Title :
On-line identification of nonlinear systems using adaptive matching pursuit
Author :
Shmilovici, Armin ; Maimon, Oded
Author_Institution :
Dept. of Manuf. Eng., Boston Univ., MA, USA
Abstract :
A reduced complexity algorithm, which is an adaptive version of the matching pursuit algorithm, is proposed for the identification of nonlinear systems. The algorithm is demonstrated on various nonlinear systems presented in the literature. The results are favorable compared to other nonlinear identification methods (e.g neural nets). It is demonstrated that the algorithm could be used for the design of adaptive controllers
Keywords :
adaptive control; adaptive filters; adaptive signal processing; computational complexity; identification; nonlinear control systems; adaptive controllers; adaptive matching pursuit; matching pursuit algorithm; nonlinear systems; on-line identification; reduced complexity algorithm; Adaptive control; Adaptive filters; Adaptive systems; Dictionaries; Matching pursuit algorithms; Neural networks; Nonlinear systems; Programmable control; Pursuit algorithms; Vectors;
Conference_Titel :
Electrical and Electronics Engineers in Israel, 1996., Nineteenth Convention of
Conference_Location :
Jerusalem
Print_ISBN :
0-7803-3330-6
DOI :
10.1109/EEIS.1996.567025
