IDEAS home Printed from https://ideas.repec.org/a/gam/jeners/v14y2021i4p984-d498813.html
   My bibliography  Save this article

Tracking Turbulent Coherent Structures by Means of Neural Networks

Author

Listed:
  • Jose J. Aguilar-Fuertes

    (Instituto Universitario de Matemática Pura y Aplicada, Universitat Politècnica de València, 46022 València, Spain
    These authors contributed equally to this work.)

  • Francisco Noguero-Rodríguez

    (Instituto Universitario de Matemática Pura y Aplicada, Universitat Politècnica de València, 46022 València, Spain
    These authors contributed equally to this work.)

  • José C. Jaen Ruiz

    (Instituto Universitario de Matemática Pura y Aplicada, Universitat Politècnica de València, 46022 València, Spain
    These authors contributed equally to this work.)

  • Luis M. García-RAffi

    (Instituto Universitario de Matemática Pura y Aplicada, Universitat Politècnica de València, 46022 València, Spain)

  • Sergio Hoyas

    (Instituto Universitario de Matemática Pura y Aplicada, Universitat Politècnica de València, 46022 València, Spain)

Abstract

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.

Suggested Citation

  • Jose J. Aguilar-Fuertes & Francisco Noguero-Rodríguez & José C. Jaen Ruiz & Luis M. García-RAffi & Sergio Hoyas, 2021. "Tracking Turbulent Coherent Structures by Means of Neural Networks," Energies, MDPI, vol. 14(4), pages 1-15, February.
    • Handle: RePEc:gam:jeners:v:14:y:2021:i:4:p:984-:d:498813
    as

    Download full text from publisher

    File URL: https://www.mdpi.com/1996-1073/14/4/984/pdf
    Download Restriction: no
    File URL: https://www.mdpi.com/1996-1073/14/4/984/
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Chao Jiang & Junyi Mi & Shujin Laima & Hui Li, 2020. "A Novel Algebraic Stress Model with Machine-Learning-Assisted Parameterization," Energies, MDPI, vol. 13(1), pages 1-21, January.
    2. Bahrami, Mehrdad & Akbari, Mohammad & Bagherzadeh, Seyed Amin & Karimipour, Arash & Afrand, Masoud & Goodarzi, Marjan, 2019. "Develop 24 dissimilar ANNs by suitable architectures & training algorithms via sensitivity analysis to better statistical presentation: Measure MSEs between targets & ANN for Fe–CuO/Eg–Water nanofluid," Physica A: Statistical Mechanics and its Applications, Elsevier, vol. 519(C), pages 159-168.
    3. Mikhail Tokarev & Egor Palkin & Rustam Mullyadzhanov, 2020. "Deep Reinforcement Learning Control of Cylinder Flow Using Rotary Oscillations at Low Reynolds Number," Energies, MDPI, vol. 13(22), pages 1-11, November.
    Full references (including those not matched with items on IDEAS)

    Citations

    Citations are extracted by the CitEc Project, subscribe to its RSS feed for this item.
    as


    Cited by:

    1. Ricardo Vinuesa & Soledad Le Clainche, 2022. "Machine-Learning Methods for Complex Flows," Energies, MDPI, vol. 15(4), pages 1-5, February.
    2. Simone Ferrari & Riccardo Rossi & Annalisa Di Bernardino, 2022. "A Review of Laboratory and Numerical Techniques to Simulate Turbulent Flows," Energies, MDPI, vol. 15(20), pages 1-56, October.

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Ricardo Vinuesa & Soledad Le Clainche, 2022. "Machine-Learning Methods for Complex Flows," Energies, MDPI, vol. 15(4), pages 1-5, February.
    2. Wu, Huawei & Bagherzadeh, Seyed Amin & D’Orazio, Annunziata & Habibollahi, Navid & Karimipour, Arash & Goodarzi, Marjan & Bach, Quang-Vu, 2019. "Present a new multi objective optimization statistical Pareto frontier method composed of artificial neural network and multi objective genetic algorithm to improve the pipe flow hydrodynamic and ther," Physica A: Statistical Mechanics and its Applications, Elsevier, vol. 535(C).
    3. Al-Rashed, Abdullah A.A.A., 2019. "Optimization of heat transfer and pressure drop of nano-antifreeze using statistical method of response surface methodology," Physica A: Statistical Mechanics and its Applications, Elsevier, vol. 521(C), pages 531-542.
    4. Roy Setiawan & Reza Daneshfar & Omid Rezvanjou & Siavash Ashoori & Maryam Naseri, 2021. "Surface tension of binary mixtures containing environmentally friendly ionic liquids: Insights from artificial intelligence," Environment, Development and Sustainability: A Multidisciplinary Approach to the Theory and Practice of Sustainable Development, Springer, vol. 23(12), pages 17606-17627, December.
    5. Mohammed Algarni & Mashhour A. Alazwari & Mohammad Reza Safaei, 2021. "Optimization of Nano-Additive Characteristics to Improve the Efficiency of a Shell and Tube Thermal Energy Storage System Using a Hybrid Procedure: DOE, ANN, MCDM, MOO, and CFD Modeling," Mathematics, MDPI, vol. 9(24), pages 1-30, December.
    6. Li, Zhixiong & Shahrajabian, Hamzeh & Bagherzadeh, Seyed Amin & Jadidi, Hamid & Karimipour, Arash & Tlili, Iskander, 2020. "Effects of nano-clay content, foaming temperature and foaming time on density and cell size of PVC matrix foam by presented Least Absolute Shrinkage and Selection Operator statistical regression via s," Physica A: Statistical Mechanics and its Applications, Elsevier, vol. 537(C).
    7. Ahmadi, Mohammad Hossein & Baghban, Alireza & Sadeghzadeh, Milad & Hadipoor, Masoud & Ghazvini, Mahyar, 2020. "Evolving connectionist approaches to compute thermal conductivity of TiO2/water nanofluid," Physica A: Statistical Mechanics and its Applications, Elsevier, vol. 540(C).
    8. Zheng, Yuanzhou & Shadloo, Mostafa Safdari & Nasiri, Hossein & Maleki, Akbar & Karimipour, Arash & Tlili, Iskander, 2020. "Prediction of viscosity of biodiesel blends using various artificial model and comparison with empirical correlations," Renewable Energy, Elsevier, vol. 153(C), pages 1296-1306.
    9. Peng, Yeping & Parsian, Amir & Khodadadi, Hossein & Akbari, Mohammad & Ghani, Kamal & Goodarzi, Marjan & Bach, Quang-Vu, 2020. "Develop optimal network topology of artificial neural network (AONN) to predict the hybrid nanofluids thermal conductivity according to the empirical data of Al2O3 – Cu nanoparticles dispersed in ethy," Physica A: Statistical Mechanics and its Applications, Elsevier, vol. 549(C).
    10. Jiang, Ping & Liu, Zhenkun & Niu, Xinsong & Zhang, Lifang, 2021. "A combined forecasting system based on statistical method, artificial neural networks, and deep learning methods for short-term wind speed forecasting," Energy, Elsevier, vol. 217(C).
    11. Ammar A. Melaibari & Yacine Khetib & Abdullah K. Alanazi & S. Mohammad Sajadi & Mohsen Sharifpur & Goshtasp Cheraghian, 2021. "Applying Artificial Neural Network and Response Surface Method to Forecast the Rheological Behavior of Hybrid Nano-Antifreeze Containing Graphene Oxide and Copper Oxide Nanomaterials," Sustainability, MDPI, vol. 13(20), pages 1-17, October.
    12. Shanti Bhushan & Greg W. Burgreen & Wesley Brewer & Ian D. Dettwiller, 2021. "Development and Validation of a Machine Learned Turbulence Model," Energies, MDPI, vol. 14(5), pages 1-34, March.
    13. Tian, Zhe & Arasteh, Hossein & Parsian, Amir & Karimipour, Arash & Safaei, Mohammad Reza & Nguyen, Truong Khang, 2019. "Estimate the shear rate & apparent viscosity of multi-phased non-Newtonian hybrid nanofluids via new developed Support Vector Machine method coupled with sensitivity analysis," Physica A: Statistical Mechanics and its Applications, Elsevier, vol. 535(C).
    14. Zarei, Amir & Karimipour, Arash & Meghdadi Isfahani, Amir Homayoon & Tian, Zhe, 2019. "Improve the performance of lattice Boltzmann method for a porous nanoscale transient flow by provide a new modified relaxation time equation," Physica A: Statistical Mechanics and its Applications, Elsevier, vol. 535(C).
    15. Wei, Li & Arasteh, Hossein & abdollahi, Ali & Parsian, Amir & Taghipour, Abdolmajid & Mashayekhi, Ramin & Tlili, Iskander, 2020. "Locally weighted moving regression: A non-parametric method for modeling nanofluid features of dynamic viscosity," Physica A: Statistical Mechanics and its Applications, Elsevier, vol. 550(C).

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:gam:jeners:v:14:y:2021:i:4:p:984-:d:498813. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: MDPI Indexing Manager (email available below). General contact details of provider: https://www.mdpi.com .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.