Pasar al contenido principal

Resultados relacionados

Resultados totales (Incluyendo duplicados): 1
Encontrada(s) 1 página(s)

Recercat. Dipósit de la Recerca de Catalunya
Publicación Artículo científico (JournalArticle)

On deep-learning-based closures for algebraic surrogate models of turbulent flows

  • Eiximeno Franch, Benet
  • Sanchís Agudo, Marcial
  • Miró Jané, Arnau
  • Rodríguez Pérez, Ivette María
  • Vinuesa Motilva, Ricardo
  • Lehmkuhl Barba, Oriol
A deep-learning-based closure model to address energy loss in low-dimensional surrogate models based on proper-orthogonal-decomposition (POD) modes is introduced. Using a transformer-encoder block with an easy-attention mechanism, the model predicts the spatial probability density function of fluctuations not captured by the truncated POD modes. The methodology is demonstrated on the wake of the Windsor body at yaw angles of d=[2.5°,5°,7.5°,10°,12.5°] , with d=7.5° as a test case, and in a realistic urban environment at wind directions of d=[-45°,-22.5°,0°,22.5°,45°] , with d=0° as a test case. Key coherent modes are identified by clustering them based on dominant frequency dynamics using Hotelling’s T2 on the spectral properties of temporal coefficients. These coherent modes account for nearly 60% and 75% of the total energy for the Windsor body and the urban environment, respectively. For each case, a common POD basis is created by concatenating coherent modes from training angles and orthonormalising the set without losing information. Transformers with different size on the attention layer, (64, 128 and 256), are trained to model the missing fluctuations in the Windsor body case. Larger attention sizes always improve predictions for the training set, but the transformer with an attention layer of size 256 slightly overshoots the fluctuation predictions in the Windsor body test set because they have lower intensity than in the training cases. A single transformer with an attention size of 256 is trained for the urban flow. In both cases, adding the predicted fluctuations close the energy gap between the reconstruction and the original flow field, improving predictions for energy, root-mean-square velocity fluctuations and instantaneous flow fields. For instance, in the Windsor body case, the deepest architecture reduces the mean energy error from 37% to 12% and decreases the Kullback–Leibler divergence of velocity distributions from DKL=0.2 to below DKL=0.026., The research leading to this work has been partially funded by the project TIFON with reference PLEC2023-010251/ AEI/10.13039/501100011033. B. Eiximeno’s work was funded by a contract from the Subprograma de Ayudas Predoctorales given by the Ministerio de Ciencia e Innovación (PRE2021-096927). O. Lehmkuhl has been partially supported by a Ramon y Cajal postdoctoral contract (Ref: RYC2018-025949-I). The authors acknowledge the support of Departament de Recerca i Universitats de la Generalitat de Catalunya to the Research Group Large-scale Computational Fluid Dynamics (Code: 2021 SGR 00902) and the Turbulence and Aerodynamics Research Group (Code: 2021 SGR 01051). M. Sanchis-Agudo and R. Vinuesa would like to acknowledge the support from Marie Sklodowska-Curie Actions project MODELAIR, funded by the European Commission under the Horizon Europe program through grant agreement number 101072559., Peer Reviewed, 9.5 - Augmentar la investigació científica i millorar la capacitat tecnològica dels sectors industrials de tots els països, en particular els països en desenvolupament, entre d’altres maneres fomentant la innovació i augmentant substancialment, d’aquí al 2030, el nombre de persones que treballen en el camp de la investigació i el desenvolupament per cada milió d’habitants, així com la despesa en investigació i desenvolupament dels sectors públic i privat, 9 - Indústria, Innovació i Infraestructura, Postprint (published version)