Proceedings of the KIEE Conference (대한전기학회:학술대회논문집)
- 1996.11a
- /
- Pages.401-403
- /
- 1996
Neural Network Learning Algorithm for Variable Structure System
가변구조 시스템을 위한 신경회로망 학습 알고리즘
- Cho, Jeong-Ho (Department of Electrical Engineering, Dongguk University) ;
- Lee, Dong-Wook (Department of Electrical Engineering, Dongguk University) ;
- Kim, Young-T. (Department of Electrical Engineering, Dongguk University)
- Published : 1996.11.16
Abstract
In this paper, a new control strategy is presented that combines sliding mode control theory with a neural network. Sliding mode control theory requires the complete knowledge of the dynamics of the controlled system. However, in practice, one often bas only a small number of state measurements. This could be a serious limitation on the practical usefulness of sliding mode control theory. A multilayer neural network is employed to solve this kind of problem. The neural network serves as a compensator without a prior knowledge about the system. The proposed control algorithm is applied to a class of uncertain nonlinear system. The robustness against parameter uncertainty, nonlinearity and external disturbances, and the effectiveness is verified by the simulation results.
Keywords