\textit{DeepFlame}: a deep learning empowered open-source platform for reacting flow simulations
From MaRDI portal
Publication:6167670
Abstract: In this work, we introduce DeepFlame, an open-source C++ platform with the capabilities of utilising machine learning algorithms and pre-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. Combust. Flame vol. 245 pp. 112319, 2022) 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.
Recommendations
- Deep-learning accelerated calculation of real-fluid properties in numerical simulation of complex flowfields
- reactingfoam-SCI: an open source CFD platform for reacting flow simulation
- Direct numerical simulations of reacting flows with detailed chemistry using many-core/GPU acceleration
- Online \textit{in situ} prediction of 3-D flame evolution from its history 2-D projections via deep learning
- PoKiTT: exposing task and data parallelism on heterogeneous architectures for detailed chemical kinetics, transport, and thermodynamics calculations
Cites work
- A detailed verification procedure for compressible reactive multicomponent Navier-Stokes solvers
- Determination of ignition delay times of different hydrocarbons in a new high pressure shock tube
- scientific article; zbMATH DE number 3251902 (Why is no real title available?)
- On the Construction and Comparison of Difference Schemes
- reactingfoam-SCI: an open source CFD platform for reacting flow simulation
- SUNDIALS
- Transport Properties of Multicomponent Gas Mixtures
- Turbulent Combustion
Cited in
(6)- Application of machine learning in low-order manifold representation of chemistry in turbulent flames
- Stochastic operator learning for chemistry in non-equilibrium flows
- \textit{DeepFlame} 2.0: a new version for fully GPU-native machine learning accelerated reacting flow simulations under low-Mach conditions
- An OpenFOAM solver incorporating detailed transport model for reacting flow simulations
- XFluids: a unified cross-architecture high performance heterogeneous reacting flows simulation solver
- COREFL: an open-source GPU-accelerated high-fidelity solver for compressible reactive flows on generalized curvilinear coordinates
This page was built for publication: \textit{DeepFlame}: a deep learning empowered open-source platform for reacting flow simulations
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6167670)
