자기 회귀 웨이블릿 신경 회로망 관측기 기반 비선형 시스템의 슬라이딩 모드 제어

Self-Recurrent Wavelet Neural Network Observer Based Sliding Mode Control for Nonlinear Systems

  • 유성진 (연세대학교 전기전자공학과) ;
  • 최윤호 (경기대학교 전자공학부) ;
  • 박진배 (연세대학교 전기전자공학과)
  • You, Sung-Jin (Dept. of Electrical & Electronic Engineering, Yonsei University) ;
  • Choi, Yoon-Ho (School of Electronic Engineering, Kyonggi University) ;
  • Park, Jin-Bae (Dept. of Electrical & Electronic Engineering, Yonsei University)
  • 발행 : 2004.07.14

초록

This paper proposes the self-recurrent wavelet neural network (SRWNN) observer based sliding mode control (SMC) method for nonlinear systems. Unlike the classical SMC, we assume that all states of nonlinear systems are not measured and design the SRWNN observer to measure the states of nonlinear systems. The SRWNN in the observer is used for approximating the observer system's gain. To generate the control input for controlling the nonlinear system, the measured states are used. The sliding surface with a boundary layer is defined to remove the chattering of the control input. Simulation result to show the effectiveness of the SRWNN observer is presented.

키워드