The computational cost associated with simulating fluid flows can make it infeasible to run many simulations across multiple flow conditions. Building upon concepts from generative modeling, we introduce a new method for learning neural network models capable of performing efficient parameterized simulations of fluid flows. Evaluated on their ability to simulate both two-dimensional and three-dimensional fluid flows, trained models are shown to capture local and global properties of the flowfields at a wide array of flow conditions. Furthermore, flow simulations generated by the trained models are shown to be orders of magnitude faster than the corresponding computational fluid dynamics simulations.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Parameter-Conditioned Sequential Generative Modeling of Fluid Flows


    Contributors:

    Published in:

    AIAA Journal ; 59 , 3 ; 825-841


    Publication date :

    2021-03-01




    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    English




    Generalized Zero-Shot Learning via VAE-Conditioned Generative Flow

    Gu, Yu-Chao / Zhang, Le / Liu, Yun et al. | ArXiv | 2020

    Free access

    A Generative Car-following Model Conditioned On Driving Styles

    Zhang, Yifan / Chen, Xinhong / Wang, Jianping et al. | ArXiv | 2021

    Free access

    Fluid Flow Regimes in Air Conditioned Rooms

    El Erian, Asser / Khalil, Essam | AIAA | 2004