Prarmeter Tuning of Fuzzy Cotroller using Neural Networks System Identifier

신경회로망 시스템 식별기를 이용한 퍼지제어기의 변수동조

  • Published : 1996.09.01

Abstract

By using the neural networks(NN) as system identifier, the on-line self tuning method for fuzzy controller(FC) is proposed. In theis method, the learning of NN is carried out during control operation of FC and the cinsequent parameters of FC is tuned on-line automatically by means of system output errors backpropagated through NN. The Sugeno fuzzy model with constants as consequent parameters is selected for simplifying computation. In procedures of parameter tuning, the gradient descent method is used and the gradient vectors for adjusting the weight of NN are transferred as controller output errors. To evaluate the performance, the proposed method is applied to the inverted pendulum system.

Keywords

References

  1. Informat.control v.8 Fuzzy sets L.A.Zadeh
  2. IEEE Trans. on Syst. Man, Cybern. v.SMC-15 Fuzzy identification of system and its applications to modeling and control T.Takagi;M.Sugeno
  3. International Journal of Approximate Reasoning Construction of fuzzy inference rules by NDF and NDFL I.Hayashi(et al.)
  4. IECON'90 Composition methods of fuzzy neural networks S.Horikawa(et al.)
  5. IEEE Trans. on Syst. Man Cybern v.23 no.3 ANFIS : Adaptive-network-based fuzzy inference system J.S.R.Jang
  6. IEEE Trans. on Syst., Man, Cybern v.23 no.3 Direct control and coordination using neural networks X.Cui;K.G.Shin
  7. Kybernets v.7 no.3 Fuzzy relations in a control setting M.Braae;D.A.Rutherford