Journal of the Korea Institute of Information and Communication Engineering (한국정보통신학회논문지)

The Korea Institute of Information and Commucation Engineering (한국정보통신학회)
권호 표지
DOI QR코드

DOI QR Code

Optimal Control using Neural Networks for Brachistochrone Problem

최단강하선 문제를 위한 신경회로망 최적 제어

  • Park, Jin-Hyun (Dept. of Mechatronics Eng., Kyeognam National University of Science and Technology) ;
  • Choi, Young-Kiu (Department of Electrical Engineering, Pusan National University)
  • Received : 2013.12.09
  • Accepted : 2014.01.23
  • Published : 2014.04.30
Download PDF
⟨ Previous Next ⟩

Abstract

The solution of brachistochrone problem turned out the form of a cycloid but correct angle values of bead can be obtained from the table form of inverse relations for the complicated nonlinear equations. To enhance the accuracy, this paper employs the neural network to represent the inverse relation of the complicated nonlinear equations. The accurate minimum-time control is possible with the interpolation property of the neural network. For various final target points, we have found that the proposed method is superior to the conventional ones through the computer simulations.

최단강하선 문제의 해는 cycloid 형태라는 것이 밝혀졌으나, bead의 정확한 각도 값은 복잡한 비선형방정식의 역관계를 테이블 형태로 구해야 얻을 수 있다. 본 논문에서는 이러한 근사해의 정확도를 높이기 위해 신경회로망을 이용하여 비선형방정식의 역관계식을 표현하였고, 신경회로망의 보간 기능으로 인해 높은 정확도의 최단시간제어가 가능하였다. 여러 가지 최종목표점에 대한 컴퓨터 시뮬레이션을 통해서 본 논문에서 제안한 방법이 기존의 방법보다 우수함을 확인할 수 있었다.

Keywords

References

  1. L. Elsgoltz, Differential Equations and Variational Calculus, Mir, Moscow, 1983.
  2. D.E. Kirk, Optimal Control Theory: An Introduction, Prentice-Hall, Inc., 2004.
  3. Frank L. Lewis and Vassilis L. Syrmos, Optimal Control: 3rd Ed, John Wiley & Sons, Inc., 2012
  4. Wang and Jun, Advances in neural Networks-ISNN2006, Springer, 2006.
  5. Fine and Terrence, Feedforward Neural Network Methodology, Springer-Verlag, 1999.
  6. Vojislav Kecman, Learning and Soft Computing, The MIT Press, Cambridge, MA, 2001.
  7. Young-Kiu Choi and Jin-Hyun Park, "Brachistochrone Minimum-Time Trajectory Control Using Neural Networks," J. Korea Inst. Info.Ccom. Eng., vol. 17, no. 12, pp 2775-2784, 2013. https://doi.org/10.6109/jkiice.2013.17.12.2775
  8. Young-Kiu Choi and Jin-Hyun Park, "Minimum-Time Trajectory Control of Ships Using Neural Networks," J. Korea Inst. Info.Ccom. Eng., vol. 17, no. 1, pp 117-126, 2013. https://doi.org/10.6109/jkiice.2013.17.1.117