Deep Learning of Temperature – Dependent Stress – Strain Hardening Curves
In this study, structure – property relationships (SPR) have been investigated using machine learning methods (ML). The research objective was to create a ML model that can predict the stress – strain response of materials at different temperatures from a given microstructure with industrially accep...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Académie des sciences
2023-05-01
|
| Series: | Comptes Rendus. Mécanique |
| Subjects: | |
| Online Access: | https://comptes-rendus.academie-sciences.fr/mecanique/articles/10.5802/crmeca.185/ |
| _version_ | 1797651389317382144 |
|---|---|
| author | Nikolić, Filip Čanađija, Marko |
| author_facet | Nikolić, Filip Čanađija, Marko |
| author_sort | Nikolić, Filip |
| collection | DOAJ |
| description | In this study, structure – property relationships (SPR) have been investigated using machine learning methods (ML). The research objective was to create a ML model that can predict the stress – strain response of materials at different temperatures from a given microstructure with industrially acceptable accuracy and high computational efficiency. Automated microstructure generation techniques and numerical simulations were developed to create a dataset for the ML model. Two – phase 3D representative volume elements (RVEs) were analyzed using finite element analysis (FEA) to obtain the stress – strain responses of the RVEs. The phase arrangement of the RVEs, the temperature, and the stress – strain responses were used to train the ML model. The microstructure arrangement and the temperature – dependent mechanical properties of each phase were known parameters, while the output parameter was the stress – strain response of the two – phase RVE. The ML model has shown excellent prediction accuracy in the temperature range from 20 °C to 250 °C. In addition, the model showed very high computational efficiency compared to FEA, allowing much faster prediction of the stress – strain curves at specific temperatures. |
| first_indexed | 2024-03-11T16:15:14Z |
| format | Article |
| id | doaj.art-7a792f7128c4414db97999b168753d7f |
| institution | Directory Open Access Journal |
| issn | 1873-7234 |
| language | English |
| last_indexed | 2024-03-11T16:15:14Z |
| publishDate | 2023-05-01 |
| publisher | Académie des sciences |
| record_format | Article |
| series | Comptes Rendus. Mécanique |
| spelling | doaj.art-7a792f7128c4414db97999b168753d7f2023-10-24T14:21:13ZengAcadémie des sciencesComptes Rendus. Mécanique1873-72342023-05-01351G115117010.5802/crmeca.18510.5802/crmeca.185Deep Learning of Temperature – Dependent Stress – Strain Hardening CurvesNikolić, Filip0https://orcid.org/0000-0002-4343-5069Čanađija, Marko1https://orcid.org/0000-0001-6550-0258Elaphe Propulsion Technologies Ltd, CAE Department, Litostrojska 44c, 1000 Ljubljana, Slovenia; University of Rijeka, Faculty of Engineering, Department of Engineering Mechanics, Vukovarska 58, 51000 Rijeka, CroatiaUniversity of Rijeka, Faculty of Engineering, Department of Engineering Mechanics, Vukovarska 58, 51000 Rijeka, CroatiaIn this study, structure – property relationships (SPR) have been investigated using machine learning methods (ML). The research objective was to create a ML model that can predict the stress – strain response of materials at different temperatures from a given microstructure with industrially acceptable accuracy and high computational efficiency. Automated microstructure generation techniques and numerical simulations were developed to create a dataset for the ML model. Two – phase 3D representative volume elements (RVEs) were analyzed using finite element analysis (FEA) to obtain the stress – strain responses of the RVEs. The phase arrangement of the RVEs, the temperature, and the stress – strain responses were used to train the ML model. The microstructure arrangement and the temperature – dependent mechanical properties of each phase were known parameters, while the output parameter was the stress – strain response of the two – phase RVE. The ML model has shown excellent prediction accuracy in the temperature range from 20 °C to 250 °C. In addition, the model showed very high computational efficiency compared to FEA, allowing much faster prediction of the stress – strain curves at specific temperatures.https://comptes-rendus.academie-sciences.fr/mecanique/articles/10.5802/crmeca.185/deep learningtemperature dependent stress – strain curvesstructure – property relationshipsfinite element analysismachine learning |
| spellingShingle | Nikolić, Filip Čanađija, Marko Deep Learning of Temperature – Dependent Stress – Strain Hardening Curves Comptes Rendus. Mécanique deep learning temperature dependent stress – strain curves structure – property relationships finite element analysis machine learning |
| title | Deep Learning of Temperature – Dependent Stress – Strain Hardening Curves |
| title_full | Deep Learning of Temperature – Dependent Stress – Strain Hardening Curves |
| title_fullStr | Deep Learning of Temperature – Dependent Stress – Strain Hardening Curves |
| title_full_unstemmed | Deep Learning of Temperature – Dependent Stress – Strain Hardening Curves |
| title_short | Deep Learning of Temperature – Dependent Stress – Strain Hardening Curves |
| title_sort | deep learning of temperature dependent stress strain hardening curves |
| topic | deep learning temperature dependent stress – strain curves structure – property relationships finite element analysis machine learning |
| url | https://comptes-rendus.academie-sciences.fr/mecanique/articles/10.5802/crmeca.185/ |
| work_keys_str_mv | AT nikolicfilip deeplearningoftemperaturedependentstressstrainhardeningcurves AT canađijamarko deeplearningoftemperaturedependentstressstrainhardeningcurves |