| 1. |
- Borrelli, Giuseppe, et al.
(författare)
-
Predicting the temporal dynamics of turbulent channels through deep learning
- 2022
-
Ingår i: International Journal of Heat and Fluid Flow. - : Elsevier BV. - 0142-727X .- 1879-2278. ; 96
-
Tidskriftsartikel (refereegranskat)abstract
- The success of recurrent neural networks (RNNs) has been demonstrated in many applications related to turbulence, including flow control, optimization, turbulent features reproduction as well as turbulence prediction and modeling. With this study we aim to assess the capability of these networks to reproduce the temporal evolution of a minimal turbulent channel flow. We first obtain a data-driven model based on a modal decom-position in the Fourier domain (which we denote as FFT-POD) of the time series sampled from the flow. This particular case of turbulent flow allows us to accurately simulate the most relevant coherent structures close to the wall. Long-short-term-memory (LSTM) networks and a Koopman-based framework (KNF) are trained to predict the temporal dynamics of the minimal-channel-flow modes. Tests with different configurations highlight the limits of the KNF method compared to the LSTM, given the complexity of the flow under study. Long-term prediction for LSTM show excellent agreement from the statistical point of view, with errors below 2% for the best models with respect to the reference. Furthermore, the analysis of the chaotic behaviour through the use of the Lyapunov exponents and of the dynamic behaviour through Poincare' maps emphasizes the ability of the LSTM to reproduce the temporal dynamics of turbulence. Alternative reduced-order models (ROMs), based on the identification of different turbulent structures, are explored and they continue to show a good potential in predicting the temporal dynamics of the minimal channel.
|
|
| 2. |
- Eivazi, Hamidreza, et al.
(författare)
-
Non-Linear Orthogonal Modal Decompositions in Turbulent Flows via Autoencoders
- 2022
-
Ingår i: 12th International Symposium on Turbulence and Shear Flow Phenomena, TSFP 2022. - : International Symposium on Turbulence and Shear Flow Phenomena, TSFP.
-
Konferensbidrag (refereegranskat)abstract
- We propose a deep probabilistic-neural-network architecture for learning a minimal and near-orthogonal set of nonlinear modes from high-fidelity turbulent-flow data. Our approach is based on β-variational autoencoders (β-VAEs) and convolutional neural networks (CNNs), which enable extracting non-linear modes from multi-scale turbulent flows while encouraging the learning of independent latent variables and penalizing the size of the latent vector. Moreover, we introduce an algorithm for ordering VAE-based modes with respect to their contribution to the reconstruction. We apply this method for non-linear mode decomposition of the turbulent flow through a simplified urban environment. We demonstrate that by constraining the shape of the latent space, it is possible to motivate the orthogonality and extract a set of parsimonious modes sufficient for high-quality reconstruction. Our results show the excellent performance of the method in the reconstruction against linear-theory-based decompositions. We show the ability of our approach in the extraction of near-orthogonal modes with the determinant of the correlation matrix equal to 0.99, which may lead to interpretability.
|
|
| 3. |
- Eivazi, Hamidreza, et al.
(författare)
-
Physics-informed neural networks for solving Reynolds-averaged Navier-Stokes equations
- 2022
-
Ingår i: Physics of fluids. - : AIP Publishing. - 1070-6631 .- 1089-7666. ; 34:8
-
Tidskriftsartikel (refereegranskat)abstract
- Physics-informed neural networks (PINNs) are successful machine-learning methods for the solution and identification of partial differential equations. We employ PINNs for solving the Reynolds-averaged Navier-Stokes equations for incompressible turbulent flows without any specific model or assumption for turbulence and by taking only the data on the domain boundaries. We first show the applicability of PINNs for solving the Navier-Stokes equations for laminar flows by solving the Falkner-Skan boundary layer. We then apply PINNs for the simulation of four turbulent flow cases, i.e., zero-pressure-gradient boundary layer, adverse-pressure-gradient boundary layer, and turbulent flows over a NACA4412 airfoil and the periodic hill. Our results show the excellent applicability of PINNs for laminar flows with strong pressure gradients, where predictions with less than 1% error can be obtained. For turbulent flows, we also obtain very good accuracy on simulation results even for the Reynolds-stress components.
|
|
| 4. |
- Eivazi, Hamidreza, et al.
(författare)
-
Towards extraction of orthogonal and parsimonious non-linear modes from turbulent flows
- 2022
-
Ingår i: Expert systems with applications. - : Elsevier BV. - 0957-4174 .- 1873-6793. ; 202, s. 117038-
-
Tidskriftsartikel (refereegranskat)abstract
- Modal-decomposition techniques are computational frameworks based on data aimed at identifying a low-dimensional space for capturing dominant flow features: the so-called modes. We propose a deep probabilistic-neural-network architecture for learning a minimal and near-orthogonal set of non-linear modes from high-fidelity turbulent-flow data useful for flow analysis, reduced-order modeling and flow control. Our approach is based on beta-variational autoencoders (beta-VAEs) and convolutional neural networks (CNNs), which enable extracting non-linear modes from multi-scale turbulent flows while encouraging the learning of independent latent variables and penalizing the size of the latent vector. Moreover, we introduce an algorithm for ordering VAE-based modes with respect to their contribution to the reconstruction. We apply this method for non-linear mode decomposition of the turbulent flow through a simplified urban environment, where the flow-field data is obtained based on well-resolved large-eddy simulations (LESs). We demonstrate that by constraining the shape of the latent space, it is possible to motivate the orthogonality and extract a set of parsimonious modes sufficient for high-quality reconstruction. Our results show the excellent performance of the method in the reconstruction against linear-theory-based decompositions, where the energy percentage captured by the proposed method from five modes is equal to 87.36% against 32.41% of the POD. Moreover, we compare our method with available AE-based models. We show the ability of our approach in the extraction of near-orthogonal modes with the determinant of the correlation matrix equal to 0.99, which may lead to interpretability.
|
|
| 5. |
- Sanchez-Roncero, A., et al.
(författare)
-
ASDG - An AI-based framework for automatic classification of impact on the SDGs
- 2022
-
Ingår i: ACM International Conference Proceeding Series. - New York, NY, USA : Association for Computing Machinery (ACM). ; , s. 119-123
-
Konferensbidrag (refereegranskat)abstract
- Achieving the Sustainable Development Goals of the United Nations is the primary goal of the 2030 Agenda. A critical step towards that objective is identifying if the scientific production is going in this way. Funders must do a manual recognition, impacting accuracy, scalability, and objectiveness. For this reason, we propose in this work an AI-based model for the automatic classification of scientific papers based on their impacts on the SDGs. The training database consists of manually extracted texts from the UN page. After preprocessing these texts, we train three models: NMF, LDA, and Top2Vec. The output of these models is the probability of a paper being associated with each SDG. We then combine their scores by implementing a voting function to take advantage of their inherently different mathematical nature. To validate this methodology, we use the database provided by Vinuesa et al., Nature Communications 11, with more than 150 papers labeled with at least 1 SDG. Using only the abstracts, we correctly identify a of the SDGs presented in a paper, while a better is obtained when fetching the complete paper information. Moreover, we find that the other identified SDGs which were not labeled are also related to the text contents. We recognize that more training files are required for the other cases since they are based on more complex human reasoning. We open-source these databases and trained models to enable future investigation in this field and allow public institutions to use this tool.
|
|
