The American Society for Testing and Materials (ASTM) is an independent organization devoted to the development of standards.

American Society for Testing and Materials

Combustion machine learning: Principles, progress and prospects

Combustion science is an interdisciplinary study that involves nonlinear physical and chemical phenomena in time and length scales, including complex chemical reactions and fluid flows. Combustion widely supplies energy for powering vehicles, heating houses, generating electricity, cooking food, etc. The key to studying combustion is to improve the combustion efficiency with minimum emission of pollutants. Machine learning facilitates data-driven techniques for handling large amounts of combustion data, either through experiments or simulations under multiple spatiotemporal scales, thereby finding the hidden patterns underlying these data and promoting combustion research. This work presents an overview of studies on the applications of machine learning in combustion science fields over the past several decades. We introduce the fundamentals of machine learning and its usage in aiding chemical reactions, combustion modeling, combustion measurement, engine performance prediction and optimization, and fuel design. The opportunities and limitations of using machine learning in combustion studies are also discussed. This paper aims to provide readers with a portrait of what and how machine learning can be used in combustion research and to inspire researchers in their ongoing studies. Machine learning techniques are rapidly advancing in this era of big data, and there is high potential for exploring the combination between machine learning and combustion research and achieving remarkable results.

Machine learning for combustion

A quasi-DNS of the partially premixed turbulent Sydney flame in configuration FJ200-5GP-Lr75-57 has been conducted using detailed molecular diffusion for multi-component mixtures and complex reaction mechanisms. In order to study flame dynamics like regime transition in this flame for the development of new combustion models and to directly compare the quasi-DNS to different LES models, the simulation results are compiled into a data base. Because the simulation was performed with OpenFOAM, we demonstrate the quasi-DNS capabilities of OpenFOAM by performing canonical test cases. They attest that OpenFOAM’s cubic discretization has lower numerical diffusion compared to classical central difference schemes and can reach higher than second order convergence rate in some cases. The quasi-DNS of the Sydney flame is conducted with a self-developed reacting flow solver which is able to accurately compute molecular diffusion coefficients from kinetic gas theory and employs a fast implementation for detailed reaction mechanisms. The computational mesh is shown to be able to resolve the flow as well as the flame front sufficiently for the quasi-DNS. Comparisons with experimental data also show that the simulation can quantitatively reproduce measured time-mean and time-RMS statistics.

/pdf/quasi-dns-dataset-of-a-piloted-flame-with-inhomogeneous-jql4s9hj2j.pdf

Quasi-DNS Dataset of a Piloted Flame with Inhomogeneous Inlet Conditions

Numerical simulations have played a vital role in the design of modern combustion systems. Over the last two decades, the focus of research has been on the development of the large eddy simulation (LES) approach, which leveraged the vast increase in computing power to dramatically improve predictive accuracy. Even with the anticipated increase in supercomputing capabilities, the use of LES in design is limited by its high computational cost. Moreover, to aid decision making, such LES computations have to be augmented to estimate underlying uncertainties in simulation components. At the same time, other changes are happening across industries that build or use combustion devices. While efficiency and emissions reduction are still the primary design objectives, reducing cost of operation by optimizing maintenance and repair is becoming an important segment of the enterprise. This latter quest is aided by the digitization of combustors, which allows collection and storage of operational data from a host of sensors over a fleet of devices. Moreover, several levels of computing including low-power hardware present on board the combustion systems are becoming available. Such large data sets create unique opportunities for design and maintenance if appropriate numerical tools are made available. As LES revolutionized computing-guided design by leveraging supercomputing, a new generation of numerical approaches is needed to utilize this vast amount of data and the varied nature of computing hardware. In this article, a review of emerging computational approaches for this heterogeneous data-driven environment is provided. A case is made that new but unconventional opportunities for physics-based combustion modeling exist in this realm.

Emerging trends in numerical simulations of combustion systems

A revised flamelet/progress variable (FPV) model in which two mixture fractions are defined has been developed to address the limitations of single mixture fraction FPV models that presume a single, compositionally uniform fuel stream. The revised model is applied in Large Eddy Simulation of the modified University of Sydney turbulent jet burner with compositionally inhomogeneous inlet conditions. The first mixture fraction (Z) characterizes the mixing between the methane/air mixture issuing from the burner and the surrounding coflow air. The second mixture fraction (Z*) tracks mixing of methane and air without regard to the point of origin of the air. Additionally, a fuel premixing fraction (F) has been defined that corresponds to the fuel side boundary condition for the solution of the 1D flamelet equations in terms of the first mixture fraction. Two methods of characterizing the thermochemical state are considered, one using Z and Z* and the other using Z and F. Comparison of temperature and species predictions with experimental data shows that the structure of the flame with inhomogeneous inlets cannot be predicted by a single mixture fraction model while this is successfully achieved with the two mixture fraction models. Even for a near-homogeneous inlet with only minor variations in composition, the two mixture fraction model predictions provide significant improvements over a single mixture fraction model.

/pdf/a-two-mixture-fraction-flamelet-model-for-large-eddy-4minfe8zg1.pdf

A two mixture fraction flamelet model for large eddy simulation of turbulent flames with inhomogeneous inlets

/pdf/a-two-mixture-fraction-flamelet-model-for-large-eddy-3fhlz6m98r.pdf

A Two Mixture Fraction Flamelet Model for Large Eddy Simulation of Turbulent Jet Flames with Inhomogeneous Inlets

Adaptive mesh based combustion simulations of direct fuel injection effects in a supersonic cavity flame-holder

To apply reduced-order manifold combustion models in Large Eddy Simulations (LES) of systems with multiple inlets, it is necessary to incorporate more than one mixture fraction. As a result, the joint subfilter Probability Density Function (PDF) of the mixture fractions must be modeled. To determine the sensitivity of the predicted turbulent flame structure to these models, LES calculations of the Sydney piloted jet burner with inhomogeneous inlets have been performed using the Dirichlet, Connor-Mosimann (CM), and Beta-Delta (BD) distributions. A memory-efficient convolution-on-the-fly approach was applied to enable use of more complex subfilter PDF models, such as the CM distribution. Strong sensitivities in the LES predictions were observed to the choice of subfilter PDF model. The Dirichlet distribution was found to be ill-suited to this partially premixed turbulent flame because as a subfilter PDF model it implicitly assumes symmetric mixing in mixture fraction space, which is inconsistent with partial premixing. Good agreement with the experimental data was obtained using both the CM and BD distributions, which are mathematically consistent with partial premixing. The CM distribution is the most general of the considered distributions and gives the best predictions, but this comes with increased complexity and computational cost.

Effect of multiscalar subfilter PDF models in LES of turbulent flames with inhomogeneous inlets

A deep neural network (DNN) based large eddy simulation (LES) model for progress variable dissipation rate in turbulent premixed flames is presented. The DNN model is trained using filtered data from direct numerical simulations (DNS) of statistically planar turbulent premixed flames with n-heptane as fuel. Training data was comprised of flames with varying turbulence levels leading to a range of Karlovitz numbers. Through a-priori tests the DNN model is shown to predict the subfilter contribution to progress variable dissipation rate accurately over a range of filter widths and for all Karlovitz numbers examined in this study. Superior performance of the DNN model relative to an established physics-based model is also demonstrated. Additionally, transferability of the DNN model is highlighted by a-priori evaluation of the model using filtered DNS data from multiple cases with different Karlovitz numbers and fuel species than those that were used for training the model.

Deep learning-based model for progress variable dissipation rate in turbulent premixed flames

Handle everyday research tasks with reliable, citation-backed results

Your personal Research Agent to handle research tasks with citation-backed results

Popular Tasks used by Researchers

How can I help with your research?

Meet SciSpace

Get more enhanced response by uploading the PDFs you want me to reference.

No relevant PDFs in your library

SciSpace is the AI research assistant for academics. Run systematic literature reviews on 280M+ papers, and write papers with cited sources. Trusted by 1M+ students, PhDs & researchers.

SciSpace | AI for Research

Analyze PDFs

Code & Manuscripts

Funding & Grants

Literature & Patents

Medical & Clinical Data

Systematic Review

Visualize & Present

Web & Data

Build a Google Scholar-like website for your research.

Build a website

Create charts and images for your research

Create a Chart

Write a paper for submission to a journal

Draft a manuscript

Patent Search

Design eye-catching scientific posters in minutes.

Scientific Poster Generation

Systematic Literature Review

One task is running at the moment. Your messages will be shown right after.

Drag and drop or click here to browse

Loved by <highlight>1 million+</highlight> researchers

Extract a list of specific topics and their sources from unstructured text

Topics

Compare and analyze relevant papers that matches with your search

Papers

Get insights from PDFs and bookmarked papers from your library

My library

Recent searches

Try searching for:

Catch AI-generated content in scholarly and non-scholarly content

{ai} Detector

Ai Writer

Get PDF Summaries, highlighted text explanations 

Chat with PDF

Effortlessly create in-text citations and bibliographies in APA and 2,500 other formats

Citation generator

Get explanations, summaries, and answers on academic papers

Ease up your research workflow with {scispace}'s cohort of exciting AI tools

Elevate your academic writing skills and convey your ideas the way you want

Paraphraser

Explore our range of reading and writing tools

Your file is being prepared and should be ready in a few minutes. If it's a large file, it might take a bit longer. You can close this window, and we'll email you the file when it's done.

You have reached a maximum limit of <strong>{limit}</strong> columns in the table. Remove at least <strong>1</strong> column to add or create another one.

Bruce A. Perry

Author Tools

Chat about Author