Title :
Optimal experiment design for wavelet-based system identification
Author :
Long, Tujing ; Sun, Zhengshun ; Li, Chunwen
Author_Institution :
Dept. of Autom., Tsinghua Univ., Beijing, China
Abstract :
In this paper we proposed a method for optimal experiment design in system identification. By using the wavelet multiresolution theory to the least-squares system identification, and associating with the control performance index of the closed-loop system, we presented a method for optimal identification input signal design. This method is a control-relevant identification method, and it can get better results compared to the existing system identification methods. The simulation result proves the effectiveness of the proposed method.
Keywords :
closed loop systems; design of experiments; identification; least squares approximations; optimisation; performance index; wavelet transforms; closed-loop system; least-squares system identification; optimal experiment design; optimal identification input signal design; performance index; wavelet multiresolution theory; wavelet-based system identification; Automatic control; Design automation; Optimal control; Performance analysis; Signal design; Signal resolution; Sun; System identification; Wavelet analysis;
Conference_Titel :
Intelligent Control and Automation, 2002. Proceedings of the 4th World Congress on
Print_ISBN :
0-7803-7268-9
DOI :
10.1109/WCICA.2002.1022073
