Co-optimized machine-learned manifold models for large eddy simulation of turbulent combustion

Perry, Barbara; Frahan, Marc Henry de; Yellapantula, Shashank

doi:10.1016/j.combustflame.2022.112286

Cited by 9 publications

(3 citation statements)

References 66 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This result can explain the improved ROM performance reported in the literature. 24 , 25 , 26 In Figure 3 A, we demonstrate this using three reacting flow datasets for the combustion of hydrogen, methane, and ethylene in air. We generate 2D and 3D projections of high-dimensional thermochemical state spaces.…”

Section: Resultsmentioning

confidence: 91%

“…This approach naturally penalizes projections that exhibit nonuniqueness or large gradients, since any difficulties in representing QoIs on a projection immediately increase the mean-squared-error (MSE) loss function during training. Evidence from the existing research 24 , 25 , 26 suggests that such a joint encoding-decoding 27 , 28 , 29 , 30 , 31 approach provides improvements to the topology of a low-dimensional data projection. Here, we demonstrate quantitatively that this is the case.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Improving reduced-order models through nonlinear decoding of projection-dependent outputs

Zdybał,

Parente,

Sutherland

2023

Patterns

View full text Add to dashboard Cite

Section: Resultsmentioning

confidence: 91%

Section: Introductionmentioning

confidence: 99%

Improving reduced-order models through nonlinear decoding of projection-dependent outputs

Zdybał,

Parente,

Sutherland

2023

Patterns

View full text Add to dashboard Cite

“…The neural network trained from such data set has been confirmed to be accurate and efficient in predicting reaction rates under various conditions. Besides, DNN was also extended to the high-dimensional tabulation of flamelets and effectively reduced the memory requirement [9][10][11][12].…”

Section: Introductionmentioning

confidence: 99%

DeepFlame: A deep learning empowered open-source platform for reacting flow simulations

Mao¹,

Lin²,

Zhang³

et al. 2022

Preprint

View full text Add to dashboard Cite

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 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.

show abstract

Reduced-Order Modeling of Reacting Flows Using Data-Driven Approaches

Zdybał

Malik

Coussement

et al. 2023

Lecture Notes in Energy

View full text Add to dashboard Cite

Data-driven modeling of complex dynamical systems is becoming increasingly popular across various domains of science and engineering. This is thanks to advances in numerical computing, which provides high fidelity data, and to algorithm development in data science and machine learning. Simulations of multicomponent reacting flows can particularly profit from data-based reduced-order modeling (ROM). The original system of coupled partial differential equations that describes a reacting flow is often large due to high number of chemical species involved. While the datasets from reacting flow simulation have high state-space dimensionality, they also exhibit attracting low-dimensional manifolds (LDMs). Data-driven approaches can be used to obtain and parameterize these LDMs. Evolving the reacting system using a smaller number of parameters can yield substantial model reduction and savings in computational cost. In this chapter, we review recent advances in ROM of turbulent reacting flows. We demonstrate the entire ROM workflow with a particular focus on obtaining the training datasets and data science and machine learning techniques such as dimensionality reduction and nonlinear regression. We present recent results from ROM-based simulations of experimentally measured Sandia flames D and F. We also delineate a few remaining challenges and possible future directions to address them. This chapter is accompanied by illustrative examples using the recently developed Python software, PCAfold. The software can be used to obtain, analyze and improve low-dimensional data representations. The examples provided herein can be helpful to students and researchers learning to apply dimensionality reduction, manifold approaches and nonlinear regression to their problems. The Jupyter notebook with the examples shown in this chapter can be found on GitHub at https://github.com/kamilazdybal/ROM-of-reacting-flows-Springer.

show abstract

Co-optimized machine-learned manifold models for large eddy simulation of turbulent combustion

Cited by 9 publications

References 66 publications

Improving reduced-order models through nonlinear decoding of projection-dependent outputs

Improving reduced-order models through nonlinear decoding of projection-dependent outputs

DeepFlame: A deep learning empowered open-source platform for reacting flow simulations

Reduced-Order Modeling of Reacting Flows Using Data-Driven Approaches

Contact Info

Product

Resources

About