| 1. |
- Soleimani, M., et al.
(författare)
-
A multiphysics-based artificial neural networks model for atherosclerosis
- 2023
-
Ingår i: Heliyon. - 2405-8440. ; 9
-
Tidskriftsartikel (refereegranskat)abstract
- Atherosclerosis is a medical condition involving the hardening and/or thickening of arteries' walls. Mathematical multi-physics models have been developed to predict the development of atherosclerosis under different conditions. However, these models are typically computationally expensive. In this study, we used machine learning techniques, particularly artificial neural networks (ANN), to enhance the computational efficiency of these models. A database of multi-physics Finite Element Method (FEM) simulations was created and used for training and validating an ANN model. The model is capable of quick and accurate prediction of atherosclerosis development. A remarkable computational gain is obtained using the ANN model compared to the original FEM simulations.
|
|
| 2. |
|
|
| 3. |
- Araújo, M.C., et al.
(författare)
-
Predicting the mechanical behavior of amorphous polymeric materials under strain through multi-scale simulation
- 2014
-
Ingår i: Applied Surface Science. - : Elsevier BV. - 0169-4332. ; 306, s. 37-46
-
Tidskriftsartikel (refereegranskat)abstract
- Polymeric materials have become the reference material for high reliability and performance applications. However, their performance in service conditions is difficult to predict, due in large part to their inherent complex morphology, which leads to non-linear and anisotropic behavior, highly dependent on the thermomechanical environment under which it is processed. In this work, a multiscale approach is proposed to investigate the mechanical properties of polymeric-based material under strain. To achieve a better understanding of phenomena occurring at the smaller scales, the coupling of a finite element method (FEM) and molecular dynamics (MD) modeling, in an iterative procedure, was employed, enabling the prediction of the macroscopic constitutive response. As the mechanical response can be related to the local microstructure, which in turn depends on the nano-scale structure, this multiscale approach computes the stress-strain relationship at every analysis point of the macro-structure by detailed modeling of the underlying micro- and meso-scale deformation phenomena. The proposed multiscale approach can enable prediction of properties at the macroscale while taking into consideration phenomena that occur at the mesoscale, thus offering an increased potential accuracy compared to traditional methods.
|
|
| 4. |
- Castricum, B. A., et al.
(författare)
-
A computationally efficient coupled multi-scale model for short fiber reinforced composites
- 2022
-
Ingår i: Composites Part A: Applied Science and Manufacturing. - : Elsevier BV. - 1359-835X. ; 163
-
Tidskriftsartikel (refereegranskat)abstract
- A coupled multi-scale (macro–micro) model is developed to predict non-linear elasto-plastic behavior of short fiber reinforced composites. At the microscopic level, a recently proposed micro-mechanical model, developed based on a two-step orientation averaging approach, is used. A wide range of micro-structural parameters, including matrix and fiber constitutive parameters, fiber volume fraction and fiber aspect ratio, can be accommodated in the model. Different interactions including Voigt, Reuss and a self-consistent assumption are considered in the model. This micro-mechanical model is then incorporated in a Finite Element model of the macro-scale problem, enabling coupled macro–micro simulations of real-life structures/specimens. Numerical examples and comparisons with experimental data, taken from literature, show that the model gives good predictions. Besides, several strategies and techniques are employed to improve the computational efficiency of the model. These techniques include replacing originally utilized trapezoidal integration (for fiber orientations and calculation of the Eshelby tensor) with more efficient integration schemes, and using a more efficient method for data storage. Comparisons of the computational efforts shows that these improvements substantially decreased the computational cost of the model.
|
|
| 5. |
|
|
| 6. |
- Cheung, Hon Lam, et al.
(författare)
-
A multi-fidelity data-driven model for highly accurate and computationally efficient modeling of short fiber composites
- 2024
-
Ingår i: Composites Science and Technology. - 0266-3538. ; 246
-
Tidskriftsartikel (refereegranskat)abstract
- To develop physics-based models and establish a structure–property relationship for short fiber composites, there are a wide range of micro-structural properties to be considered. To achieve a high accuracy, high-fidelity full-field simulations are required. These simulations are computationally very expensive, and any single analysis could potentially take days to finish. A solution for this issue is to develop surrogate models using artificial neural networks. However, generating a high-fidelity data set requires a huge amount of time. To solve this problem, we used transfer learning technique, a limited amount of high-fidelity full-field simulations, together with a previously developed recurrent neural network model trained on low-fidelity mean-field data. The new RNN model has a very high accuracy (in comparison with full-field simulations) and is remarkably efficient. This model can be used not only for highly efficient modeling purposes, but also for designing new short fiber composites.
|
|
| 7. |
- Cheung, Hon Lam, et al.
(författare)
-
Augmentation of scarce data—A new approach for deep-learning modeling of composites
- 2024
-
Ingår i: Composites Science and Technology. - 0266-3538. ; 249
-
Tidskriftsartikel (refereegranskat)abstract
- High-fidelity full-field micro-mechanical modeling of the non-linear path-dependent materials demands a substantial computational effort. Recent trends in the field incorporates data-driven Artificial Neural Networks (ANNs) as surrogate models. However, ANNs are inherently data-hungry, functioning as a bottleneck for the development of high-fidelity data-driven models. This study introduces a novel approach for data augmentation, expanding an original dataset without additional computational simulations. A Recurrent Neural Network (RNN) was trained and validated on high-fidelity micro-mechanical simulations of elasto-plastic short fiber reinforced composites. The obtained results showed a considerable improvement of the network predictions trained on expanded datasets using the proposed data augmentation approach. The proposed method for augmentation of scarce data may be used not only for other kind of composites, but also for other materials and at different length scales, and hence, opening avenues for innovative data-driven models in materials science and computational mechanics.
|
|
| 8. |
|
|
| 9. |
- Friemann, J., et al.
(författare)
-
A micromechanics-based recurrent neural networks model for path-dependent cyclic deformation of short fiber composites
- 2023
-
Ingår i: International Journal for Numerical Methods in Engineering. - : Wiley. - 0029-5981 .- 1097-0207. ; 124:10, s. 2292-2314
-
Tidskriftsartikel (refereegranskat)abstract
- The macroscopic response of short fiber reinforced composites (SFRCs) is dependent on an extensive range of microstructural parameters. Thus, micromechanical modeling of these materials is challenging and in some cases, computationally expensive. This is particularly important when path-dependent plastic behavior is needed to be predicted. A solution to this challenge is to enhance micromechanical solutions with machine learning techniques such as artificial neural networks. In this work, a recurrent deep neural network model is trained to predict the path-dependent elasto-plastic stress response of SFRCs, given the microstructural parameters and the strain path. Micromechanical mean-field simulations are conducted to create a database for training the validating the model. The model gives very accurate predictions in a computationally efficient manner when compared with independent micromechanical simulations.
|
|
| 10. |
|
|
