A real-time model based on least squares support vector machines and output bias update for the prediction of NO x emission from coal-fired power plant

详细信息    查看全文

• 作者：Faisal Ahmed ; Hyun Jun Cho ; Jin Kuk Kim…
• 关键词：NOx Prediction ; Real ; time Model ; Least Squares Support Vector Machine ; Partial Least Squares ; Output Bias Update
• 刊名：Korean Journal of Chemical Engineering
• 出版年：2015
• 出版时间：June 2015
• 年：2015
• 卷：32
• 期：6
• 页码：1029-1036
• 全文大小：475 KB
• 参考文献：1.H. Zhou, K. Cen and J. Fan, Energy, 29, 167 (2004).View Article
  2.Z. Ligang, J. Hailin, Y. Minggao and Y. Minggao, Bioinformatics and Biomedical Engineering (iCBBE), 2010 4 th International Conference on, 1 (2010).
  3.S. Matsumura, T. Iwahara, K. Ogata, S. Fujii and M. Suzuki, Control Eng. Pract., 6, 1267 (1998).View Article
  4.J. Sj枚berg, Q. Zhang, L. Ljung, A. Benveniste, B. Delyon, P. Glorennec, H. Hjalmarsson and A. Juditsky, Automatica, 12, 1691 (1995).View Article
  5.K. Li, S. Thompson and J. Peng, Control Eng. Prac., 12, 707 (2004).View Article
  6.Y. Lv, J. Liu and T. Yang, Ind. Eng. Chem. Res., 51(49), 16092 (2012).View Article
  7.Y.K. Lee, M. Kim and C. Han, J. Environ. Eng., 131, 961 (2005).View Article
  8.T. Adali, B. Bakal, M.K. S脰Nmez and R. Fakory, Integr Comput- Aid E, 6, 27 (1999).
  9.F. Wu, H. Zhou, T. Ren, L. Zheng and K. Cen, Fuel, 88, 1864 (2009).View Article
  10.S. Hui, Power and Energy Engineering Conference (APPEEC), 2012 Asia-Pacific, 1 (2012).
  11.V. Vapnik, The nature of statistical learning theory, Springer Verlag, New York (1995).View Article
  12.J.A.K. Suykens and J. Vandewalle, Neural Processing Letters, 9, 293 (1999).View Article
  13.L. Sheng, and Y. Zhen, Industrial Engineering and Engineering Management (IE&EM), 2011 IEEE 18 th International Conference on, 1732 (2011).
  14.S. Tatinati, Y. Wang, G. Shafiq and K.C. Veluvolu, Conf. Proc. IEEE Eng. Med. Biol. Soc., 6043 (2013).
  15.A. Niazi, S. Sharifi and E. Amjadi, J. Electroanal. Chem., 623, 86 (2008).View Article
  16.A. Niazi, M. Goodarzi and A. Yazdanipour, J. Brazilian Chemical Society, 19, 536 (2008).View Article
  17.R. M. Balabin and E. I. Lomakina, Analyst, 136, 1703 (2011).View Article
  18.F. Ahmed, S. Nazir and Y.K. Yeo, Korean J. Chem. Eng., 26(1), 14 (2009).View Article
  19.C. Cortes and V. Vapnik, Mach Learn, 20, 273 (1995).
  20.K. Helland, H.E. Berntsen, O.S. Borgen and H. Martens, Chemom. Intell. Lab. Syst., 14, 129 (1992).View Article
  21.S. Mu, Y. Zeng, R. Liu, P. Wu, H. Su and J. Chu, J. Process Contr., 16, 557 (2006).View Article
  22.H. Kaneko and K. Funatsu, J. Chem. Eng. Japan, 46, 219 (2013).View Article
  23.R. Sharmin, U. Sundararaj, S. Shah, L.V. Griend and Y. Sun, Chem. Eng. Sci., 61, 6372 (2006).View Article
  24.H. Kubinyi, 鈥淨sar in drug design,鈥?Handbook of Chemoinformatics, Wiley-VCH Verlag GmbH, 1532 (2008).
  25.C. R眉cker, G. R眉cker and M. Meringer, J. Chem. Inf. Model., 47, 2345 (2007).View Article
  26.P. Geladi and B.R. Kowalski, Anal. Chim. Acta, 185, 1 (1986).View Article
  27.P. Kennedy, A guide to econometrics, MIT Press (2003).
  
• 作者单位：Faisal Ahmed (1)
  Hyun Jun Cho (1)
  Jin Kuk Kim (1)
  Noh Uk Seong (1)
  Yeong Koo Yeo (1)
  
  1. Department of Chemical Engineering, Hanyang University, Haengdang-dong, Sungdong-gu, Seoul, 139-791, Korea
  
• 刊物类别：Chemistry and Materials Science
• 刊物主题：Chemistry
  Industrial Chemistry and Chemical Engineering
  Catalysis
  Materials Science
  Biotechnology
  
• 出版者：Springer New York
• ISSN：1975-7220

文摘

The accurate and reliable real-time estimation of NOx emission is indispensable for the implementation of successful control and optimization of NOx emission from a coal-fired power plant. We apply a real-time update scheme to least squares support vector machines (LSSVM) to build a real-time version for real-time prediction of NOx. Incorporation of LSSVM in the update scheme enhances its generalization ability for long-term predictions. The proposed real-time model based on LSSVM (LSSVM-scheme) is applied to NOx emission process data from a coal-fired power plant in Korea to compare the prediction performance of NOx emission with real-time model based on partial least squares (PLS-scheme). Prediction results show that LSSVM-scheme predicts robustly for a long passage of time with higher accuracy in comparison with PLS-scheme. We also present a user friendly and sophisticated graphical user interface to enhance the convenience to approach the features of real-time LSSVM-scheme.