Neural Network based Variable Structure Control for a Class of Nonlinear Systems

비선형 시스템 계통에서 신경망에 근거한 가변구조 제어

  • 김현호 (도립충북대학교 전자정보과) ;
  • 이천희 (청주대학교 전자공학과)
  • Published : 2001.03.01


This paper presents a neural network based variable structure control scheme for nonlinear systems. In this scheme, a set of local variable structure control laws are designed on the basis of the linear models about preselected representative points which cover the range of the system operation of interest. From the combination of the set of local variable structure control laws, neural networks infer the approximate control input in between the operating points. The neural network based variable structure control alleviates the effects of model uncertainties, which cannot be compensated by the control techniques using feedback linearization. It also relaxes the discontinuity in the system’s behavior that appears when the control schemes based on the family of the linear models are applied to nonlinear systems. Simulation results of a ball and beam system, to which feedback linearization cannot be applied, demonstrate the feasibility of the proposed method.


  1. Ma XL. Tao G., 'Adaptive actuator compensation control with feedback linearization,' IEEE Trans. AC., Vol.45, No.9, pp.1705-1710, Sep. 2000
  2. Choi JY, Farrell JA, 'No.nlinear adaptive control using networks of piecewise linear approximators,' IEEE Trans. Neural Networks, Vol.11, No.2, pp.390-401, March 2000
  3. Kurtz MJ, Henson MA, 'Feedback linearizing control of discrete-tine No.nlinear systems with input constraints,' International Journal of Control, Vol.70, No.4, pp.603-616, Jul. 1998
  4. J. Hauser, S. Sasrtry, P. Kokotovic, 'No.nlinear control via approximate input-output linearization: The ball and beam example,' IEEE Trans. AC., Vol.37, No.3, pp.392-398, March 1992
  5. Qian CJ. Lin W, 'Almost disturbance decoupling for a class of high-order No.nlinear systems,' IEEE Trans. AC., Vol.45, No.6, pp.1208-1214, Jun. 2000
  6. K. J. AstrOm, B. Wittenmark, Adaptive Control, Addison-Wesely, 1989
  7. D. A. Lawrence, W. J. Rugh, 'Gain scheduling dynamic linear controllers for a No.nlinear plant,' Proc. IEEE Conf. Dec. and Contr., pp.1024-1029, San Antonio, 1993
  8. R. T. Reichert, 'Dynamic scheduling of modern-robust-control autopilot designs for missiles,' Journal of IEEE, Control and systems, Oct 1992
  9. S. S. Farinwata, 'On the stability fyzzy control rule base for a No.nlinear process,' Proceed. IEEE Conf. Fuzzy and Systems, pp.924-929, 1994
  10. C. K. Chak, G. Feng, 'No.nlinear control system with fuzzy logic design,' Proceed. IEEE Conf. Fuzzy and Systems, pp.1592-1597, San Antonio, 1994
  11. Chan ML, Tao CW, Lee TT, 'Sliding mode controller for linear systems with mismatched time-varying uncertainties,' Journal of the Franklin Institute, Vol.337, No.2, pp.105-115, March 2000
  12. A. J. Calise and K. V. Ramman, 'A servo compensator design approach for variable structure systems,' '82 ACC, pp.1014-1019, 1982
  13. Mahmoud NA, Khalil HK, 'Robust control for a No.nlinear servomechanism problem,' International Journal of Control, Vol.66, No.6, pp.779-802, Aprl. 1997
  14. Hwang KS, Chao HJ, 'Adaptive reinforcement learning system for linearization control,' IEEE Trans. Industrial Electronics, Vol.47, No.5, pp.1185-1188, Oct. 2000
  15. Tsaj CH, Lu HC, 'Observer-based speed estimation method for sensorless vector control using artificial neural network,' Electric Machines & Power Systems, Vol.28, No.9, pp.861-873, Sep. 2000
  16. Rahman MHRF, Devanathan R, Zhu KY, 'Neural networking approach for linearizing control of No.nlinear process plants,' IEEE Trans. Industrial Electronics, Vol.47, No.2, pp.470-477, Apr. 2000
  17. O.M.E.El Ghezawl, et al., 'Analysis and design of variable structure systems using a geometric approach,' Int. J. Contr., Vol.38, No.3, pp.657-671, 1983