Gast ::
| Hauptseite > Publikationsdatenbank > Deciphering the dynamics of distorted turbulent flows: Lagrangian particle tracking and chaos prediction through transformer-based deep learning models |
| Hauptseite > Publikationsdatenbank > Deciphering the dynamics of distorted turbulent flows: Lagrangian particle tracking and chaos prediction through transformer-based deep learning models |
| Journal Article | FZJ-2024-03131 |
; ; ;
2023
American Institute of Physics
[Erscheinungsort nicht ermittelbar]
This record in other databases: 
Please use a persistent id in citations: doi:10.1063/5.0157897 doi:10.34734/FZJ-2024-03131
Abstract: Turbulent flow is a complex and vital phenomenon in fluid dynamics, as it is the most common type of flow in both natural and artificialsystems. Traditional methods of studying turbulent flow, such as computational fluid dynamics and experiments, have limitations such ashigh computational costs, experiment costs, and restricted problem scales and sizes. Recently, artificial intelligence has provided a newavenue for examining turbulent flow, which can help improve our understanding of its flow features and physics in various applications.Strained turbulent flow, which occurs in the presence of gravity in situations such as combustion chambers and shear flow, is one such case.This study proposes a novel data-driven transformer model to predict the velocity field of turbulent flow, building on the success of this deepsequential learning technique in areas such as language translation and music. The present study applied this model to experimental work byHassanian et al., who studied distorted turbulent flow with a specific range of Taylor microscale Reynolds numbers 100 < Rek < 120. Theflow underwent a vertical mean strain rate of 8 s^-1 in the presence of gravity. The Lagrangian particle tracking technique recorded everytracer particle’s velocity field and displacement. Using this dataset, the transformer model was trained with different ratios of data and usedto predict the velocity of the following period. The model’s predictions significantly matched the experimental test data, with a mean absoluteerror of 0.002–0.003 and an R2 score of 0.98. Furthermore, the model demonstrated its ability to maintain high predictive performance withless training data, showcasing its potential to predict future turbulent flow velocity with fewer computational resources. To assess the model,it has been compared to the long short-term memory and gated recurrent units model. High-performance computing machines, such asJUWELS-DevelBOOSTER at the Juelich Supercomputing Center, were used to train and run the model for inference.
; 
; 
; Clarivate Analytics Master Journal List ; Current Contents - Physical, Chemical and Earth Sciences ; Ebsco Academic Search ; Essential Science Indicators ; IF < 5 ; JCR ; NCBI Molecular Biology Database ; National-Konsortium ; PubMed Central ; SCOPUS ; Science Citation Index Expanded ; Web of Science Core Collection
|
The record appears in these collections: |
PDF