| 多维滑动和（MA）模型参数的自适应估计 |
| |
| 引用本文： | 茅宁,张良起.多维滑动和（MA）模型参数的自适应估计[J].控制理论与应用,1990,7(4):29-36. |
| |
| 作者姓名： | 茅宁 张良起 |
| |
| 作者单位： | 国防科技大学自控系 长沙
(茅宁)，国防科技大学自控系 长沙(张良起) |
| |
| 摘 要： | 本文利用AR模型LS梯格滤波的有关公式给出了实时辨识多维MA模型参数的递推算法,该算法建立在对模型噪声和观测的自协方差阵和互协方差阵的矩估计基础上,由一个N阶反馈形式的梯格滤波器构成,可关于时间和阶次双重递推,该算法计算量为O(N)的量级,并具备梯格滤波固有的良好数值及结构特性。
|
| 关 键 词： | 多维滑动 MA模型参数 自适应估计 |
| 收稿时间： | 1988/12/28 0:00:00 |
| 修稿时间： | 7/8/1989 12:00:00 AM |
The Adaptive Estimation of the Parameters of a Vector Moving Average (MA) Model |
| |
| Mao Ning,Chang Liangqi.The Adaptive Estimation of the Parameters of a Vector Moving Average (MA) Model[J].Control Theory & Applications,1990,7(4):29-36. |
| |
| Authors: | Mao Ning Chang Liangqi |
| |
| Affiliation: | Mao Ning Chang LiangqiDepartment of Automatic Control,National University of Defence Technology |
| |
| Abstract: | A new recursive algorithm fur tbe on line identification of the parameters of a vector moving average (MA) model is presented by using the results of the LS ladder filtering for an autoregressive (AR) model. It is based on the moment estimation of auto-and cross-covariance matrice of the model noise and observation. The scheme can be represented in a feedback ladder form of order N,recursive both in time and order. The algorithm requires 0(N) operations per input sample and preserves the advantages of nice numerical and structual properties of the LS ladder algorithm. |
| |
| Keywords: | system identification parameter estimation moving average (MA) model LS ladder filtering recursive |
| 本文献已被 CNKI 维普 等数据库收录！ |
| 点击此处可从《控制理论与应用》浏览原始摘要信息 |
|
点击此处可从《控制理论与应用》下载全文 |
