Some new results on system identification with dynamic neural networks

作者: Wen Yu , Xiaoou Li

DOI: 10.1109/72.914535

关键词:

摘要: Nonlinear system online identification via dynamic neural networks is studied in this paper. The main contribution of the paper that passivity approach applied to access several new stable properties neuro identification. conditions for passivity, stability, asymptotic and input-to-state stability are established certain senses. We conclude gradient descent algorithm weight adjustment an L/sub /spl infin// sense robust any bounded uncertainties.

参考文章(17)
K.J. Hunt, D. Sbarbaro, R. Żbikowski, P.J. Gawthrop, Neural networks for control systems: a survey Automatica. ,vol. 28, pp. 1083- 1112 ,(1992) , 10.1016/0005-1098(92)90053-I
W. Yu, A.S. Poznyak, Indirect adaptive control via parallel dynamic neural networks IEE Proceedings - Control Theory and Applications. ,vol. 146, pp. 25- 30 ,(1999) , 10.1049/IP-CTA:19990368
J. Willems, Least squares stationary optimal control and the algebraic Riccati equation IEEE Transactions on Automatic Control. ,vol. 16, pp. 621- 634 ,(1971) , 10.1109/TAC.1971.1099831
Wen Yu, Xiaoou Li, Some stability properties of dynamic neural networks IEEE Transactions on Circuits and Systems I-regular Papers. ,vol. 48, pp. 256- 259 ,(2001) , 10.1109/81.904893
Jing Sun, Petros A. Ioannou, Robust Adaptive Control ,(1995)
C.I. Byrnes, A. Isidori, J.C. Willems, Passivity, feedback equivalence, and the global stabilization of minimum phase nonlinear systems IEEE Transactions on Automatic Control. ,vol. 36, pp. 1228- 1240 ,(1991) , 10.1109/9.100932
M. Forti, S. Manetti, M. Marini, Necessary and sufficient condition for absolute stability of neural networks IEEE Transactions on Circuits and Systems I-regular Papers. ,vol. 41, pp. 491- 494 ,(1994) , 10.1109/81.298364
E. Kaszkurewicz, A. Bhaya, On a class of globally stable neural circuits IEEE Transactions on Circuits and Systems I-regular Papers. ,vol. 41, pp. 171- 174 ,(1994) , 10.1109/81.269055