Neural Network Closure Models for Estimating Flame Variables in a Liquid-Propellant Rocket Engine

Shadram, Zeinab; Nguyen, Tuan M.; Sideris, Athanasios; Sirignano, William A.

doi:10.2514/6.2019-2008

Cited by 3 publications

(3 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Similar to our previous work [10,24,23], we used CVRC experiment as our testbed. Both spontaneous and triggered instabilities in this single-injector coaxial dumped combustor have been analyzed in the past, see [27,28,29,31].…”

Section: Background On Combustion Instability Analysismentioning

confidence: 99%

“…developed NN-based models utilizing the data from the existing flamelet tables and validated their results by comparing CFD simulations based on the flamelet table and the ones based on NN representation of the flamelet model.A next and more complicated step in using NNs in combustion is to use available CFD data to train the NN-based models. Training a NN on CFD data has been suggested as future research in our previous work[23,24], where only offline tests were analyzed both with single output and multiple outputs NNs. The challenge here comes from the fact that in a CFD configuration, only a small portion (a manifold) of the flamelet space is used; thus, reconstructing the whole flamelet space may be accomplished by training NNs based on data from multiple simulations.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Physics-Aware Neural Network Flame Closure for Combustion Instability Modeling in a Single-Injector Engine

Shadram¹,

Nguyen²,

Sideris³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Neural networks (NN) are implemented as sub-grid flame models in a large-eddy simulation of a singleinjector liquid-propellant rocket engine. The NN training process presents an extraordinary challenge. The multi-dimensional combustion instability problem involves multi-scale lengths and characteristic times in an unsteady flow problem with nonlinear acoustics, addressing both transient and dynamic-equilibrium behaviors, superimposed on a turbulent reacting flow with very narrow, moving flame regions. Accurate interpolation between the points of the training data becomes vital. The NNs proposed here are trained based on data processed from a few CFD simulations of a single-injector liquid-propellant rocket engine with different dynamical configurations to reproduce the information stored in a flamelet table. The training set is also enriched by data from the physical characteristics and considerations of the combustion model. Flame temperature is used as an extra input for other flame variables to improve the NN-based model accuracy and physical consistency. The trained NNs are first tested offline on the flamelet table. These physicsaware NN-based closure models are successfully implemented into CFD simulations and verified by being tested on various dynamical configurations. The results from those tests compare favorably with counterpart table-based CFD simulations.

show abstract

Section: Background On Combustion Instability Analysismentioning

confidence: 99%

mentioning

confidence: 99%

Physics-Aware Neural Network Flame Closure for Combustion Instability Modeling in a Single-Injector Engine

Shadram¹,

Nguyen²,

Sideris³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…In the earlier stages of the work, the approach was to develop a model that calculates flame related variables from the CFD simulation, replacing the function described within the dashed line in the schematic in Fig. 1b, [27,28]. In this paper, however, the approach is to study the data inside the flamelet table directly and to develop NNs that focus only on the flamelet model outputs.…”

mentioning

confidence: 99%