DeepFlame: A deep learning empowered open-source platform for reacting flow simulations.
Saved in:
| Title: | DeepFlame: A deep learning empowered open-source platform for reacting flow simulations. |
|---|---|
| Authors: | Mao, Runze1,2 (AUTHOR), Lin, Minqi1 (AUTHOR), Zhang, Yan1,3,4 (AUTHOR) zhang_yan2@iapcm.ac.cn, Zhang, Tianhan2,5 (AUTHOR), Xu, Zhi-Qin John6,7 (AUTHOR), Chen, Zhi X.1,2 (AUTHOR) chenzhi@pku.edu.cn |
| Source: | Computer Physics Communications. Oct2023, Vol. 291, pN.PAG-N.PAG. 1p. |
| Subjects: | Deep learning, Flow simulations, Machine learning, Computational fluid dynamics, Reactive flow, High performance computing |
| Abstract: | Recent developments in deep learning have brought many inspirations for the scientific computing community and it is perceived as a promising method in accelerating the computationally demanding reacting flow simulations. In this work, we introduce DeepFlame , an open-source C++ platform with the capabilities of utilising machine learning algorithms and offline-trained models to solve for reactive flows. We combine the individual strengths of the computational fluid dynamics library OpenFOAM, machine learning framework Torch, and chemical kinetics program Cantera. The complexity of cross-library function and data interfacing (the core of DeepFlame) is minimised to achieve a simple and clear workflow for code maintenance, extension and upgrading. As a demonstration, we apply our recent work on deep learning for predicting chemical kinetics (Zhang et al., 2022 [8]) to highlight the potential of machine learning in accelerating reacting flow simulation. A thorough code validation is conducted via a broad range of canonical cases to assess its accuracy and efficiency. The results demonstrate that the convection-diffusion-reaction algorithms implemented in DeepFlame are robust and accurate for both steady-state and transient processes. In addition, a number of methods aiming to further improve the computational efficiency, e.g. dynamic load balancing and adaptive mesh refinement, are explored. Their performances are also evaluated and reported. With the deep learning method implemented in this work, a speed-up of two orders of magnitude is achieved in a simple hydrogen ignition case when performed on a medium-end graphics processing unit (GPU). Further gain in computational efficiency is expected for hydrocarbon and other complex fuels. A similar level of acceleration is obtained on an AI-specific chip – deep computing unit (DCU), highlighting the potential of DeepFlame in leveraging the next-generation computing architecture and hardware. Program Title: DeepFlame CPC Library link to program files: https://doi.org/10.17632/3pg9xmypp3.1 Developer's repository link: https://github.com/deepmodeling/deepflame-dev Licensing provisions: GPLv3 Programming language: C++ Nature of problem: Solving chemically reacting flows with direct (quasi-direct) simulation methods is usually troubled by the following problems: 1. as the widely-used computational fluid dynamics (CFD) toolbox, OpenFOAM features limited ODE solvers for chemistry and oversimplified transport models, yielding non-negligible errors in simulation results; 2. the chemical source term evaluation is the most computationally expensive and usually accounts for more than 80% of total computing time. Solution method: An open-source platform bringing together the individual strengths of OpenFOAM, Cantera and PyTorch libraries is built in this study. In the present implementation, CVODE solvers, detailed transport models and deep learning algorithms are all adopted to assist the simulation of reacting flow. Note that here machine learning is introduced in combination with heterogeneous computing to accelerate the most demanding solving procedure for chemical source term evaluation. [ABSTRACT FROM AUTHOR] |
| Copyright of Computer Physics Communications is the property of Elsevier B.V. and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
| FullText | Text: Availability: 0 |
|---|---|
| Header | DbId: egs DbLabel: Engineering Source An: 169751820 AccessLevel: 6 PubType: Periodical PubTypeId: serialPeriodical PreciseRelevancyScore: 0 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: DeepFlame: A deep learning empowered open-source platform for reacting flow simulations. – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Mao%2C+Runze%22">Mao, Runze</searchLink><relatesTo>1,2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Lin%2C+Minqi%22">Lin, Minqi</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Zhang%2C+Yan%22">Zhang, Yan</searchLink><relatesTo>1,3,4</relatesTo> (AUTHOR)<i> zhang_yan2@iapcm.ac.cn</i><br /><searchLink fieldCode="AR" term="%22Zhang%2C+Tianhan%22">Zhang, Tianhan</searchLink><relatesTo>2,5</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Xu%2C+Zhi-Qin+John%22">Xu, Zhi-Qin John</searchLink><relatesTo>6,7</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Chen%2C+Zhi+X%2E%22">Chen, Zhi X.</searchLink><relatesTo>1,2</relatesTo> (AUTHOR)<i> chenzhi@pku.edu.cn</i> – Name: TitleSource Label: Source Group: Src Data: <searchLink fieldCode="JN" term="%22Computer+Physics+Communications%22">Computer Physics Communications</searchLink>. Oct2023, Vol. 291, pN.PAG-N.PAG. 1p. – Name: Subject Label: Subjects Group: Su Data: <searchLink fieldCode="DE" term="%22Deep+learning%22">Deep learning</searchLink><br /><searchLink fieldCode="DE" term="%22Flow+simulations%22">Flow simulations</searchLink><br /><searchLink fieldCode="DE" term="%22Machine+learning%22">Machine learning</searchLink><br /><searchLink fieldCode="DE" term="%22Computational+fluid+dynamics%22">Computational fluid dynamics</searchLink><br /><searchLink fieldCode="DE" term="%22Reactive+flow%22">Reactive flow</searchLink><br /><searchLink fieldCode="DE" term="%22High+performance+computing%22">High performance computing</searchLink> – Name: Abstract Label: Abstract Group: Ab Data: Recent developments in deep learning have brought many inspirations for the scientific computing community and it is perceived as a promising method in accelerating the computationally demanding reacting flow simulations. In this work, we introduce DeepFlame , an open-source C++ platform with the capabilities of utilising machine learning algorithms and offline-trained models to solve for reactive flows. We combine the individual strengths of the computational fluid dynamics library OpenFOAM, machine learning framework Torch, and chemical kinetics program Cantera. The complexity of cross-library function and data interfacing (the core of DeepFlame) is minimised to achieve a simple and clear workflow for code maintenance, extension and upgrading. As a demonstration, we apply our recent work on deep learning for predicting chemical kinetics (Zhang et al., 2022 [8]) to highlight the potential of machine learning in accelerating reacting flow simulation. A thorough code validation is conducted via a broad range of canonical cases to assess its accuracy and efficiency. The results demonstrate that the convection-diffusion-reaction algorithms implemented in DeepFlame are robust and accurate for both steady-state and transient processes. In addition, a number of methods aiming to further improve the computational efficiency, e.g. dynamic load balancing and adaptive mesh refinement, are explored. Their performances are also evaluated and reported. With the deep learning method implemented in this work, a speed-up of two orders of magnitude is achieved in a simple hydrogen ignition case when performed on a medium-end graphics processing unit (GPU). Further gain in computational efficiency is expected for hydrocarbon and other complex fuels. A similar level of acceleration is obtained on an AI-specific chip – deep computing unit (DCU), highlighting the potential of DeepFlame in leveraging the next-generation computing architecture and hardware. Program Title: DeepFlame CPC Library link to program files: https://doi.org/10.17632/3pg9xmypp3.1 Developer's repository link: https://github.com/deepmodeling/deepflame-dev Licensing provisions: GPLv3 Programming language: C++ Nature of problem: Solving chemically reacting flows with direct (quasi-direct) simulation methods is usually troubled by the following problems: 1. as the widely-used computational fluid dynamics (CFD) toolbox, OpenFOAM features limited ODE solvers for chemistry and oversimplified transport models, yielding non-negligible errors in simulation results; 2. the chemical source term evaluation is the most computationally expensive and usually accounts for more than 80% of total computing time. Solution method: An open-source platform bringing together the individual strengths of OpenFOAM, Cantera and PyTorch libraries is built in this study. In the present implementation, CVODE solvers, detailed transport models and deep learning algorithms are all adopted to assist the simulation of reacting flow. Note that here machine learning is introduced in combination with heterogeneous computing to accelerate the most demanding solving procedure for chemical source term evaluation. [ABSTRACT FROM AUTHOR] – Name: AbstractSuppliedCopyright Label: Group: Ab Data: <i>Copyright of Computer Physics Communications is the property of Elsevier B.V. and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.) |
| PLink | https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=169751820 |
| RecordInfo | BibRecord: BibEntity: Identifiers: – Type: doi Value: 10.1016/j.cpc.2023.108842 Languages: – Code: eng Text: English PhysicalDescription: Pagination: PageCount: 1 StartPage: N.PAG Subjects: – SubjectFull: Deep learning Type: general – SubjectFull: Flow simulations Type: general – SubjectFull: Machine learning Type: general – SubjectFull: Computational fluid dynamics Type: general – SubjectFull: Reactive flow Type: general – SubjectFull: High performance computing Type: general Titles: – TitleFull: DeepFlame: A deep learning empowered open-source platform for reacting flow simulations. Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Mao, Runze – PersonEntity: Name: NameFull: Lin, Minqi – PersonEntity: Name: NameFull: Zhang, Yan – PersonEntity: Name: NameFull: Zhang, Tianhan – PersonEntity: Name: NameFull: Xu, Zhi-Qin John – PersonEntity: Name: NameFull: Chen, Zhi X. IsPartOfRelationships: – BibEntity: Dates: – D: 01 M: 10 Text: Oct2023 Type: published Y: 2023 Identifiers: – Type: issn-print Value: 00104655 Numbering: – Type: volume Value: 291 Titles: – TitleFull: Computer Physics Communications Type: main |
| ResultId | 1 |
