Thermodynamically consistent Recurrent Neural Networks to predict non linear behaviors of dissipative materials subjected to non-proportional loading paths
dc.rights.license | open | en_US |
hal.structure.identifier | Institut de Mécanique et d'Ingénierie [I2M] | |
dc.contributor.author | DANOUN, Aymen
IDREF: 256486999 | |
hal.structure.identifier | Institut de Mécanique et d'Ingénierie [I2M] | |
dc.contributor.author | PRULIÈRE, Etienne | |
hal.structure.identifier | Institut de Mécanique et d'Ingénierie [I2M] | |
dc.contributor.author | CHEMISKY, Yves
IDREF: 143502301 | |
dc.date.accessioned | 2022-10-14T12:24:31Z | |
dc.date.available | 2022-10-14T12:24:31Z | |
dc.date.issued | 2022-10-01 | |
dc.identifier.issn | 0167-6636 | en_US |
dc.identifier.uri | oai:crossref.org:10.1016/j.mechmat.2022.104436 | |
dc.identifier.uri | https://oskar-bordeaux.fr/handle/20.500.12278/170000 | |
dc.description.abstractEn | The present work aims at proposing a hybrid physics-AI based model to predict non-linear mechanical behaviors of dissipative materials. By introducing a specific Neural Network architecture called Thermodynamically Consistent Recurrent Neural Networks (ThC-RNN), this study proposes a new paradigm for the simulation of dissipative materials under complex loading conditions. The design of such architecture allows to take into account the material loading history subjected to multi-axial and non-proportional loading paths, similarly to internal variables for homogeneous materials. A special focus has been given to the respect of thermodynamics principles in the ThC-RNN model by introducing specific thermodynamical constraints during the training phase. Finally, the model’s reliability has been tested on different plasticity models once the training is completed. It is shown that thermodynamic consistency improves significantly the prediction capabilities of the ThC-RNN model, considering several outputs such as stress tensor and tangent modulus components, state variables and mechanical work rate partition (recoverable part, irrecoverable part and dissipative part). | |
dc.language.iso | EN | en_US |
dc.source | crossref | |
dc.subject.en | Recurrent Neural Network (RNN) | |
dc.subject.en | Plasticity | |
dc.subject.en | Dissipative materials | |
dc.subject.en | Non-proportional loadings | |
dc.subject.en | Thermodynamics | |
dc.title.en | Thermodynamically consistent Recurrent Neural Networks to predict non linear behaviors of dissipative materials subjected to non-proportional loading paths | |
dc.type | Article de revue | en_US |
dc.identifier.doi | 10.1016/j.mechmat.2022.104436 | en_US |
dc.subject.hal | Sciences de l'ingénieur [physics]/Matériaux | en_US |
bordeaux.journal | Mechanics of Materials | en_US |
bordeaux.page | 104436 | en_US |
bordeaux.volume | 173 | en_US |
bordeaux.hal.laboratories | Institut de Mécanique et d’Ingénierie de Bordeaux (I2M) - UMR 5295 | en_US |
bordeaux.institution | Université de Bordeaux | en_US |
bordeaux.institution | Bordeaux INP | en_US |
bordeaux.institution | CNRS | en_US |
bordeaux.institution | INRAE | en_US |
bordeaux.institution | Arts et Métiers | en_US |
bordeaux.peerReviewed | oui | en_US |
bordeaux.inpress | non | en_US |
bordeaux.import.source | dissemin | |
hal.identifier | hal-03815188 | |
hal.version | 1 | |
hal.date.transferred | 2022-10-14T12:24:33Z | |
hal.export | true | |
workflow.import.source | dissemin | |
dc.rights.cc | Pas de Licence CC | en_US |
bordeaux.COinS | ctx_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.jtitle=Mechanics%20of%20Materials&rft.date=2022-10-01&rft.volume=173&rft.spage=104436&rft.epage=104436&rft.eissn=0167-6636&rft.issn=0167-6636&rft.au=DANOUN,%20Aymen&PRULI%C3%88RE,%20Etienne&CHEMISKY,%20Yves&rft.genre=article |
Fichier(s) constituant ce document
Fichiers | Taille | Format | Vue |
---|---|---|---|
Il n'y a pas de fichiers associés à ce document. |