZ
10L6V
11M7S
12PQEST
13PQQKQ
14PQUKI
15PTHSS
sort
creationdate20200405
titleA hydrodynamic prediction model of throttle orifice plate using space filling and adaptive sampling method
authorTang, Tengfei ; Yang, Gang ; Zhang, Dijia ; Lei, Lei ; Li, Baoren ; Gao, Longlong
facets
frbrtype5
frbrgroupidcdi_FETCH-LOGICAL-c301t-ad7d1b06431cec1a18e6a7d2ceaff8246ff6f6f954d28db4c36bff853c2c68fe0
rsrctypearticles
prefilterarticles
languageeng
creationdate2020
topic
0Adaptive control
1Adaptive sampling
2Analysis
3Back propagation networks
4Computational fluid dynamics
5Computational Mathematics and Numerical Analysis
6Design improvements
7Dynamic tests
8Engineering
9Engineering Design
10Flow control
11Flow velocity
12Fluid dynamics
13Hypercubes
14Industrial Application Paper
15Latin hypercube sampling
16Methods
17Models
18Neural networks
19Orifice meters
20Orifices
21Prediction models
22Sampling methods
23Theoretical and Applied Mechanics
24Throttles
toplevelpeer_reviewed
creatorcontrib
0Tang, Tengfei
1Yang, Gang
2Zhang, Dijia
3Lei, Lei
4Li, Baoren
5Gao, Longlong
collection
0CrossRef
1Academic OneFile (A&I only)
2ProQuest SciTech Collection
3ProQuest Technology Collection
4Materials Science & Engineering Collection
5ProQuest Central
6Technology Collection
7ProQuest Central Korea
8SciTech Premium Collection
9ProQuest Engineering Collection
10Engineering Database
11ProQuest One Academic Eastern Edition
12ProQuest One Academic
13ProQuest One Academic UKI Edition
14Engineering Collection
jtitleStructural and multidisciplinary optimization
delivery
delcategoryRemote Search Resource
fulltextno_fulltext
addata
au
0Tang, Tengfei
1Yang, Gang
2Zhang, Dijia
3Lei, Lei
4Li, Baoren
5Gao, Longlong
formatjournal
genrearticle
ristypeJOUR
atitleA hydrodynamic prediction model of throttle orifice plate using space filling and adaptive sampling method
jtitleStructural and multidisciplinary optimization
stitleStruct Multidisc Optim
date2020-04-05
risdate2020
volume62
issue3
spage1563
epage1578
pages1563-1578
issn1615-147X
eissn1615-1488
abstractThe hydrodynamic prediction model improved design efficiency of the flow control application. A global sampling process with space filling method, adaptive sampling method, and neural network is proposed to generate a hydrodynamic prediction model for the flow control device. The optimized Latin hypercube sampling method is applied to create a uniform set of initial sample points for analysis. An automatic computational fluid dynamics analysis process is developed to provide data for the hydrodynamic objective of the multi-stage throttle orifice plate. By self-learning from previous sample points, the new sample points placed in the region of interest are collected by the adaptive sampling method in several iterations. Two numerical examples and the flow rate modeling for the throttle orifice plate are provided to demonstrate the approximation capability of the proposed process. Ten prediction model cases are established by a back-propagation feed-forward neural network, and the test data show that the model constructed by optimized Latin hypercube sampling and adaptive sampling has 1% mean relative error and 4.85% maximum relative error, which is nearly 25% more accurate than the optimized Latin hypercube sampling model. The proposed global sampling process is efficient to build the hydrodynamic prediction model and shows potential in the flow control design area.
copBerlin/Heidelberg
pubSpringer Berlin Heidelberg
doi10.1007/s00158-020-02564-w