Combining flamelet-generated manifold and machine learning models in simulation of a non-premixed diffusion flame

Aug 4, 2026

Upload by Logic

Flamelet Generated Manifold (FGM) is widely used for accurate, fast prediction of combustion characteristics, yet its application is limited by the large memory footprint of tabulated chemistry data. This work replaces stored tabulated sources and transport properties using machine learning models, focusing on the progress variable source term because of its strong gradients and broad variation across the control-variable space. Four ML approaches—two ANN variants, Random Forest, and Gradient Boosted Trees—are trained, validated, and compared. Ensemble RF/GBT models deliver high training efficiency with acceptable accuracy, while ANN models achieve lower training errors with longer training. The ML-FGM models are then coupled to a one-dimensional combustion code and evaluated against detailed chemistry and the original FGM model for key combustion properties and species profiles.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages17

Reading Time43 min

AccessFree to download

Highlights

Model development and evaluation

Abstract

Introduction

Motivation: detailed kinetics complexity

Combining flamelet-generated manifold and machine learning models in simulation of a non-premixed diffusion flame Citation for published version (APA): Li, K. , Rahnama, P. , Novella, R. , & Somers, B. (2023) . Combining flamelet-generated manifold and machine learning models in simulation of a non-premixed diffusion flame. Energy and AI, 14, Article 100266. [https://doi.org/10.1016/j.egyai.2023.100266](https://doi.org/10.1016/j.egyai.2023.100266) Document license: CC BY DOI: 10.1016/j.egyai.2023.100266 Document status and date: Published: 01/10/2023 Document Version: Publisher’s PDF, also known as Version of Record (includes final page, issue and volume numbers) Please check the document version of this publication: • A submitted manuscript is the version of the article upon submission and before peer-review. There can be important differences between the submitted version and the official published version of record. People interested in the research are advised to contact the author for the final version of the publication, or visit the DOI to the publisher's website. • The final author version and the galley proof are versions of the publication after peer review. • The final published version features the final layout of the paper including the volume, issue and page numbers. Link to publication General rights Copyright and moral rights for the publications made accessible in the public portal are retained by the authors and/or other copyright owners and it is a condition of accessing publications that users recognise and abide by the legal requirements associated with these rights. • Users may download and print one copy of any publication from the public portal for the purpose of private study or research. • You may not further distribute the material or use it for any profit-making activity or commercial gain • You may freely distribute the URL identifying the publication in the public portal. If the publication is distributed under the terms of Article 25fa of the Dutch Copyright Act, indicated by the “Taverne” license above, please follow below link for the End User Agreement: [www.tue.nl/taverne](www.tue.nl/taverne) Take down policy If you believe that this document breaches copyright please contact us at: [openaccess@tue.nl](openaccess@tue.nl) providing details and we will investigate your claim. Download date: 03. Aug. 2026 Energy and AI 14 (2023) 100266 Contents lists available at ScienceDirect Energy and AI journal [homepage: www.sciencedirect.com/journal/energy-and-ai](homepage: www.sciencedirect.com/journal/energy-and-ai) | Combining flamelet-generated manifold and machine learning models in simulation of a non-premixed diffusion flame
Kaimeng Lia, Pourya Rahnamaa, b, *, Ricardo Novellab, Bart Somersa
a Power & Flow – Department of Mechanical Engineering. Technical University of Eindhoven. P.O. Box 513, 5600 MB Eindhoven, The Netherlands b CMT – Motores T´ermicos. Universidad Polit´ecnica de Valencia. Camino de Vera s/n, E-46022 Valencia, Spain | | | | --- | --- | --- | | H I G H L I G H T S
• The performance of a hybrid FGM/Machine learning combustion model was studied.
• The model was implemented for an ndodecane counterflow diffusion flame.
• The performance of four different machine learning models was investigated.
• A data preprocessing method for improving the PV source prediction was suggested.
A R T I C L E I N F O
Keywords:
Flamelet models
Tabulated chemistry models Computational fluid dynamics Machine learning
Non-premixed diffusion flame | G R A P H I C A L A B S T R A C T
A B S T R A C T
Flamelet Generated Manifold (FGM) is an example of a chemistry tabulation or a flamelet method that is under attention because of its accuracy and speed in predicting combustion characteristics. However, the main problem in applying the model is a large amount of memory required. One way to solve this problem i

FAQs

What problem does Flamelet Generated Manifold (FGM) face in practice?

Applying FGM can require a large amount of memory because it relies on stored tabulated chemistry data.

Which machine learning methods are trained and compared in the study?

The study trains and compares two Artificial Neural Network (ANN) models, Random Forest (RF), and Gradient Boosted Trees (GBT).

How are the ML-FGM models assessed for combustion performance?

The ML-FGM models are coupled with a one-dimensional combustion code to simulate a counterflow non-premixed diffusion flame, and predictions are compared with detailed chemical simulations and the original FGM model for key properties and representative species profiles.

Aug 4, 2026

Upload by Logic