Advertisement

Recurrent Fuzzy-Neural Network with Fast Learning Algorithm for Predictive Control

Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8131)

Abstract

This paper presents a Takagi-Sugeno type recurrent fuzzy-neural network with a global feedback. To improve the predictions and to minimize the possible model oscillations, a hybrid learning procedure based on Gradient descent and the fast converging Gauss-Newton algorithms, is designed. The model performance is evaluated in prediction of two chaotic time series – Mackey-Glass and Rossler. The proposed recurrent fuzzy-neural network is coupled with analytical optimization approach in a Model Predictive Control scheme. The potentials of the obtained predictive controller are demonstrated by simulation experiments to control a nonlinear Continuous Stirred Tank Reactor.

Keywords

recurrent fuzzy-neural networks Takagi-Sugeno predictive control optimization Gradient descent Gauss-Newton method momentum learning 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Mendes, J.: Adaptive fuzzy generalized predictive control based on Discrete-Time T-S fuzzy model. In: Proc. IEEE Conf. of Em. Tech. and Factory Automation, pp. 1–8 (2010)Google Scholar
  2. 2.
    Chaladi, M., Borne, P.: Multiple Models Approach in Automation: TS Fuzzy Systems. Wiley (2012)Google Scholar
  3. 3.
    Chi-Huang, L., Chi-Ming, L.: Stable predictive control based on recurrent fuzzy neural networks. In: Proceeding on 8th Asian Control Conf (ASCC), pp. 897–901 (2011)Google Scholar
  4. 4.
    Chi-Huang, L., Ching-Chih, T.: Generalized predictive control using recurrent fuzzy neural networks for industrial processes. Journal of Process Control 17, 83–92 (2007)CrossRefGoogle Scholar
  5. 5.
    Mendes, J., Sousa, N., Araujo, R.: Adaptive predictive control with recurrent fuzzy neural network for industrial processes. In: 16th IEEE ETFA Conference, pp. 1–8 (2011)Google Scholar
  6. 6.
    Ching-Hung, L., Chang, H., Ting Kuo, C., Chieh Chien, J., Wei Hu, T.: A Novel Recurrent Interval Type-2 Fuzzy neural Network for Nonlinear Channel Equilization. In: Proceeding of the Int. MultiConf. of Eng. and Computer Sci., pp. 7–12 (2009)Google Scholar
  7. 7.
    Chia-Feng, J., Yang-Yin, L., I-Fang, C.: Dynamic System Identification Using A Type-2 Recurrent Fuzzy Neural Network. In: Proc. of the 7th Asian Control Conference (2009)Google Scholar
  8. 8.
    Chia-Feng, J., Chun-Feng, L., Po-Han, C.: Dynamic Plant Control Using Recurrent Fuzzy Controller with Ant Colony Optimization in Real Space. In: Proc. of the International IEEE Conference on Systems Man and Cybernetics, pp. 1134–1138 (2010)Google Scholar
  9. 9.
    Ya-Ling, C., Ching-Chih, T.: A TSK-Type Recurrent Fuzzy Neural Network Adaptive Inverse Modeling Control for a Class of Nonlinear Discrete-Time Time-Delay Systems. In: Proc. of SICE Annual Conference, pp. 2390–2393 (2010)Google Scholar
  10. 10.
    Terzyiska, M., Todorov, Y., Mitev, A., Petrov, M.: Nonlinear Model Based Predictive Controller using a Fuzzy-Neural Hammerstein model. In: Proc. of the Int. Conf. ‘Modern Trends in Control’, pp. 299–308 (2006)Google Scholar
  11. 11.
    Terzyiska, M., Todorov, Y., Petrov, M.: Nonlinear Model Predictive Controller with Adaptive Learning rate Scheduling of an internal model. In: Proc. of the Int. Conf. ‘Modern Trends in Control’, pp. 289–298 (2006)Google Scholar
  12. 12.
    Todorov, Y., Tsvetkov, T.: Volterra Model Predictive Control of a Lyophilization plant. In: Proc. of the 4th IEEE Conf. “Intelligent Systems”, vol. 3, pp. 13–18 (2008)Google Scholar
  13. 13.
    Yao, J., Mao, J., Zhang, W.: Application of Fuzzy Tree on Chaotic Time Series Prediction. In: IEEE Proc. of Int. Conf. on Aut. and Logistics, pp. 326–330 (2008)Google Scholar
  14. 14.
    Lai, Y.: Recent developments in chaotic time series analysis. International Journal of Bifurcation and Chaos 13(6), 1383–1422 (2003)MathSciNetCrossRefzbMATHGoogle Scholar
  15. 15.
    Diaconescu, E.: The use of NARX Neural Networks to predict Chaotic Time Series. WSEAS Trans. on Computer Research 3(3), 182–191 (2008)Google Scholar
  16. 16.
    Archana, R., Unnikrishnan, A., Gopikakumari, R.: Bifurcation Analysis of Chaotic Systems using a Model Built on Artificial Neural Networks. In: Proc. of Int. Conf. on Comp. Tech. and Artificial Intelligence, pp. 198–202 (2013)Google Scholar
  17. 17.
    Ray, W.H.: Advanced Proceess Control. McGraw-Hill, New York (1981)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  1. 1.Institute of Information and Communication TechnologiesBulgarian Academy of SciencesSofiaBulgaria
  2. 2.Technical University-SofiaPlovdivBulgaria

Personalised recommendations