EDA365欢迎您登录!
您需要 登录 才可以下载或查看,没有帐号?注册
x
Neural Network Inverse Adaptive Controller Based or,Davidon Least Square*
0 j/ I/ a2 Z; _! U2 ?) B* [9 lChen Zengqiang, Lu Zhao & Yuan Zhtuzhi
7 M {7 Q9 ^. n" eDepartment of Computer & System Science, Nankai Univeraity, Tianjin, 300071, P. R. China ! f2 O. g3 r2 z6 L. V
(Received September 20, 1999) ! [" S7 \. ?: z1 L% d! y' D8 ?; A( x
- c$ E* s- H: ]5 t- tAbstract: General neural network inverse adaptive controller haw two flaws: the first i the slow convergence speed; the second is the invalidation to the non-minimum phase mystem. Tbese defects limit the scope in which the neural network inverse adaptive controller is used. We employ Davidon least squares in training the multi-layer feedforward neural network used in approximating the invense model of plant to expedite the convergence, and then through constructing the pseudo-plant, a neural network inverse adaptive controller泅put forward which is stil efective to the nonlinear non-minimum phase system. The simulation reoults show the validity of this scheme.2 _. y. d% n% l
) Z8 m( h' c8 f; V, Z. c5 T( {$ ?Keywords: Neural network, Adaptive control, Davidon least squarea, Inverse control.; Z9 g/ {2 h2 V: @7 V( Y
9 B5 q( ~* P' }, {3 G- H) ~
: B1 m& r. t4 m7 D. Q. z4 e, r2 ~1 G/ A" ^3 j4 o' F7 B
, {2 h. l( }9 l) n$ C5 g
/ ?- [% e' j9 W! Y6 K |