Learn More
Abstracr-Layered neural networks are used in a nonlinear self-toning adaptive control problem. The plant is an unknown feedback-hearimble discrete-time system, q " t e d by an input-ut model. To derive the linearizing-stabilizing feedback control, a @ossiMy n o " a l) state-space model of the plant is obtriwd. This model is used to define the zero dynamics,(More)
Abstruct-The cerebellar model articulation controller (CMAC) neural network is a practical tool for improving existing nonlinear control systems. A typical simulation study is used to clearly demonstrate that the CMAC can effectively reduce tracking error, but can also destabilize a control system which is otherwise stable. Then quantitative studies are(More)
n 2 N W 2 (t) = 0 for all t 2 [t 0 ; t n ], and at time t n queue 1 forms a homogeneous layer of size wn and composition a1 = 1; a J+3 = x n. Moreover, x n 2 I, hence w n n w 0 for some < 1, and t n tends to a finite limit, which completes the proof. APPENDIX B PROOF OF PROPOSITION 2.3 Set b = J+2 s=3 1 c. Assume that for some j; 0 j < J, the following(More)
A back-propagation neural network is applied to a nonlinear self-tuning tracking problem. Traditional self-tuning adaptive control techniques can only deal with linear systems or some special nonlin-ear systems. The emerging back-propagation neural networks have the capability to learn arbitrary nonlinearity and show great potential for adaptive control(More)