Adaptive Controller Based on Wavelets Neural Network for a Class of Nonlinear Systems

  • Zhijun Zhang
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4113)


An adaptive control strategy for nonlinear systems is presented. The simple control law is derived based on minimizing a well-chosen performance index. Wavelets neural network model is applied to the scheme that can overcome the problem caused by the local minima when training the neural network. Compared with existing algorithms such as stochastic gradient algorithm, the present algorithm has the advantage of rapid convergence and low computational cost. The proposed approach is finally applied in a chemical reactor control problem. The simulation results proved that the proposed adaptive control method can effectively control unknown nonlinear systems.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Yasar, B., Ahmet, F.K., Tariq, S.: Intelligent Optimal Control with Dynamic Neural Networks. Neural networks 16, 251–259 (2003)CrossRefGoogle Scholar
  2. 2.
    Ahmed, M.S.: Design of a Fixed Neural Controller for Nonlinear Plants. Internat. J. Control 69, 65–83 (1998)zbMATHCrossRefMathSciNetGoogle Scholar
  3. 3.
    Boozarjomehry, R.B., Svrcek, W.L.Y.: Automatic Design of Neural Network Structures. Computer and Chemical Engineering 25, 1075–1088 (2001)CrossRefGoogle Scholar
  4. 4.
    Arim, M.N., AI-Duwaish, H.: Use of Multilayer Feedforward Neural Networks in Identification and Control of Wiener Model. IEE Proceedings, Control Theory and Applications 143, 255–258 (1996)CrossRefGoogle Scholar
  5. 5.
    Wang, J.: Adaptive Control for Nonlinear Systems Using Decomposed Neural Networks. Cybernetics and Systems. An International Journal 29, 73–83 (1998)zbMATHCrossRefGoogle Scholar
  6. 6.
    Debnath, L.: Wavelet Transforms and Their Applications. Springer, New York (2002)zbMATHGoogle Scholar
  7. 7.
    Jose, V., Fernando, M.D., Alexandre, M.: Artificial Neural Networks and Neurofuzzy Systems for Modelling and Controlling Real Systems: a Comparative Study. Engineering Applications of Artificial Intelligence 17, 265–273 (2004)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Zhijun Zhang
    • 1
  1. 1.Dalian university of technologyDalianChina

Personalised recommendations