Multiscale Analysis of Composite Structures with Artificial Neural Network Support for Micromodel Stress Determination
Structures made of heterogeneous materials, such as composites, often require a multiscale approach when their behavior is simulated using the finite element method. By solving the boundary value problem of the macroscale model, for previously homogenized material properties, the resulting stress ma...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-12-01
|
| Series: | Materials |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1996-1944/17/1/154 |
| _version_ | 1797358517547433984 |
|---|---|
| author | Wacław Kuś Waldemar Mucha Iyasu Tafese Jiregna |
| author_facet | Wacław Kuś Waldemar Mucha Iyasu Tafese Jiregna |
| author_sort | Wacław Kuś |
| collection | DOAJ |
| description | Structures made of heterogeneous materials, such as composites, often require a multiscale approach when their behavior is simulated using the finite element method. By solving the boundary value problem of the macroscale model, for previously homogenized material properties, the resulting stress maps can be obtained. However, such stress results do not describe the actual behavior of the material and are often significantly different from the actual stresses in the heterogeneous microstructure. Finding high-accuracy stress results for such materials leads to time-consuming analyses in both scales. This paper focuses on the application of machine learning to multiscale analysis of structures made of composite materials, to substantially decrease the time of computations of such localization problems. The presented methodology was validated by a numerical example where a structure made of resin epoxy with randomly distributed short glass fibers was analyzed using a computational multiscale approach. Carefully prepared training data allowed artificial neural networks to learn relationships between two scales and significantly increased the efficiency of the multiscale approach. |
| first_indexed | 2024-03-08T15:02:09Z |
| format | Article |
| id | doaj.art-2b6586d73827464da85677472a1f95c0 |
| institution | Directory Open Access Journal |
| issn | 1996-1944 |
| language | English |
| last_indexed | 2024-03-08T15:02:09Z |
| publishDate | 2023-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Materials |
| spelling | doaj.art-2b6586d73827464da85677472a1f95c02024-01-10T15:02:47ZengMDPI AGMaterials1996-19442023-12-0117115410.3390/ma17010154Multiscale Analysis of Composite Structures with Artificial Neural Network Support for Micromodel Stress DeterminationWacław Kuś0Waldemar Mucha1Iyasu Tafese Jiregna2Department of Computational Mechanics and Engineering, Silesian University of Technology, 44-100 Gliwice, PolandDepartment of Computational Mechanics and Engineering, Silesian University of Technology, 44-100 Gliwice, PolandDepartment of Computational Mechanics and Engineering, Silesian University of Technology, 44-100 Gliwice, PolandStructures made of heterogeneous materials, such as composites, often require a multiscale approach when their behavior is simulated using the finite element method. By solving the boundary value problem of the macroscale model, for previously homogenized material properties, the resulting stress maps can be obtained. However, such stress results do not describe the actual behavior of the material and are often significantly different from the actual stresses in the heterogeneous microstructure. Finding high-accuracy stress results for such materials leads to time-consuming analyses in both scales. This paper focuses on the application of machine learning to multiscale analysis of structures made of composite materials, to substantially decrease the time of computations of such localization problems. The presented methodology was validated by a numerical example where a structure made of resin epoxy with randomly distributed short glass fibers was analyzed using a computational multiscale approach. Carefully prepared training data allowed artificial neural networks to learn relationships between two scales and significantly increased the efficiency of the multiscale approach.https://www.mdpi.com/1996-1944/17/1/154multiscale modelingfinite element methodhomogenizationartificial neural networkcomposite materialfiber-reinforced composite |
| spellingShingle | Wacław Kuś Waldemar Mucha Iyasu Tafese Jiregna Multiscale Analysis of Composite Structures with Artificial Neural Network Support for Micromodel Stress Determination Materials multiscale modeling finite element method homogenization artificial neural network composite material fiber-reinforced composite |
| title | Multiscale Analysis of Composite Structures with Artificial Neural Network Support for Micromodel Stress Determination |
| title_full | Multiscale Analysis of Composite Structures with Artificial Neural Network Support for Micromodel Stress Determination |
| title_fullStr | Multiscale Analysis of Composite Structures with Artificial Neural Network Support for Micromodel Stress Determination |
| title_full_unstemmed | Multiscale Analysis of Composite Structures with Artificial Neural Network Support for Micromodel Stress Determination |
| title_short | Multiscale Analysis of Composite Structures with Artificial Neural Network Support for Micromodel Stress Determination |
| title_sort | multiscale analysis of composite structures with artificial neural network support for micromodel stress determination |
| topic | multiscale modeling finite element method homogenization artificial neural network composite material fiber-reinforced composite |
| url | https://www.mdpi.com/1996-1944/17/1/154 |
| work_keys_str_mv | AT wacławkus multiscaleanalysisofcompositestructureswithartificialneuralnetworksupportformicromodelstressdetermination AT waldemarmucha multiscaleanalysisofcompositestructureswithartificialneuralnetworksupportformicromodelstressdetermination AT iyasutafesejiregna multiscaleanalysisofcompositestructureswithartificialneuralnetworksupportformicromodelstressdetermination |