A combined neural network/gradient‐based approach for the identification of constitutive model parameters using self‐boring pressuremeter tests
Identifieur interne : 000A21 ( Main/Exploration ); précédent : 000A20; suivant : 000A22A combined neural network/gradient‐based approach for the identification of constitutive model parameters using self‐boring pressuremeter tests
Auteurs : Rafał F. Obrzud [Suisse] ; Laurent Vulliet [Suisse] ; Andrzej Truty [Pologne]Source :
- International Journal for Numerical and Analytical Methods in Geomechanics [ 0363-9061 ] ; 2009-04-25.
English descriptors
- KwdEn :
Abstract
This paper presents a numerical procedure of material parameter identification for the coupled hydro‐mechanical boundary value problem (BVP) of the self‐boring pressuremeter test (SBPT) in clay. First, the neural network (NN) technique is applied to obtain an initial estimate of model parameters, taking into account the possible drainage conditions during the expansion test. This technique is used to avoid potential pitfalls related to the conventional gradient‐based optimization techniques, considered here as a corrector that improves predicted parameters. Parameter identification based on measurements obtained through the pressuremeter expansion test and two types of holding tests is illustrated on the Modified Cam clay model. NNs are trained using a set of test samples, which are generated by means of finite element simulations of SBPT. The measurements obtained through expansion and consolidation tests are normalized so that NN predictors operate independently of the testing depth. Examples of parameter determination are demonstrated on both numerical and field data. The efficiency of the combined parameter identification in terms of accuracy, effectiveness and computational effort is also discussed. Copyright © 2008 John Wiley & Sons, Ltd.
Url:
DOI: 10.1002/nag.750
Affiliations:
Links toward previous steps (curation, corpus...)
- to stream Istex, to step Corpus: 001198
- to stream Istex, to step Curation: 001125
- to stream Istex, to step Checkpoint: 000543
- to stream Main, to step Merge: 000A29
- to stream Main, to step Curation: 000A21
Le document en format XML
<record><TEI wicri:istexFullTextTei="biblStruct"><teiHeader><fileDesc><titleStmt><title xml:lang="en">A combined neural network/gradient‐based approach for the identification of constitutive model parameters using self‐boring pressuremeter tests</title>
<author><name sortKey="Obrzud, Rafal F" sort="Obrzud, Rafal F" uniqKey="Obrzud R" first="Rafał F." last="Obrzud">Rafał F. Obrzud</name>
</author>
<author><name sortKey="Vulliet, Laurent" sort="Vulliet, Laurent" uniqKey="Vulliet L" first="Laurent" last="Vulliet">Laurent Vulliet</name>
</author>
<author><name sortKey="Truty, Andrzej" sort="Truty, Andrzej" uniqKey="Truty A" first="Andrzej" last="Truty">Andrzej Truty</name>
</author>
</titleStmt>
<publicationStmt><idno type="wicri:source">ISTEX</idno>
<idno type="RBID">ISTEX:6F74BE073B110E3118395C214CA00DECBABAEB13</idno>
<date when="2009" year="2009">2009</date>
<idno type="doi">10.1002/nag.750</idno>
<idno type="url">https://api.istex.fr/document/6F74BE073B110E3118395C214CA00DECBABAEB13/fulltext/pdf</idno>
<idno type="wicri:Area/Istex/Corpus">001198</idno>
<idno type="wicri:Area/Istex/Curation">001125</idno>
<idno type="wicri:Area/Istex/Checkpoint">000543</idno>
<idno type="wicri:doubleKey">0363-9061:2009:Obrzud R:a:combined:neural</idno>
<idno type="wicri:Area/Main/Merge">000A29</idno>
<idno type="wicri:Area/Main/Curation">000A21</idno>
<idno type="wicri:Area/Main/Exploration">000A21</idno>
</publicationStmt>
<sourceDesc><biblStruct><analytic><title level="a" type="main" xml:lang="en">A combined neural network/gradient‐based approach for the identification of constitutive model parameters using self‐boring pressuremeter tests</title>
<author><name sortKey="Obrzud, Rafal F" sort="Obrzud, Rafal F" uniqKey="Obrzud R" first="Rafał F." last="Obrzud">Rafał F. Obrzud</name>
<affiliation wicri:level="4"><country xml:lang="fr">Suisse</country>
<wicri:regionArea>Soil Mechanics Laboratory, École Polytechnique Fédérale de Lausanne, EPFL</wicri:regionArea>
<placeName><settlement type="city">Lausanne</settlement>
<region nuts="3" type="region">Canton de Vaud</region>
</placeName>
<orgName type="university">École polytechnique fédérale de Lausanne</orgName>
</affiliation>
</author>
<author><name sortKey="Vulliet, Laurent" sort="Vulliet, Laurent" uniqKey="Vulliet L" first="Laurent" last="Vulliet">Laurent Vulliet</name>
<affiliation wicri:level="4"><country xml:lang="fr">Suisse</country>
<wicri:regionArea>Soil Mechanics Laboratory, École Polytechnique Fédérale de Lausanne, EPFL</wicri:regionArea>
<placeName><settlement type="city">Lausanne</settlement>
<region nuts="3" type="region">Canton de Vaud</region>
</placeName>
<orgName type="university">École polytechnique fédérale de Lausanne</orgName>
</affiliation>
</author>
<author><name sortKey="Truty, Andrzej" sort="Truty, Andrzej" uniqKey="Truty A" first="Andrzej" last="Truty">Andrzej Truty</name>
<affiliation wicri:level="1"><country xml:lang="fr">Pologne</country>
<wicri:regionArea>Institute of Geotechnics, Cracow University of Technology, PK</wicri:regionArea>
<wicri:noRegion>PK</wicri:noRegion>
</affiliation>
</author>
</analytic>
<monogr></monogr>
<series><title level="j">International Journal for Numerical and Analytical Methods in Geomechanics</title>
<title level="j" type="abbrev">Int. J. Numer. Anal. Meth. Geomech.</title>
<idno type="ISSN">0363-9061</idno>
<idno type="eISSN">1096-9853</idno>
<imprint><publisher>John Wiley & Sons, Ltd.</publisher>
<pubPlace>Chichester, UK</pubPlace>
<date type="published" when="2009-04-25">2009-04-25</date>
<biblScope unit="volume">33</biblScope>
<biblScope unit="issue">6</biblScope>
<biblScope unit="page" from="817">817</biblScope>
<biblScope unit="page" to="849">849</biblScope>
</imprint>
<idno type="ISSN">0363-9061</idno>
</series>
<idno type="istex">6F74BE073B110E3118395C214CA00DECBABAEB13</idno>
<idno type="DOI">10.1002/nag.750</idno>
<idno type="ArticleID">NAG750</idno>
</biblStruct>
</sourceDesc>
<seriesStmt><idno type="ISSN">0363-9061</idno>
</seriesStmt>
</fileDesc>
<profileDesc><textClass><keywords scheme="KwdEn" xml:lang="en"><term>modified cam clay</term>
<term>neural networks</term>
<term>parameter identification</term>
<term>self‐boring pressuremeter</term>
<term>soft clay deposit</term>
</keywords>
</textClass>
<langUsage><language ident="en">en</language>
</langUsage>
</profileDesc>
</teiHeader>
<front><div type="abstract" xml:lang="en">This paper presents a numerical procedure of material parameter identification for the coupled hydro‐mechanical boundary value problem (BVP) of the self‐boring pressuremeter test (SBPT) in clay. First, the neural network (NN) technique is applied to obtain an initial estimate of model parameters, taking into account the possible drainage conditions during the expansion test. This technique is used to avoid potential pitfalls related to the conventional gradient‐based optimization techniques, considered here as a corrector that improves predicted parameters. Parameter identification based on measurements obtained through the pressuremeter expansion test and two types of holding tests is illustrated on the Modified Cam clay model. NNs are trained using a set of test samples, which are generated by means of finite element simulations of SBPT. The measurements obtained through expansion and consolidation tests are normalized so that NN predictors operate independently of the testing depth. Examples of parameter determination are demonstrated on both numerical and field data. The efficiency of the combined parameter identification in terms of accuracy, effectiveness and computational effort is also discussed. Copyright © 2008 John Wiley & Sons, Ltd.</div>
</front>
</TEI>
<affiliations><list><country><li>Pologne</li>
<li>Suisse</li>
</country>
<region><li>Canton de Vaud</li>
</region>
<settlement><li>Lausanne</li>
</settlement>
<orgName><li>École polytechnique fédérale de Lausanne</li>
</orgName>
</list>
<tree><country name="Suisse"><region name="Canton de Vaud"><name sortKey="Obrzud, Rafal F" sort="Obrzud, Rafal F" uniqKey="Obrzud R" first="Rafał F." last="Obrzud">Rafał F. Obrzud</name>
</region>
<name sortKey="Vulliet, Laurent" sort="Vulliet, Laurent" uniqKey="Vulliet L" first="Laurent" last="Vulliet">Laurent Vulliet</name>
</country>
<country name="Pologne"><noRegion><name sortKey="Truty, Andrzej" sort="Truty, Andrzej" uniqKey="Truty A" first="Andrzej" last="Truty">Andrzej Truty</name>
</noRegion>
</country>
</tree>
</affiliations>
</record>
Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Ticri/CIDE/explor/OcrV1/Data/Main/Exploration
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 000A21 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 000A21 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien |wiki= Ticri/CIDE |area= OcrV1 |flux= Main |étape= Exploration |type= RBID |clé= ISTEX:6F74BE073B110E3118395C214CA00DECBABAEB13 |texte= A combined neural network/gradient‐based approach for the identification of constitutive model parameters using self‐boring pressuremeter tests }}
This area was generated with Dilib version V0.6.32. |