Tracking Turbulent Coherent Structures by Means of Neural Networks
The behaviours of individual flow structures have become a relevant matter of study in turbulent flows as the computational power to allow their study feasible has become available. Especially, high instantaneous Reynolds Stress events have been found to dominate the behaviour of the logarithmic lay...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-02-01
|
| Series: | Energies |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1996-1073/14/4/984 |
| _version_ | 1797396652537937920 |
|---|---|
| author | Jose J. Aguilar-Fuertes Francisco Noguero-Rodríguez José C. Jaen Ruiz Luis M. García-RAffi Sergio Hoyas |
| author_facet | Jose J. Aguilar-Fuertes Francisco Noguero-Rodríguez José C. Jaen Ruiz Luis M. García-RAffi Sergio Hoyas |
| author_sort | Jose J. Aguilar-Fuertes |
| collection | DOAJ |
| description | The behaviours of individual flow structures have become a relevant matter of study in turbulent flows as the computational power to allow their study feasible has become available. Especially, high instantaneous Reynolds Stress events have been found to dominate the behaviour of the logarithmic layer. In this work, we present a viability study where two machine learning solutions are proposed to reduce the computational cost of tracking such structures in large domains. The first one is a Multi-Layer Perceptron. The second one uses Long Short-Term Memory (LSTM). Both of the methods are developed with the objective of taking the the structures’ geometrical features as inputs from which to predict the structures’ geometrical features in future time steps. Some of the tested Multi-Layer Perceptron architectures proved to perform better and achieve higher accuracy than the LSTM architectures tested, providing lower errors on the predictions and achieving higher accuracy in relating the structures in the consecutive time steps. |
| first_indexed | 2024-03-09T00:54:28Z |
| format | Article |
| id | doaj.art-65ec99c5411a421da32ca5791e598007 |
| institution | Directory Open Access Journal |
| issn | 1996-1073 |
| language | English |
| last_indexed | 2024-03-09T00:54:28Z |
| publishDate | 2021-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Energies |
| spelling | doaj.art-65ec99c5411a421da32ca5791e5980072023-12-11T16:57:56ZengMDPI AGEnergies1996-10732021-02-0114498410.3390/en14040984Tracking Turbulent Coherent Structures by Means of Neural NetworksJose J. Aguilar-Fuertes0Francisco Noguero-Rodríguez1José C. Jaen Ruiz2Luis M. García-RAffi3Sergio Hoyas4Instituto Universitario de Matemática Pura y Aplicada, Universitat Politècnica de València, 46022 València, SpainInstituto Universitario de Matemática Pura y Aplicada, Universitat Politècnica de València, 46022 València, SpainInstituto Universitario de Matemática Pura y Aplicada, Universitat Politècnica de València, 46022 València, SpainInstituto Universitario de Matemática Pura y Aplicada, Universitat Politècnica de València, 46022 València, SpainInstituto Universitario de Matemática Pura y Aplicada, Universitat Politècnica de València, 46022 València, SpainThe behaviours of individual flow structures have become a relevant matter of study in turbulent flows as the computational power to allow their study feasible has become available. Especially, high instantaneous Reynolds Stress events have been found to dominate the behaviour of the logarithmic layer. In this work, we present a viability study where two machine learning solutions are proposed to reduce the computational cost of tracking such structures in large domains. The first one is a Multi-Layer Perceptron. The second one uses Long Short-Term Memory (LSTM). Both of the methods are developed with the objective of taking the the structures’ geometrical features as inputs from which to predict the structures’ geometrical features in future time steps. Some of the tested Multi-Layer Perceptron architectures proved to perform better and achieve higher accuracy than the LSTM architectures tested, providing lower errors on the predictions and achieving higher accuracy in relating the structures in the consecutive time steps.https://www.mdpi.com/1996-1073/14/4/984turbulenceturbulent structuresDNSmachine learningneural networks |
| spellingShingle | Jose J. Aguilar-Fuertes Francisco Noguero-Rodríguez José C. Jaen Ruiz Luis M. García-RAffi Sergio Hoyas Tracking Turbulent Coherent Structures by Means of Neural Networks Energies turbulence turbulent structures DNS machine learning neural networks |
| title | Tracking Turbulent Coherent Structures by Means of Neural Networks |
| title_full | Tracking Turbulent Coherent Structures by Means of Neural Networks |
| title_fullStr | Tracking Turbulent Coherent Structures by Means of Neural Networks |
| title_full_unstemmed | Tracking Turbulent Coherent Structures by Means of Neural Networks |
| title_short | Tracking Turbulent Coherent Structures by Means of Neural Networks |
| title_sort | tracking turbulent coherent structures by means of neural networks |
| topic | turbulence turbulent structures DNS machine learning neural networks |
| url | https://www.mdpi.com/1996-1073/14/4/984 |
| work_keys_str_mv | AT josejaguilarfuertes trackingturbulentcoherentstructuresbymeansofneuralnetworks AT francisconoguerorodriguez trackingturbulentcoherentstructuresbymeansofneuralnetworks AT josecjaenruiz trackingturbulentcoherentstructuresbymeansofneuralnetworks AT luismgarciaraffi trackingturbulentcoherentstructuresbymeansofneuralnetworks AT sergiohoyas trackingturbulentcoherentstructuresbymeansofneuralnetworks |