Modeling of Nonlinear Dynamic Dynamic Systems Using a Modified GMDH Algorithm

수정된 GMDH 알고리즘을 이용한 비선형 동적 시스템의 모델링

  • 홍연찬 (인천대학교 전자공학과) ;
  • 엄상수 (인천대학교 전자공학과)
  • Published : 1998.06.01

Abstract

The GMDH(Group Method of Data Handling) is a useful data analysis technique for identification of nonlinear complex systems. Therefore, in this paper the application method of GMDH algorithm for modeling nonlinear dynamic systems is proposed. The identification of dynamic systems by using GMDH consists of applying a set of input/output data and computing the necessary coefficient set dynamically. Also, in this paper, by reducing sequentially the criterion which can adopt or reject the data, a method to prevent excessive computation that is a disadvantage of GMDH is proposed.

GMDH(Group Method of Data Handing)는 복잡한 비선형 시스템을 인식하는데 유용한 데이타 분석 기법이다. 따라서 본 논문에서는 비선형 다이내믹 시스템을 모델링하기 위한 GMDH 알고리즘의 적용 방법을 제안한다. GMDH를 사용한 다이내믹 시스템의 인식은 일련의 입출력 데이타를 인가하여 필요한 계수들의 집합을 동적으로 산출함으로써 이루어진다. 또한, 본 논문에서는 데이타를 취사 선택하는 기준을 순차적으로 감소시킴으로써 GMDH의 단점인 계산량의 과다를 방지하는 방법도 제안하였다.

Keywords

References

  1. IEEE Trans.Syst.Man Cybern v.SMC-1 Polynomial theory of complex systems A.G.Ivakhnenko
  2. Automatica v.6 Heuristic self-organization in problems of engineering cybernetics A.G.Ivakhnenko
  3. IEEE Trans.Automat.Contr. v.AC-12 A learning technique for Volterra series representation R.A.Roy;J.Sherman
  4. Mathl.Comput.Modeling v.17 no.1 The characteristics of a biased estimator applied to the adaptive GMDH T.Nishikawa;S.Shimizu
  5. Self-Organizing Methods in Modeling:GMDG Type Algorithms S.J.Farlow
  6. Soviet Automatic Control v.25 no.3 Estimating the coeffcients of polynomials in parametric GMDH algorithms by the improved instrumental variables method A.G.Ivakhnenko;A.A.Zholnarskiy
  7. Proc.23rd IFAC World Conger. v.ⅩⅩⅢ Application of revised GMDH Algorithms to the prediction of air pollutant concentrations T.Yoshimura;R.Kiyozumi;K.Nishino;T.Soeda
  8. IEEE Trans.Automat.Contr. v.AC-19 A new look at the statistical model identification H.Akaike
  9. Fuzzy Sets and Systems v.36 The fuzzy GMDH algorithms by possibility models and its application I.Hayashi;H.Tanaka
  10. Journal of Manufacturing Systems v.7 no.3 Applications of GMDH-type modeling in manufacturing P.Y.Chao;P.M.Ferreira;C.R.Liu
  11. Proc.1991 IEEE Int.Conf.on Robotics and Automation Robot Kinematics learning computations using polynomial neural networks C.L.P.Chen;A.D.McAulay
  12. IEEE Trans.Neural Networks v.1 no.1 Identification and control of dynamical systems using neural networks K.S.Narendra;K.Parthasarathy