All Issue

2026 Vol.31, Issue 3 Preview Page

Research Article

GPR-MOGA-Based Optimization of Combustor Operating Conditions for Enhancing Combustion Efficiency and Reducing NOx Emissions

연소효율 향상 및 NOx 배출 저감을 위한 GPR-MOGA 기반 연소기 운전 조건 최적화

Juwon Kim1
,
Deukgyun Lim1
,
Minha Hwang1
,
Jongkwang Lee1
,
Gil-Eon Jeong1
,
Minwoo W. Lee1†
김 주원1
,
임 득균1
,
황 민하1
,
이 종광1
,
정 길언1
,
이 민우1†
1Department of Mechanical Engineering, Hanbat National University
1국립한밭대학교 기계공학과
*Corresponding Author
30 September 2026. pp. 24-34
PDF XML Citation
Abstract

This study presents a computational fluid dynamics (CFD)-based surrogate optimization framework to determine the optimal operating conditions of a non-premixed bluff-body combustor. The inlet mass flow rates of fuel and oxidizer, along with the fuel inlet temperature, are selected as design variables, while the CH4 conversion-based combustion efficiency and NO emission index serve as performance metrics. To construct the surrogate model, a database generated via Latin hypercube sampling is utilized to train Gaussian process regression (GPR) models, which are subsequently validated using independent test cases. The trained GPR models demonstrate robust predictive performance, yielding high coefficients of determination for both metrics. By coupling the validated GPR models with a multi-objective genetic algorithm (MOGA), optimal operating conditions are identified to simultaneously maximize combustion efficiency and minimize NO emissions. CFD re-analysis of the optimized operating points confirms significant improvements in combustion efficiency and substantial reductions in the NO emission index compared to the initial trial results. These findings demonstrate that the GPR-MOGA optimization framework employed in this study can efficiently identify optimal operating conditions for enhancing combustion performance and reducing emissions in practical combustors.

Keywords
Combustion efficiency
NOx reduction
Gaussian process regression
Multi-objective genetic algorithm
References
1

Y. Liu, X. Sun, V. Sethi, D. Nalianda, Y.-G. Li, L. Wang, Review of modern low emissions combustion technologies for aero gas turbine engines, Prog. Aerosp. Sci. 94 (2017) 12-45.

10.1016/j.paerosci.2017.08.001
2

M. Lee, K.T. Kim, V. Gupta, L.K.B. Li, System identification and early warning detection of thermoacoustic oscillations in a turbulent combustor using its noise-induced dynamics, Proc. Combust. Inst. 38(4) (2021) 6025-6033.

10.1016/j.proci.2020.06.057
3

H. Son, M. Lee, A PINN approach for identifying governing parameters of noisy thermoacoustic systems, J. Fluid Mech. 984 (2024) A21.

10.1017/jfm.2024.219
4

M. Lee, Numerical aspects of noise-induced dynamics in continuous combustion systems, J. Korean Soc. Combust. 28(2) (2023) 66-77.

10.15231/jksc.2023.28.2.067
5

N.T. Davis, G.S. Samuelsen, Optimization of gas turbine combustor performance throughout the duty cycle, Proc. Combust. Inst. 26(2) (1996) 2819- 2825.

10.1016/S0082-0784(96)80121-4
6

E. Amani, P. Rahdan, S. Pourvosoughi, Multi- objective optimizations of air partitioning in a gas turbine combustor, Appl. Therm. Eng. 148 (2019) 1292-1302.

10.1016/j.applthermaleng.2018.12.015
7

Z. Saboohi, F. Ommi, M.J. Akbari, Multi-objective optimization approach toward conceptual design of gas turbine combustor, Appl. Therm. Eng. 148 (2019) 1210-1223.

10.1016/j.applthermaleng.2018.11.082
8

A. Abou-Taouk, I. Sigfrid, R. Whiddon, L.-E. Eriksson, A four-step global reaction mechanism for CFD simulations of flexi-fuel burner for gas turbines, in: Proceedings of the Seventh International Symposium on Turbulence, Heat and Mass Transfer, Palermo, Italy, 2012, pp. 785-788.

10.1615/ICHMT.2012.ProcSevIntSympTurbHeatTransfPal.660
9

R.F.D. Monaghan, R. Tahir, G. Bourque, R.L. Gordon, A. Cuoci, T. Faravelli, A. Frassoldati, H.J. Curran, Detailed emissions prediction for a turbulent swirling nonpremixed flame, Energy Fuels 28(2) (2014) 1470-1488.

10.1021/ef402057w
10

S. Koziel, L. Leifsson, Simulation-driven design using surrogate-based optimization and variable- resolution computational fluid dynamic models, J. Comput. Methods Sci. Eng. 12(1-2) (2012) 75-98.

10.3233/JCM-2012-0405
11

M. Yang, S. Kim, X. Sun, S. Kim, J. Choi, T.S. Park, J.-I. Choi, Deep-learning-based reduced-order modeling to optimize recuperative burner operating conditions, Appl. Therm. Eng. 236 (2024) 121669.

10.1016/j.applthermaleng.2023.121669
12

J.M. Reumschüssel, J.G.R. von Saldern, B. Ćosić, C.O. Paschereit, Data-driven optimization of a gas turbine combustor: A Bayesian approach addressing NOx emissions, lean extinction limits, and thermoacoustic stability, Data-Centric Eng. 5 (2024) e32.

10.1017/dce.2024.29
13

F. Bazdidi-Tehrani, A. Teymoori, Optimization of a gas turbine model combustor due to variations in geometrical characteristics of stabilizing air jets, Appl. Therm. Eng. 217 (2022) 119206.

10.1016/j.applthermaleng.2022.119206
14

Z. Tang, Z. Zhang, The multi-objective optimization of combustion system operations based on deep data-driven models, Energy 182 (2019) 37-47.

10.1016/j.energy.2019.06.051
15

P. Yang, X. Zhou, B. Zhang, H. Xu, Multi-objective optimization design of micro-mixed hydrogen combustor based on small sample agent model, Int. J. Hydrogen Energy 139 (2025) 257-267.

10.1016/j.ijhydene.2025.01.152
16

Y. Zhang, Z. Zhao, Y. Ma, M. Yang, Y. Tian, Multi-objective optimization of scramjet combustor ramp configuration using machine learning methods, Aerosp. Sci. Technol. 165 (2025) 110476.

10.1016/j.ast.2025.110476
17

A. Alfazazi, S. Kumar, O. Behar, B. Dally, Effects of ammonia substitution on the structure and emissions of non-premixed methane flames stabilized by a bluff-body burner, Int. J. Hydrogen Energy 170 (2025) 151314.

10.1016/j.ijhydene.2025.151314
18

A. Rowhani, Z.W. Sun, P.R. Medwell, Z.T. Alwahabi, G.J. Nathan, B.B. Dally, Effects of the bluff-body diameter on the flow-field characteristics of non- premixed turbulent highly-sooting flames, Combust. Sci. Technol. 194(2) (2022) 378-396.

10.1080/00102202.2019.1680508
19

L. Zhang, J. Zhu, Y. Yan, H. Guo, Z. Yang, Numerical investigation on the combustion characteristics of methane/air in a micro-combustor with a hollow hemispherical bluff body, Energy Convers. Manage. 94 (2015) 293-299.

10.1016/j.enconman.2015.01.014
20

A. Marrel, B. Iooss, Probabilistic surrogate modeling by Gaussian process: A review on recent insights in estimation and validation, Reliab. Eng. Syst. Saf. 247 (2024) 110094.

10.1016/j.ress.2024.110094
21

C.E. Rasmussen, C.K.I. Williams, Gaussian Processes for Machine Learning, MIT Press, Cambridge, MA, 2006, pp. 106-107.

10.7551/mitpress/3206.001.0001
22

T.O. Hodson, Root-mean-square error (RMSE) or mean absolute error (MAE): when to use them or not, Geosci. Model Dev. 15 (2022) 5481-5487.

10.5194/gmd-15-5481-2022
23

D. Chicco, M.J. Warrens, G. Jurman, The coefficient of determination R-squared is more informative than SMAPE, MAE, MAPE, MSE and RMSE in regression analysis evaluation, PeerJ Comput. Sci. 7 (2021) e623.

10.7717/peerj-cs.62334307865PMC8279135
24

K. Deb, A. Pratap, S. Agarwal, T. Meyarivan, A fast and elitist multiobjective genetic algorithm: NSGA- II, IEEE Trans. Evol. Comput. 6(2) (2002) 182-197.

10.1109/4235.996017
25

S. Guk, S. Seo, M. Lee, Thermoacoustic dynamics in an annular model gas-turbine combustor under transverse stochastic forcing, J. Korean Soc. Combust. 28(3) (2023) 20-27.

10.15231/jksc.2023.28.3.020
26

M. Lee, Coupling and synchronisation effects on local lock-in of two thermoacoustic oscillators in a stochastic environment, J. Fluid Mech. 1017 (2025) R2.

10.1017/jfm.2025.10489
27

S. Guk, S. Seo, M. Lee, An image-based spatiotemporal approach for detecting coherence resonance in annular model gas-turbine combustor, Phys. Fluids 36(5) (2024) 054121.

10.1063/5.0208950
28

E. Jung, S. Park, M. Lee, Propulsion performance analysis of a turbofan engine using the ammonia- blended fuel: low-order numerical simulation, J. Korean Soc. Combust. 29(4) (2024) 51-60.

10.15231/jksc.2024.29.4.051
29

S. Guk, J. Lee, J. Kim, M. Lee, Advances and challenges in thermoacoustic network modeling for hydrogen and ammonia combustors, Energies 18(2) (2025) 346.

10.3390/en18020346
Information
  • Publisher :The Korean Society of Combustion
  • Publisher(Ko) :한국연소학회
  • Journal Title :Journal of the Korean Society of Combustion
  • Journal Title(Ko) :한국연소학회지
  • Volume : 31
  • No :3
  • Pages :24-34
  • Received Date : 2026-07-28
  • Revised Date : 2026-08-18
  • Accepted Date : 2026-08-18
  • DOI :https://doi.org/10.15231/jksc.2026.31.3.024
Journal Informaiton Journal of the Korean Society of Combustion Journal of the Korean Society of Combustion
Online submission
  • ESCI_jkosco
  • NRF
  • KOFST
  • crossref cited-by
  • crosscheck
  • orcid
  • open access
  • ccl
Journal Informaiton Journal Informaiton - close