The Transactions of the Korean Institute of Electrical Engineers D (대한전기학회논문지:시스템및제어부문D)

The Korean Institute of Electrical Engineers (대한전기학회)
권호 표지

Evolving Neural Network Controller for Stabilization of Inverted Pendulum System

도립 진자 시스템의 안정화를 위한 진화형 신경회로망 제어기

  • Sim, Yeong-Jin (Dept.of Electronics Engineering, Donga University) ;
  • Lee, Jun-Tak (Dept.of Electronics Engineering, Donga University)
  • Published : 2000.03.01
Download PDF
⟨ Previous Next ⟩

Abstract

In this paper, an Evolving Neural Network Controller(ENNC) which its structure and its connection weights are optimized simultaneously by Real Variable Elitist Genetic Algoithm(RVEGA) was presented for stabilization of an Inverter Pendulum(IP) system with nonlinearity. This proposed ENNC was described by a simple genetic chromosome. And the deletion of neuron, the determinations of input or output neuron, the deleted neuron and the activation functions types are given according to the various flag types. Therefore, the connection weights, its structure and the neuron types in the given ENNC can be optimized by the proposed evolution strategy. Through the simulations, we showed that the finally acquired optimal ENNC was successfully applied to the stabilization control of an IP system.

Keywords

References

  1. H. F. Shao, B. G. Hu, Z. L. Zhu, 'A Case Study of One-to-Two Mapping Fuzzy PD Controllers on Inverted Pendulum' IEEE International Fuzzy Systems Conference Proceedings, pp. 1-424 -1-429, 1999 https://doi.org/10.1109/FUZZY.1999.793277
  2. Shigeyasu Kawaji, Teruyuki Maeda, 'Fuzzy Servo Control System for an Inverted Pendulum', Fuzzy Engineering toward Human Friendly Systems, Vol. 2, pp. 812-823, 1991
  3. Jianqiang Yi, Naoyoshi Yubazaki, Kaoru Hirota, 'Upswing and Stabilization Control of Inverted Pendulum and Cart System by the SlRMs Dynamically Connected Fuzzy Inference Model', IEEE International Fuzzy Systems Conference Proceedings, pp. I-400 - I-405, 1999
  4. Mark G. Cooper, Jacques J. Vidal, 'Genetic Design of Fuzzy Controllers: The Cart and Jointed-Pole Problem', 1994
  5. Branko Souck and The IRIS Group, Dynamic, Genetic and Chaotic Programming, A. Wiley-Interscience Publication, 1992
  6. 이준탁, 이권순, 이상석, 박철영, '신경회로망 제어기를 이용한 직류 서보 전동기의 위치 제어'. 대한전기학회 하계학술대회 논문집 A, pp. 241-243, 1993
  7. David E. Goldberg, Genetic Algorithms in Searching, Optimization & Machine Learning, Addison-Wesley, 1989
  8. K. Balakrishnan and V. Honavar, 'Evolutionary Design of Neural Architectures', Artificial Intelligence Research Group, CS TR #95-01, Jan, 1995
  9. D. Whitley, F. Gruau, and L. Pyeatt, 'Cellular Encoding Applied to Neurocontrol', In Proceedings of 6th International Conference on Genetic Algorithms, pp. 460-467, 1995
  10. F. Gruau, D. Whitley, and L. Pyeatt, 'A Comparison between Cellular Encoding and Direct Encoding for Genetic Neural Networks, In J. Koza, D. Goldberg, D. Fogel, and R. Riolo, editors, Genetic Programming 1996: Proceedings of the First Annual Conference, pp. 81-89, 1996
  11. J. C. F. Pujol and R. Poli, 'Evolving Neural Controller Using a Dual Network Representation', Technical Report CSRP-97-25, The University of Birmingham, School of Computer Science, 1997
  12. Technical Report CSRP-97-25 Evolving Neural Controller Using a Dual Network Representation J.C.F. Pujol;R. Poli