Proceedings of the KIEE Conference (대한전기학회:학술대회논문집)
- 2006.07d
- /
- Pages.1848-1849
- /
- 2006
Robust Flight Control System Using Neural Networks: Dynamic Surface Design Approach
신경 회로망을 이용한 강인 비행 제어 시스템: 동적 표면 설계 접근
- Yoon, Sung-Jin (Dept. of Electrical & Electronic Engineering, Yonsei University) ;
- Choi, Yoon-Ho (School of Electronic Engineering, Hyonggi University) ;
- Park, Jin-Bae (Dept. of Electrical & Electronic Engineering, Yonsei University)
- Published : 2006.07.12
Abstract
The new robust controller design method is proposed for the flight control systems with model uncertainties. The proposed control system is a combination of the adaptive dynamic surface control (DSC) technique and the self recurrent wavelet neural network (SRWNN). The adaptive DSC technique provides us with the ability to overcome the "explosion of complexity" problem of the backstepping controller. The SRWNNs are used to observe the arbitrary model uncertainties of flight systems and all their weights are trained on-line. From the Lyapunov stability analysis, their adaptation laws are induced and the uniformly ultimately boundedness of all signals in a closed-loop adaptive system is proved. Finally, simulation results for a high performance aircraft (F-16) are utilized to validate the good tracking performance and robustness of the proposed control system.
Keywords