Multi-model Modeling of Heating Furnace System Based on FCM and GA Optimization ElasticNet-SVR

  • Zhengguang Xu
  • Weijian Kong
  • Mushu Wang
Conference paper
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 529)


Aiming at the characteristics of non-linear, time-varying and wide-ranging working conditions of heating furnace, with the improvement of control requirements for actual system prediction, single model modeling has the problems of large amount of calculation and poor accuracy. A multi-model modeling method is proposed in this paper. This method first divides the actual data of the heating furnace system into training set, validation set and test set, and uses FCM clustering to divide the training set into different working conditions; The Elastic Network (ElasticNet) and support Vector Machine regression (SVR) models are established in each local condition, and the optimal model of each local condition is selected from the two models by the validation set; use genetic algorithm (GA) to obtain the optimal weight of each local model, finally construct a model suitable for the global. This modeling method has a good global adaptability to the identification process. The veracity of the model is verified on the test set, and good results are obtained.


Multi-model modeling FCM clustering ElasticNet-SVR model Genetic algorithm 


  1. 1.
    Q. Cai, Furnace (Metallurgical Industry Press, Beijing, 2007)Google Scholar
  2. 2.
    L. Wang, Z. Zhao, System Identification: new patterns, challenges and opportunities. Acta Automatica Sin. 397, 933–942 (2013)CrossRefGoogle Scholar
  3. 3.
    G. Tang, Z. Zhuang, Analysis on energy saving scheme of refinery heating furnace. Chem. Mach. 27, 352–355 (2000)Google Scholar
  4. 4.
    S. Liu, Y. Qi, L. Wang et al., Hybrid modeling and optimization of coal consumption and NOx emission of utility boiler. Petrochemical Auto-chemical Equip. 1, 30–34 (2016)Google Scholar
  5. 5.
    H. Li, Q. Li, Y. Tang, A neural network model for heating furnace. Min. Metall. 12(3), 67–69 (2003)MathSciNetGoogle Scholar
  6. 6.
    Z. Wang, T. Chai, C. Shao, Prediction model of reheating furnace steel temperature based on RBF neural network. Rep. Syst. Simul. 181–185 (1999)Google Scholar
  7. 7.
    C. Mu, R. Zhang, C. Sun, A particle swarm optimization based least squares support vector machine predictive control method for nonlinear systems. Control Theory Appl. (2010)Google Scholar
  8. 8.
    Y. Wang, D. Huang et al., Nonlinear predictive control technique based on LS-SVM. Control Decis. Making 4, 383–387 (2004)zbMATHGoogle Scholar
  9. 9.
    T.A. Johansen, B.A. Foss, A NARMAX model representation for adaptive control based on local models. Model. Ident. Control 13(1), 25–39 (1992)CrossRefGoogle Scholar
  10. 10.
    R. Murray-Smith, T.A. Johansen, Local learning in local model networks, in International Conference on Artificial Neural Networks (IET, 1995), pp. 40–46Google Scholar
  11. 11.
    C. Huang, Y. Gao, L. Peng, Study on modeling and identification of industrial process with multiple models. Comput. Eng. Appl. 52(20), 251–262 (2016)Google Scholar
  12. 12.
    J. Lin, J. Shen, Y. Li, Multi-model modeling method for thermal processes based on hierarchical G-K clustering. J. Electr. Eng. China (CAE) 26(11), 23–28 (2006)Google Scholar
  13. 13.
    H. Zou, T. Hastie, Regularization and variable selection via the elastic net. J. R. Stat. Soc. Ser. B (Stat. Methodol.) 67(2), 301–320 (2005)MathSciNetCrossRefGoogle Scholar
  14. 14.
    C. De Mol, E. De Vito, L. Rosasco, Elastic-net regularization in learning theory. J. Complex. 25(2), 201–230 (2009)MathSciNetCrossRefGoogle Scholar
  15. 15.
    Y. Cai, C. Hu, Study on multi-output ε-SVR model for identification of nonlinear MIMO systems. Control Decis. 237, 813–816 (2008)Google Scholar
  16. 16.
    H. Zhang, Z. Han, C. Li, Nonlinear system identification based on support vector machine. J. Syst. Simul. 15(1), 119–121 (2003)Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2019

Authors and Affiliations

  1. 1.School of Automation & Electrical EngineeringUniversity of Science and Technology BeijingBeijingChina

Personalised recommendations