Deep Learning Forecasts a Strained Turbulent Flow Velocity Field in Temporal Lagrangian Framework: Comparison of LSTM and GRU
The subject of this study presents an employed method in deep learning to create a model and predict the following period of turbulent flow velocity. The applied data in this study are extracted datasets from simulated turbulent flow in the laboratory with the Taylor microscale Reynolds numbers in t...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-11-01
|
| Series: | Fluids |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2311-5521/7/11/344 |
| _version_ | 1797468318994530304 |
|---|---|
| author | Reza Hassanian Ásdís Helgadóttir Morris Riedel |
| author_facet | Reza Hassanian Ásdís Helgadóttir Morris Riedel |
| author_sort | Reza Hassanian |
| collection | DOAJ |
| description | The subject of this study presents an employed method in deep learning to create a model and predict the following period of turbulent flow velocity. The applied data in this study are extracted datasets from simulated turbulent flow in the laboratory with the Taylor microscale Reynolds numbers in the range of 90 < <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><msub><mi>R</mi><mi>λ</mi></msub></mrow></semantics></math></inline-formula>< 110. The flow has been seeded with tracer particles. The turbulent intensity of the flow is created and controlled by eight impellers placed in a turbulence facility. The flow deformation has been conducted via two circular flat plates moving toward each other in the center of the tank. The Lagrangian particle-tracking method has been applied to measure the flow features. The data have been processed to extract the flow properties. Since the dataset is sequential, it is used to train long short-term memory and gated recurrent unit model. The parallel computing machine DEEP-DAM module from Juelich supercomputer center has been applied to accelerate the model. The predicted output was assessed and validated by the rest of the data from the experiment for the following period. The results from this approach display accurate prediction outcomes that could be developed further for more extensive data documentation and used to assist in similar applications. The mean average error and R<sup>2</sup> score range from 0.001–0.002 and 0.9839–0.9873, respectively, for both models with two distinct training data ratios. Using GPUs increases the LSTM performance speed more than applications with no GPUs. |
| first_indexed | 2024-03-09T19:05:45Z |
| format | Article |
| id | doaj.art-b45adddb291f448cb1d2b244c934c42f |
| institution | Directory Open Access Journal |
| issn | 2311-5521 |
| language | English |
| last_indexed | 2024-03-09T19:05:45Z |
| publishDate | 2022-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Fluids |
| spelling | doaj.art-b45adddb291f448cb1d2b244c934c42f2023-11-24T04:38:39ZengMDPI AGFluids2311-55212022-11-0171134410.3390/fluids7110344Deep Learning Forecasts a Strained Turbulent Flow Velocity Field in Temporal Lagrangian Framework: Comparison of LSTM and GRUReza Hassanian0Ásdís Helgadóttir1Morris Riedel2The Faculty of Industrial Engineering, Mechanical Engineering and Computer Science, University of Iceland, 102 Reykjavík, IcelandThe Faculty of Industrial Engineering, Mechanical Engineering and Computer Science, University of Iceland, 102 Reykjavík, IcelandThe Faculty of Industrial Engineering, Mechanical Engineering and Computer Science, University of Iceland, 102 Reykjavík, IcelandThe subject of this study presents an employed method in deep learning to create a model and predict the following period of turbulent flow velocity. The applied data in this study are extracted datasets from simulated turbulent flow in the laboratory with the Taylor microscale Reynolds numbers in the range of 90 < <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><msub><mi>R</mi><mi>λ</mi></msub></mrow></semantics></math></inline-formula>< 110. The flow has been seeded with tracer particles. The turbulent intensity of the flow is created and controlled by eight impellers placed in a turbulence facility. The flow deformation has been conducted via two circular flat plates moving toward each other in the center of the tank. The Lagrangian particle-tracking method has been applied to measure the flow features. The data have been processed to extract the flow properties. Since the dataset is sequential, it is used to train long short-term memory and gated recurrent unit model. The parallel computing machine DEEP-DAM module from Juelich supercomputer center has been applied to accelerate the model. The predicted output was assessed and validated by the rest of the data from the experiment for the following period. The results from this approach display accurate prediction outcomes that could be developed further for more extensive data documentation and used to assist in similar applications. The mean average error and R<sup>2</sup> score range from 0.001–0.002 and 0.9839–0.9873, respectively, for both models with two distinct training data ratios. Using GPUs increases the LSTM performance speed more than applications with no GPUs.https://www.mdpi.com/2311-5521/7/11/344turbulent flowLagrangian frameworkunsteadypredictiondeep learningsequential |
| spellingShingle | Reza Hassanian Ásdís Helgadóttir Morris Riedel Deep Learning Forecasts a Strained Turbulent Flow Velocity Field in Temporal Lagrangian Framework: Comparison of LSTM and GRU Fluids turbulent flow Lagrangian framework unsteady prediction deep learning sequential |
| title | Deep Learning Forecasts a Strained Turbulent Flow Velocity Field in Temporal Lagrangian Framework: Comparison of LSTM and GRU |
| title_full | Deep Learning Forecasts a Strained Turbulent Flow Velocity Field in Temporal Lagrangian Framework: Comparison of LSTM and GRU |
| title_fullStr | Deep Learning Forecasts a Strained Turbulent Flow Velocity Field in Temporal Lagrangian Framework: Comparison of LSTM and GRU |
| title_full_unstemmed | Deep Learning Forecasts a Strained Turbulent Flow Velocity Field in Temporal Lagrangian Framework: Comparison of LSTM and GRU |
| title_short | Deep Learning Forecasts a Strained Turbulent Flow Velocity Field in Temporal Lagrangian Framework: Comparison of LSTM and GRU |
| title_sort | deep learning forecasts a strained turbulent flow velocity field in temporal lagrangian framework comparison of lstm and gru |
| topic | turbulent flow Lagrangian framework unsteady prediction deep learning sequential |
| url | https://www.mdpi.com/2311-5521/7/11/344 |
| work_keys_str_mv | AT rezahassanian deeplearningforecastsastrainedturbulentflowvelocityfieldintemporallagrangianframeworkcomparisonoflstmandgru AT asdishelgadottir deeplearningforecastsastrainedturbulentflowvelocityfieldintemporallagrangianframeworkcomparisonoflstmandgru AT morrisriedel deeplearningforecastsastrainedturbulentflowvelocityfieldintemporallagrangianframeworkcomparisonoflstmandgru |