DOI QR코드

DOI QR Code

Adaptive Learning Control of Neural Network Using Real-Time Evolutionary Algorithm

실시간 진화 알고리듬을 통한 신경망의 적응 학습제어

  • 장성욱 (부산대학교 기계공학부 대학원) ;
  • 이진걸 (부산대학교 기계기술연구소)
  • Published : 2002.06.01

Abstract

This paper discusses the composition of the theory of reinforcement teaming, which is applied in real-time teaming, and evolutionary strategy, which proves its the superiority in the finding of the optimal solution at the off-line teaming method. The individuals are reduced in order to team the evolutionary strategy in real-time, and new method that guarantee the convergence of evolutionary mutations are proposed. It is possible to control the control object varied as time changes. As the state value of the control object is generated, applied evolutionary strategy each sampling time because of the teaming process of an estimation, selection, mutation in real-time. These algorithms can be applied, the people who do not have knowledge about the technical tuning of dynamic systems could design the controller or problems in which the characteristics of the system dynamics are slightly varied as time changes. In the future, studies are needed on the proof of the theory through experiments and the characteristic considerations of the robustness against the outside disturbances.

Keywords

References

  1. Chang, S.D. and Lee, J,K., 2000, 'Development of a Hydraulic Servo System Real-Time Simulator Using a One-Board Microprocessor and personal computer,' Proceedings of the 4th Asia-Pacific conference on Control and Measurement, pp. 128-132
  2. 장성욱, 이진걸, 2000a, '원보드 마이크로 프로세서 제어기 및 PC를 이용한 유압서보시스템의 실시간 시뮬레이터 개발,' 한국정밀공학회지, 제17권, 제8호, pp.94-99
  3. Chang, S.D. and Lee, J,K., 2000b, 'A Study on the Application of the Real-Time Simulator,' Proceedings of the 15th Korea Automatic Control Conference
  4. Jain, A. K., 1996, 'Artificial Neural Networks: A Tutorial,' IEEE Computer, Vol. 26, No.3, pp. 31-44 https://doi.org/10.1109/2.485891
  5. Lippmann, R.P., 1987, 'An Introduction to Computing with Neural Nets,' IEEE ASSP Magazine, Vol. 4, No.2, pp. 4-22
  6. Simon Haykin, Neural Networks A Comprehensive Foundation, Second Ed. 1999, Prentice-Hall Inc
  7. CAnderson, harles W., 1989, 'Learning to Control an Inverted Pendulum Using Neural Networks,' IEEE Control Systems Magazine, Vol. 9, No.2, pp. 31-37 https://doi.org/10.1109/37.24809
  8. Barto, A. G., Sutton, R. S. and Anderson, C. W., 1983, 'Neuronlike Adaptive Elements That Can Solve Difficult Learning Control Problem,' IEEE Transactions on Systems, Vol. 13, No.5, pp. 835-846
  9. D.B. Fogel, 1997, 'The Advantages of Evolutionary Computation,' Proc. of BCEC97: BioComputing and Emergent Computation, World Scientific, Singapore, pp. 1 - 11
  10. Fogel, D.B. and L.J. Fogel, 1996, 'Preliminary Experiments on Discriminating between Chaotic Signals and Noise Using Evolutionary Programming,' Proceedings of the First Annual Conference, MIT Press, pp. 512 - 520
  11. Chellapilla, K. and Fogel, D., 1997, 'Two New Mutation Operators for Enhanced Search and Optimization in Evolutionary Programming,' in Applications of Soft Computing, Proc. SPIE Vol. 3165, pp. 260-269 https://doi.org/10.1117/12.279596
  12. Back, T. and Schwefel, H.P., 1996, 'Evolutionary Computation: An Overview,' Proceedings of IEEE International Conference on Evolutionary Computation, pp. 20 - 29 https://doi.org/10.1109/ICEC.1996.542329
  13. Fogel, D. B., 1995, Evolutionary Computation. Toward a New Philosophy of Machine Intelligence, Pisoataway, NJ : IEEE Press
  14. Vonk, E., Jain, L.C. and Johnson, R.P., 1997, Automatic Generation of Neural Network Architecture Using Evolutionary Computation, World Scientific Publishing Co.
  15. Fogel, D.B. and Atmar, J.W., 1990, 'Comparing Genetic Operators with Gaussian Mutations in Simulated Evolutionary Processes Using Linear Systems,' Biological Cybernetics, Vol. 63:2, pp. 111-114 https://doi.org/10.1007/BF00203032
  16. Back, T., 1996, Evolutionary Algorithms in Theory and Practice,' Oxford, NY
  17. Schwefel, H.P., 1995, Evolution and Optimum Seeking,' John Wiley, NJ
  18. Michalewicz, Z. and Fogel, D. B., 2000, How to Solve It: Modern Heuristic, Springer-Verlag, Berlin, pp. 161-184/335-341
  19. Sanchez, E. and Tomassini, M., eds., 1996, Toward Evolvable Hardware: The Evolutionary Engineering Approach, Springer-Verlag, Berlin, pp. 19-47/221-249
  20. Back, T., Hammel, U. and Schwefel, H. P., 1997, 'Evolutionary Computation: Commnets on the History and Current State,' IEEE Transaction on Evolutionary Computation, Vol. 1, No.1, pp. 3-17 https://doi.org/10.1109/4235.585888
  21. Fogel, D. B., 1994, 'An Introdution to Simulated Evolutionary Optimization,' IEEE Tran-saction on Neural Network, Vol. 5, No.1, pp. 3-14 https://doi.org/10.1109/72.265956
  22. Martha L. Abell, 1992, The mathematica handbook, Boston: Academic Press
  23. Moog, 1981, Technical Bulletin, Moog Controls Division, East Autora N.Y
  24. Merrit, H.E., 1967, Hydraulic Control Systems,' John & Wiley & Sons Inc
  25. Geva, S. and Sitte, J., 1995, 'A Cart Experiment Benchmark for Trainable Controllers,' IEEE Control Systems, Vol. 13, No.5, pp. 4051 https://doi.org/10.1109/37.236324
  26. Sutton, R. S. and Barto, A. G., 1998, Reinforcement Learning: An Introduction, The MIT Press, Cambrigde