Deep learning of nonlinear flame fronts development due to Darrieus–Landau instability
The Darrieus–Landau instability is studied using a data-driven, deep neural network approach. The task is set up to learn a time-advancement operator mapping any given flame front to a future time. A recurrent application of such an operator rolls out a long sequence of predicted flame fronts, and a...
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
AIP Publishing LLC
2023-06-01
|
| Series: | APL Machine Learning |
| Online Access: | http://dx.doi.org/10.1063/5.0139857 |
| _version_ | 1797635535549759488 |
|---|---|
| author | Rixin Yu |
| author_facet | Rixin Yu |
| author_sort | Rixin Yu |
| collection | DOAJ |
| description | The Darrieus–Landau instability is studied using a data-driven, deep neural network approach. The task is set up to learn a time-advancement operator mapping any given flame front to a future time. A recurrent application of such an operator rolls out a long sequence of predicted flame fronts, and a learned operator is required to not only make accurate short-term predictions but also reproduce characteristic nonlinear behavior, such as fractal front structures and detached flame pockets. Using two datasets of flame front solutions obtained from a heavy-duty direct numerical simulation and a light-duty modeling equation, we compare the performance of three state-of-art operator-regression network methods: convolutional neural networks, Fourier neural operator (FNO), and deep operator network. We show that, for learning complicated front evolution, FNO gives the best recurrent predictions in both the short and long term. A consistent extension allowing the operator-regression networks to handle complicated flame front shape is achieved by representing the latter as an implicit curve. |
| first_indexed | 2024-03-11T12:23:10Z |
| format | Article |
| id | doaj.art-de4d20238e11407aa7773f4b6f9a6cbe |
| institution | Directory Open Access Journal |
| issn | 2770-9019 |
| language | English |
| last_indexed | 2024-03-11T12:23:10Z |
| publishDate | 2023-06-01 |
| publisher | AIP Publishing LLC |
| record_format | Article |
| series | APL Machine Learning |
| spelling | doaj.art-de4d20238e11407aa7773f4b6f9a6cbe2023-11-06T21:03:50ZengAIP Publishing LLCAPL Machine Learning2770-90192023-06-0112026106026106-1810.1063/5.0139857Deep learning of nonlinear flame fronts development due to Darrieus–Landau instabilityRixin Yu0Department of Energy Sciences, Lund University, 22100 Lund, SwedenThe Darrieus–Landau instability is studied using a data-driven, deep neural network approach. The task is set up to learn a time-advancement operator mapping any given flame front to a future time. A recurrent application of such an operator rolls out a long sequence of predicted flame fronts, and a learned operator is required to not only make accurate short-term predictions but also reproduce characteristic nonlinear behavior, such as fractal front structures and detached flame pockets. Using two datasets of flame front solutions obtained from a heavy-duty direct numerical simulation and a light-duty modeling equation, we compare the performance of three state-of-art operator-regression network methods: convolutional neural networks, Fourier neural operator (FNO), and deep operator network. We show that, for learning complicated front evolution, FNO gives the best recurrent predictions in both the short and long term. A consistent extension allowing the operator-regression networks to handle complicated flame front shape is achieved by representing the latter as an implicit curve.http://dx.doi.org/10.1063/5.0139857 |
| spellingShingle | Rixin Yu Deep learning of nonlinear flame fronts development due to Darrieus–Landau instability APL Machine Learning |
| title | Deep learning of nonlinear flame fronts development due to Darrieus–Landau instability |
| title_full | Deep learning of nonlinear flame fronts development due to Darrieus–Landau instability |
| title_fullStr | Deep learning of nonlinear flame fronts development due to Darrieus–Landau instability |
| title_full_unstemmed | Deep learning of nonlinear flame fronts development due to Darrieus–Landau instability |
| title_short | Deep learning of nonlinear flame fronts development due to Darrieus–Landau instability |
| title_sort | deep learning of nonlinear flame fronts development due to darrieus landau instability |
| url | http://dx.doi.org/10.1063/5.0139857 |
| work_keys_str_mv | AT rixinyu deeplearningofnonlinearflamefrontsdevelopmentduetodarrieuslandauinstability |