Adaptive Control of Nonlinear Discrete-Time Systems Using Neural Networks and Least Squares Algorithm with Dead-Zone
Xie Xuejun
Wang Yuan
Abstract：Multilayer neural networks are used in a nonlinear discrete-time adaptive control problem.The weights of the neural networks are updated by using least squares (LS) algorithm with dead-zone.LS algorithm has much superior rate of convergence compared with gradient algorithm and δ-modification algorithm.For the adaptive control algorithm,we prove that: 1) all signals in the closed-loop systems are bounded;and 2) the tracking error converges to a bounded ball.
Keywords：Nonlinear systemsmultilayer neural networksleast squares algorithm with dead-zoneadaptive control
Publication Date：1999-01-01
Online Publishing Date：2025-08-15(First online date of this platform, not the publication date of the document)
Pages：6( 355-360 )