제어로봇시스템학회:학술대회논문집

Institute of Control, Robotics and Systems (제어로봇시스템학회)
권호 표지

A study on an identification procedure for control of nonlinear plants using neural networks

  • Lee, In-Soo (Dept. of Eletronics, Kyungpook National University, Taegu, Korea and Eng. Research Center for Adv. control and Instr. of SNU by KOSEF) ;
  • Jeon, Gi-Joon (Dept. of Eletronics, Kyungpook National University, Taegu, Korea and Eng. Research Center for Adv. control and Instr. of SNU by KOSEF)
  • Published : 1993.10.01
Download PDF
⟨ Previous Next ⟩

Abstract

A new learning method of both NNI and NNC by which the NNI identifies precisely the dynamic characteristics of the plant is proposed. For control of ihe nonlinear plant we use two neural networks, one -for identification and the other for control. We define a closed loop en-or which depends on identification and control error. In the proposed learning method, the closed loop en-or is utilized to train the NNI and the NNC. Computer simulation results reveal that the NNC based on proposed method is insensitive to variations of the plant parameters.

Keywords