Machine Learning of Combustion LES Models from Reacting Direct Numerical Simulation

Yellapantula, Shashank; Frahan, Marc Henry de; King, Ruth; Day, Marc; Grout, Ray

doi:10.1007/978-3-030-44718-2_14

Cited by 6 publications

(7 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…2020; Yellapantula et al. 2020; Abbate, Conlin & Kolemen 2021; Bai & Peng 2021; Hatfield et al. 2021; Maschler & Weyrich 2021; Brunton & Kutz 2022).…”

Section: Background and Previous Workmentioning

confidence: 99%

“…However, even with high-performance computing techniques, it is a challenge for real-time demand response in feedback control. Emerging data-driven methods have revolutionised how researchers model, predict and eventually control these complex systems in a diverse range of fields, including but not limited to automation, climate, combustion, fluids, high-energy physics, plasma science and plasmonics (Malkiel et al 2018;Duraisamy, Iaccarino & Xiao 2019;Wilkes et al 2020;Yellapantula et al 2020;Abbate, Conlin & Kolemen 2021;Bai & Peng 2021;Hatfield et al 2021;Maschler & Weyrich 2021;Brunton & Kutz 2022). A variety of ML techniques have been used such as deep neural networks (DNNs) to fit simulation data.…”

Section: Using ML To Accelerate Computationsmentioning

confidence: 99%

See 1 more Smart Citation

Towards fast and accurate predictions of radio frequency power deposition and current profile via data-driven modelling: applications to lower hybrid current drive

et al. 2022

View full text Add to dashboard Cite

Three machine learning techniques (multilayer perceptron, random forest and Gaussian process) provide fast surrogate models for lower hybrid current drive (LHCD) simulations. A single GENRAY/CQL3D simulation without radial diffusion of fast electrons requires several minutes of wall-clock time to complete, which is acceptable for many purposes, but too slow for integrated modelling and real-time control applications. The machine learning models use a database of more than 16 000 GENRAY/CQL3D simulations for training, validation and testing. Latin hypercube sampling methods ensure that the database covers the range of nine input parameters ( $n_{e0}$ , $T_{e0}$ , $I_p$ , $B_t$ , $R_0$ , $n_{\|}$ , $Z_{{\rm eff}}$ , $V_{{\rm loop}}$ and $P_{{\rm LHCD}}$ ) with sufficient density in all regions of parameter space. The surrogate models reduce the inference time from minutes to $\sim$ ms with high accuracy across the input parameter space.

show abstract

“…2020; Yellapantula et al. 2020; Abbate, Conlin & Kolemen 2021; Bai & Peng 2021; Hatfield et al. 2021; Maschler & Weyrich 2021; Brunton & Kutz 2022).…”

Section: Background and Previous Workmentioning

confidence: 99%

Section: Using ML To Accelerate Computationsmentioning

confidence: 99%

Towards fast and accurate predictions of radio frequency power deposition and current profile via data-driven modelling: applications to lower hybrid current drive

et al. 2022

View full text Add to dashboard Cite

show abstract

“…[43] uses convolutional neural networks on the full field of the resolved progress variable to construct subgrid flame density function estimates; and Ref. [44] uses neural networks to learn the filtered progress variable source term.…”

Section: A Closure Term and Model Inadequacy Representationsmentioning

confidence: 99%

Perspectives on Machine Learning-augmented Reynolds-averaged and Large Eddy Simulation Models of Turbulence

Duraisamy

2020

Preprint

View full text Add to dashboard Cite

This work presents a review and perspectives on recent developments in the use of machine learning (ML) to augment Reynolds-averaged Navier-Stokes (RANS) and Large Eddy Simulation (LES) models of turbulent flows. Different approaches of applying supervised learning to represent unclosed terms, model discrepancies and sub-filter scales are discussed in the context of RANS and LES modeling. Particular emphasis is placed on the impact of the training procedure on the consistency of ML augmentations with the underlying physical model. Techniques to promote model-consistent training, and to avoid the requirement of full fields of direct numerical simulation data are detailed. This is followed by a discussion of physics-informed and mathematical considerations on the choice of the feature space, and imposition of constraints on the ML model. With a view towards developing generalizable ML-augmented RANS and LES models, outstanding challenges are discussed, and perspectives are provided. While the promise of ML-augmented turbulence modeling is clear, and successes have been demonstrated in isolated scenarios, a general consensus of this paper is that truly generalizable models require model-consistent training with careful characterization of underlying assumptions and imposition of physically and mathematically informed priors and constraints to account for the inevitable shortage of data relevant to predictions of interest. This endeavor requires multi-disciplinary advances, and thus the target audience for this paper is the fluid mechanics community, as well as the computational science and machine learning communities.

show abstract

“…Many researchers in the literature have used machine learning (ML) techniques for various aspects of engine research such as simulation, 19 modeling, [20][21][22][23][24][25] optimization, [26][27][28][29][30][31][32] and control. [33][34][35][36][37][38] Traditional reinforcement learn-ing (RL) has been used for hard-coal combustion processes in a power plant, 39,40 for spark ignition and injection timing, 41,42 for energy management strategies for hybrid-electric vehicles, [43][44][45] and for the control of the air-fuel ratio 46 and spark engine exhaust gas recirculation (EGR) operation.…”

Section: Introductionmentioning

confidence: 99%

Deep reinforcement learning to discover multi-fuel injection strategies for compression ignition engines

Wimer

Frahan

Yellapantula

2023

International Journal of Engine Research

Self Cite

View full text Add to dashboard Cite

Over the past several decades, regulation of compression ignition engine emissions has become increasingly stringent as concern about the environmental and health implications of these emissions has grown. These changing constraints have led to a series of new, alternative fuel injection strategies that aim to maintain power output while reducing in-cylinder generated emissions by operating in the low-temperature combustion (LTC) regime. These advanced injection strategies are created and retuned for individual combinations of engine geometry, fuel, and emissions constraints. Deep reinforcement learning has been shown to be an effective alternative to traditional optimization approaches for highly combinatorial control problems, such as discovering the optimal injection schedules for compression ignition engines. In this study, we deploy a previously presented deep reinforcement learning framework to iteratively optimize a series of engine geometries over a range of increasingly strict NO x emissions regulations. We then examine the resulting injection schedules. We discuss the potential for using this deep reinforcement learning framework for fuel selection screening and for discovering unique injection strategies for different engine geometries and future emissions standards.

show abstract

Machine Learning of Combustion LES Models from Reacting Direct Numerical Simulation

Cited by 6 publications

References 35 publications

Towards fast and accurate predictions of radio frequency power deposition and current profile via data-driven modelling: applications to lower hybrid current drive

Towards fast and accurate predictions of radio frequency power deposition and current profile via data-driven modelling: applications to lower hybrid current drive

Perspectives on Machine Learning-augmented Reynolds-averaged and Large Eddy Simulation Models of Turbulence

Deep reinforcement learning to discover multi-fuel injection strategies for compression ignition engines

Contact Info

Product

Resources

About