Korean Journal of Chemical Engineering, Vol.35, No.9, 1779-1790, September, 2018
Comparative study of estimation methods of NOx emission with selection of input parameters for a coal-fired boiler
This study focuses on estimation of NOx emission and selection of input parameters for a coal-fired boiler in a 500MW power generation plant. Careful selection of input parameters is required not only to improve accuracy of the estimation, but also to reduce the model dimensionality. The initial operating input parameters are determined based on operation heuristics and accumulated operation knowledge; the essential input parameters are selected by sensitivity analysis where the performance of the estimation model is assessed as one or some input parameters are successively eliminated from the computation while all other input parameters are retained. From the sequential input selection process, less than ten input parameters survived out of 36 initial input parameters. Auto-regressive moving average (ARMA) model, artificial neural networks (ANN), partial least-squares (PLS) model, and least-squares support vector machine (LSSVM) algorithm were proposed to express the relationship between the operating input parameters and the content of NOx emission. Historical real-time data obtained from a 500MW power plant coal-fired boiler were used to test the proposed models. It was found that principal components analysis (PCA) enhances the estimation performance of each model. Among the four proposed estimation models, the LSSVM model coupled with PCA scheme showed the minimum root-mean square error (RMSE) and the best R-square value.
- Choi CR, Kim CN, Fuel, 88(9), 1720 (2009)
- Fiveland WA, Latham CE, Combust. Sci. Technol., 93(1), 53 (1993)
- Zhou H, Cen KF, Fan JR, Energy, 29(1), 167 (2004)
- Zhou H, Zheng LG, Cen KF, Energy Conv. Manag., 51(3), 580 (2010)
- Zheng LG, Zhou H, Cen KF, Wang CL, Expert. Syst. Appl., 36(2), 2780 (2009)
- Ahmed F, Cho HJ, Kim JK, Seong NU, Yeo YK, Korean J. Chem. Eng., 36(6), 1029 (2015)
- Lv Y, Liu JZ, Yang TT, Zeng DL, Energy, 55, 319 (2013)
- Ding YR, Cai YJ, Sun PD, Caen B, J. Appl. Res. Technol., 12, 493 (2014)
- Nomikos P, Macgregor JF, AIChE J., 40(8), 1361 (1994)
- Haykin S, Neural networks: A comprehensive foundation (2nd Ed.), Prentice Hall, New Jersey (1999).
- Smrekar J, Assadi M, Fast M, Kustrin I, De S, Energy, 34(2), 144 (2009)
- Geladi P, Kowalski BR, Anal. Chim. Acta, 185, 1 (1986)
- Sharaf MA, Illman DL, Kowalski BR, Chemometrics, Wiley, New York (1986).
- Baffi G, Martin EB, Morris AJ, Comput. Chem. Eng., 23(3), 395 (1999)
- Kim TY, Kim BS, Park C, Yeo YK, Korean J. Chem. Eng., 34(7), 1952 (2017)
- Suykens JAK, Vandewalle J, Neural Process Letters, 9(3), 293 (1999)
- van Gestel T, Suykens JAK, Baesens B, Viaene S, Vanthienen J, Dedene G, de Moor B, Vandewalle J, Mach Learning, 54(1), 5 (2004)
- Olsen RL, Chappell RW, Loftis JC, Water Res., 46, 3110 (2012)
- Dunteman GH, Principal components analysis, Sage University Paper Series on Quantitative Applications in the Social Sciences, California (1999).
- Jeong H, Cho S, Kim D, Pyun H, Ha D, Han C, Kang M, Jeong M, Lee S, Int. J. Hydrog. Energy, 37(15), 11394 (2012)
- Zeng J, Liu K, Huang W, Liang J, Korean J. Chem. Eng., 34(8), 2135 (2017)