Computational intelligence approach for NOx emissions  minimization in a 30 MW  premixed gas burner

Weibo Chen, Guixiong Liu


Artificial intelligence algorithms have become a research hotspot in attempts to reduce NOx emissions in gas burners through NOx emission modeling and optimizing operating parameters. This paper compres the predictive accuracy of NOx emission models based on LSSVM, SVR and ELM. CGA and three other GA based hybrid algorithms proposed to modify CGA were employed to optimize the operating parameters of a 30MW gas burner in order to reduce NOx emission. The results show that the NOx emission model built by LSSVM is more accurate than that of SVR and ELM. The mean relative error and correlation coefficient obtained by the LSSVM model were 0.0731% and 0.999, respectively. Among the four optimization algorithms, the novel TSGA proposed in this paper showed its superiority over the other three algorithms, excelling in its global searching ability and stability. The LSSVM plus TSGA method is a potential combination for predicting  and reducing NOx emission by optimizing the operating parameters for the gas burner on-line.


NOx emission modeling, Operating parameters optimization, TSGA, Hybrid algorithm, Gas burner

Full Text:



Gonzalez, M.A., Oddi, A., Rasconi, R., and Varela,

R. (2015) Scatter search with path relinking for the

job shop with time lags and setup times. Computers

& Operations Research, 60, 37{54.

Xie, K., Li, W., and Zhao, W. (2010) Coal chemical

industry and its sustainable development in China.

Energy, 35 (11), 4349{4355.



WITH LOW Nox EMISSION. Chinese Jour-

nal of Mechanical Engineering, 38 (01), 108.


CHANG, J.S. (1998) Removal of NOxfrom Flue Gas

by Reburning with Plasma Activated Natural Gas: Review

and Economics. Combustion Science and Tech-

nology, 133 (1-3), 161{190.

Seputro, S., and Sudarmanta, B. (2019) Numerical

Investigation of Over Fire Air (OFA) Eect on

Flow Characteristics NOx Combustion and Emission

in a 600 Mw Tangentially Fired Pulverized Coal Boiler.

IPTEK The Journal of Engineering, 5 (2).

Hiramatsu, T., Najafabadi, H.M., Kobayashi, N.,

and Itaya, Y. (2012) Non-Catalytic Decomposition

of NO by Microwave Plasma Induced at Atmospheric

Pressure in an Activated Coke Bed. KAGAKU KO-

GAKU RONBUNSHU, 38 (6), 397{402.

ZHANG, X. (2009) Eects of Stereo-staged Combustion

Technique on NOx Emmision Charactisctics.

Chinese Journal of Mechanical Engineering, 45 (02),

Zheng, L., Zhou, H., Wang, C., and Cen, K. (2008)

Combining Support Vector Regression and Ant Colony

Optimization to Reduce NOx Emissions in Coal-Fired

Utility Boilers. Energy & Fuels, 22 (2), 1034{1040.

Kowalczyk, B. (2014) Model of an ANSALDO

V94.2 gas turbine from Lublin Wrotkow Combined

Heat and Power Plant using GateCycle™ software.

Journal of Power Technologies, 94.

Isaza, C.V., Sarmiento, H.O., Kempowsky-Hamon,

T., and LeLann, M.-V. (2014) Situation prediction

based on fuzzy clustering for industrial complex processes.

Information Sciences, 279, 785{804.

Li, G., Niu, P., Wang, H., and Liu, Y. (2014) Least

Square Fast Learning Network for modeling the combustion

eciency of a 300WM coal-red boiler. Neu-

ral Networks, 51, 57{66.

Li, G., Niu, P., Ma, Y., Wang, H., and Zhang,

W. (2014) Tuning extreme learning machine by an

improved articial bee colony to model and optimize

the boiler eciency. Knowledge-Based Systems, 67,


Sainlez, M., and Heyen, G. (2013) Comparison of

supervised learning techniques for atmospheric pollutant

monitoring in a Kraft pulp mill. Journal of Com-

putational and Applied Mathematics, 246, 329{334.

Li, G., Niu, P., Liu, C., and Zhang, W. (2012) Enhanced

combination modeling method for combustion

eciency in coal-red boilers. Applied Soft Comput-

ing, 12 (10), 3132{3140.

Rusinowski, H., and Stanek, W. (2010) Hybrid

model of steam boiler. Energy, 35 (2), 1107{1113.

Kalogirou, S.A. (2003) Articial intelligence for the

modeling and control of combustion processes: a review.

Progress in Energy and Combustion Science,

(6), 515{566.

Lee, J.W., Park, Y.J., Kim, I.T., and Lee, K.W.

(2008) Clinical Results After Application of Bevacizumab

in Recurrent Pterygium. Journal of the Ko-

rean Ophthalmological Society, 49 (12), 1901.

Yin, C., Rosendahl, L., Clausen, S., and Hvid, S.L.

(2012) Characterizing and modeling of an 88 MW

grate-red boiler burning wheat straw: Experience

and lessons. Energy, 41 (1), 473{482.

Lopes, C., and Perdig~ao, F. (2008) Event Detection

by HMM SVM and ANN: A Comparative Study,

in Lecture Notes in Computer Science, Springer Berlin

Heidelberg, pp. 1{10.

Smrekar, J., Potocnik, P., and Senegacnik, A.

(2013) Multi-step-ahead prediction of NOx emissions

for a coal-based boiler. Applied Energy, 106, 89{99.

Guo, M.L., Li, D.J., Du, C.B., Jia, Z.H., Qin, X.Z.,

Chen, L., Sheng, L., and Li, H. (2012) Prediction of

the Busy Trac in Holidays Based on GA-SVR, in

Advances in Intelligent and Soft Computing, Springer

Berlin Heidelberg, pp. 577{582.

Lu, Y., and Roychowdhury, V. (2007) Parallel randomized

sampling for support vector machine (SVM)

and support vector regression (SVR). Knowledge and

Information Systems, 14 (2), 233{247.

Hong, W.-C., Dong, Y., Chen, L.-Y., and Wei, S.-

Y. (2011) SVR with hybrid chaotic genetic algorithms

for tourism demand forecasting. Applied Soft Com-

puting, 11 (2), 1881{1890.

Wei, Z., Li, X., Xu, L., and Cheng, Y. (2013)

Comparative study of computational intelligence approaches

for NOx reduction of coal-red boiler. En-

ergy, 55, 683{692.

Chamkalani, A., Zendehboudi, S., Bahadori, A.,

Kharrat, R., Chamkalani, R., James, L., and Chatzis,

I. (2014) Integration of LSSVM technique with PSO

to determine asphaltene deposition. Journal of

Petroleum Science and Engineering, 124, 243{253.

Wu, J., Shen, J., Krug, M., Nguang, S.K., and

Li, Y. (2011) GA-based nonlinear predictive switching

control for a boiler-turbine system. Journal of Control

Theory and Applications, 10 (1), 100{106.

Zhou, H., Lu, J., Cao, Z., Shi, J., Pan, M., Li, W.,

and Jiang, Q. (2011) Modeling and optimization of

an industrial hydrocracking unit to improve the yield

of diesel or kerosene. Fuel, 90 (12), 3521{3530.

Ahmadi, M.A., and Ebadi, M. (2014) Evolving

smart approach for determination dew point pressure

through condensate gas reservoirs. Fuel, 117,


Ahmadi, M.-A., Bahadori, A., and Shadizadeh,

S.R. (2015) A rigorous model to predict the amount of

Dissolved Calcium Carbonate Concentration throughout

oil eld brines: Side eect of pressure and temperature.

Fuel, 139, 154{159.

Ahmadi, M.A., Zahedzadeh, M., Shadizadeh, S.R.,

and Abbassi, R. (2015) Connectionist model for predicting

minimum gas miscibility pressure: Application

to gas injection process. Fuel, 148, 202{211.

Sels, V., Coelho, J., Dias, A.M., and Vanhoucke,

M. (2015) Hybrid tabu search and a truncated branchand-

bound for the unrelated parallel machine scheduling

problem. Computers & Operations Research, 53,


Glover F, L.M. (1997) Tabu search, Kluwer Academic


Gendreau M, P.J.-Y. (2010) Handbook of meta-

heuristics, Springer.


  • There are currently no refbacks.