Air-Fuel-Ratio Optimal Control of a Gas Heating Furnace Based on Fuzzy Neural Networks

  • Heng Cao
  • Ding Du
  • Yunhua Peng
  • Yuhai Yin
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3973)


Based on Neural Network BP algorithm and self-optimizing control, taking gas heating furnace air-fuel-ratio optimized control as goal, a new heating furnace intelligent control algorithm is raised and applied in the practice. Comparing fuzzy neural network hybrid algorithm and PID control algorithm, with gas heating furnace energy-saving control reconstruct, new algorithm can achieve function of automatic tracking calorific value variable and adjusting air-fuel-ratio. The characteristics of this algorithm are high precision and reliability, and suitable for project application.


Membership Function Fuzzy Rule Fuzzy Controller Fuzzy Neural Network Heating Furnace 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Vesloki, T.A., et al.: Application of a Dynamic Model of a Reheating Furnace. Iron and Steel Engineer 59(4), 46–51 (1982)Google Scholar
  2. 2.
    Holland, F.D.: Development and Performance of On-line Computer Control in a 3–Zone Reheating Furnace. Iron and Steel Engineer 59(1), 44–52 (1982)Google Scholar
  3. 3.
    Las, K.: Advance Process Control Handbook I~VII. Hydrocarbon Processing (1986-1992)Google Scholar
  4. 4.
    Ronald, R.Y.: Implementing Fuzzy Logic Controllers Using a Neural Network Framework. Fuzzy Sets and Systems 48(8), 53–64 (1992)MathSciNetGoogle Scholar
  5. 5.
    Lee, H.M., Chen, C., Huang, T.C.: Learning Efficiency Improvement of Back-propagation Algorithm by Error Saturation Prevention Method. Neuron Computing 41(2), 125–143 (2002)Google Scholar
  6. 6.
    Smith, O.J.M.: Closer Control of Loops with Dead Time. Chemical Engineering Progress Trans. 53(5), 217–219 (1997)Google Scholar
  7. 7.
    Majhi, S., Atherton, D.P.: Obtaining Controller Parameters for a New Smith Predictor Using Autotuning. Automatica 36(6), 161–168 (2000)MathSciNetGoogle Scholar
  8. 8.
    Tan, K.K., Lee, T.H., Leu, F.M.: Predictive PI Versus Smith Control for Dead-time Compensation. ISA Transactions (40), 17–29 (2001)Google Scholar
  9. 9.
    Li, W., Chang, X.G., Wahl, F.M., et al.: Tracking Control of a Manipulator under Uncertainty by Fuzzy PID Controller. Fuzzy Sets and Systems 15(23), 125–137 (2002)MATHCrossRefMathSciNetGoogle Scholar
  10. 10.
    Gao, X., Li, S., Chai, T.: Modeling and Intelligent Compound Control of Direct Current Electric Arc Furnace. Control Theory and Applications 6(16), 49–52 (1996)Google Scholar
  11. 11.
    Rumelhart, D.E., Hinton, G.E., Williams, R.J.: Learning Internal Representations by Error Propagation in Parallel Distributed Processing. Instrumentation in the Power Industry 33(5), 17–29 (1996)Google Scholar
  12. 12.
    Maffezoni, C.: Boiler-turbine Dynamics in Power-plant Control. Control Engineering Practice 5(3), 303–304 (1997)CrossRefGoogle Scholar
  13. 13.
    Koo, K.-D., Lee, O.-J.: Technical Review of Enhanced Process Digital Control and Automation at the Poryong Thermal Power Plant. Industry Computing Conference 5(3), 1–6 (1997)Google Scholar
  14. 14.
    Emoto, G.: Integrated Large-scale Multivariable Control and Real-time. Optimization of a Power Plant 16(8), 11–18 (1995)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Heng Cao
    • 1
  • Ding Du
    • 1
  • Yunhua Peng
    • 2
  • Yuhai Yin
    • 1
  1. 1.School of Mechanical and Power EngineeringEast China University of Science and TechnologyShanghaiChina
  2. 2.Shanghai Baosteel Chemical Co. Ltd.ShanghaiChina

Personalised recommendations