Adaptive Neural Control for Pure-feedback Nonlinear Systems

순궤환 비선형 시스템의 적응 신경망 제어기

  • Park Jang-Hyun (School of Electric, Control, Advanced Material Engineering, Mokpo University) ;
  • Kim Do-Hee (School of Electric, Control, Advanced Material Engineering, Mokpo University) ;
  • Kim Seong-Hwan (School of Electric, Control, Advanced Material Engineering, Mokpo University) ;
  • Moon Chae-Joo (School of Electric, Control, Advanced Material Engineering, Mokpo University) ;
  • Choi Jun-Ho (Department of Electrical Engineering, Chonnam Univerity)
  • 박장현 (목포대학교 전기제어신소재공학부) ;
  • 김도희 (목포대학교 전기제어신소재공학부) ;
  • 김성환 (목포대학교 전기제어신소재공학부) ;
  • 문채주 (목포대학교 전기제어신소재공학부) ;
  • 최준호 (전남대학교 전기공학과)
  • Published : 2006.06.01

Abstract

Adaptive neural state-feedback controllers for the fully nonaffine pure-feedback nonlinear system are presented in this paper. By reformulating the original pure-feedback system to a standard normal form with respect to newly defined state variables, the proposed controllers require no backstepping design procedures. Avoiding backstepping makes the controller structure and stability analysis considerably to be simplified. The proposed controllers employ only one neural network to approximate unknown ideal controllers, which highlights the simplicity of the proposed neural controller.

Keywords