Convergence rates in stochastic adaptive tracking
Convergence rates in stochastic adaptive tracking
复制标题
DOI：
10.1080/00207178908559752
复制
发表时间：
1989-06
影响因子：
2.1
通讯作者：
Han-Fu Chen;Ji-feng Zhang
中科院分区：
文献类型：
--
作者：
Han-Fu Chen;Ji-feng Zhang
对于矩阵系数未知的ARMAX模型描述的随机控制系统，设计了随机自适应控制，使得参数估计以O((Logn)(Logn)c/na)的收敛速度O((Logn)(Logn)c/na)以a>；0，c>；1的收敛速度收敛到真值，跟踪误差以e>；0的速度O(n-1/2e)趋于最小值。
Abstract For stochastic control systems described by the ARMAX model with unknown matrix coefficients, the stochastic adaptive control is designed so that the parameter estimates converge to the true values with a rate of convergence O((log n)(log log n) c /n a) with a>0, c>1 and the tracking error tends to its minimum value at a speed of O(n -1/2e) with e>0.